MIND-Mem

Replayable memory for AI agents. Deterministic recall with a byte-identical audit chain across runs, machines, and substrates.

Built on the MIND substrate • Governed-write • Deterministic recall • 84 MCP tools
_{MIND Language Profile: default (full tensor stdlib + Q16.16 + heap) — see Phase 10.6}

_{Current release: v4.0.17 —
see CHANGELOG
(single source of truth; per-version detail tables below may lag the changelog)}

Built on the MIND substrate. Governed-write (propose → review → approve_apply). Deterministic recall. 84 MCP tools as the surface — but the differentiator is the substrate underneath. On the same workspace, recall is deterministic (same query → same ranked results) and every block and audit hash is byte-identical across every architecture mind-mem builds on — the Q16.16 audit chain. (The ranking scores themselves are standard floating-point; the byte-identity guarantee is the audit/replay chain.)

Most memory layers ship tools. That is table-stakes. MIND-Mem ships a substrate: Q16.16 fixed-point scoring kernels compiled from MIND source, a governance pipeline that rejects every unreviewed write, and an audit chain where every applied proposal is hash-anchored. The same query on the same workspace produces the same ranked recall, every time; that recall's audit/replay chain is byte-identical whether you replay it on the same machine or a different one that pulls the same workspace. That property is what makes MIND-Mem suitable as a canonical memory layer across heterogeneous agent stacks.

If your agent runs for weeks, it will drift. MIND-Mem prevents silent drift.

MIND-Mem powers the Memory Plane of the MIND Cognitive Kernel — the deterministic AI runtime architecture.

30-Second Demo

pip install mind-mem
mind-mem-init ~/my-workspace        # Create workspace
mind-mem-recall -q "API decisions" --workspace ~/my-workspace  # Hybrid BM25F search
mind-mem-scan ~/my-workspace        # Detect drift & contradictions

Output:

[1.204] D-20260215-001 (decision) — Use async/await for all API endpoints
        decisions/DECISIONS.md:11
[1.094] D-20260210-003 (decision) — REST over GraphQL for public API
        decisions/DECISIONS.md:20

_{Current release: v4.0.17 — Full per-release notes (issues closed, CI run ids, job counts) live in CHANGELOG.md.}

Substrate Properties

Property	What it means
Byte-identical replay	Deterministic recall: same workspace + query → same ranked results, every time. The audit/replay chain (Q16.16) is byte-identical across machines. No probabilistic mutations in the core.
Governed-write	Nothing reaches the source of truth without `propose → review → approve_apply`. No silent mutations. Ever.
Auditable	Every apply logged with timestamp, receipt, and DIFF. Full traceability from signal to decision.
Deterministic	No ML in the retrieval core. Q16.16 fixed-point scoring. The same preimage produces the same hash.
Local-first	All data stays on disk. No cloud calls, no telemetry, no phoning home.
No vendor lock-in	Plain Markdown files. Move to any system, any time.
Zero infrastructure	Core requires only Python 3.10+ stdlib. Postgres, Redis, Docker, and GPU are opt-in extras.
100% NIAH	250/250 Needle In A Haystack retrieval. Every needle, every depth, every size.

docs/setup.md — install, configure, wire MCP, opt in to MIND native kernels
docs/usage.md — every surface (MCP tools by category, mm CLI, mind-mem-verify, Python library) with worked examples
docs/client-integrations.md — 18 AI client integrations (Claude Code, Codex, Grok Build, Vibe, Gemini, Cursor, Windsurf, aider, OpenClaw, NanoClaw, NemoClaw, Continue, Cline, Roo, Zed, Copilot, Cody, Qodo) with mm install-all auto-detection
docs/mind-mem-4b-setup.md — download + run the star-ga/mind-mem-4b full-FT model locally (transformers, exllamav2, vLLM, llama.cpp, Ollama, MindLLM)
docs/companion-tools.md — companion tools that complement (not compete with) mind-mem: MindLLM for deterministic + evidence-chained inference, GitNexus for code knowledge-graph
ROADMAP.md — feature roadmap (genuinely-open items at the top; bulk of v3.2.0→v4.0.0 shipped)
CHANGELOG.md — release notes for every published version

Why MIND-Mem

Most memory plugins store and retrieve. That's table stakes.

MIND-Mem also detects when your memory is wrong — contradictions between decisions, drift from informal choices never formalized, dead decisions nobody references, orphan tasks pointing at nothing — and offers a safe path to fix it.

Problem	Without MIND-Mem	With MIND-Mem
Contradicting decisions	Follows whichever seen last	Flags, links both, proposes fix
Informal chat decision	Lost after session ends	Auto-captured, proposed to formalize
Stale decision	Zombie confuses future sessions	Detected as dead, flagged
Orphan task reference	Silent breakage	Caught in integrity scan
Scattered recall quality	Single-mode search misses context	Hybrid BM25+Vector+RRF fusion finds it
Ambiguous query intent	One-size-fits-all retrieval	9-type intent router optimizes parameters

Novel Contributions

MIND-Mem introduces several techniques not found in existing memory systems:

Technique	What's new	Why it matters
Co-retrieval graph	PageRank-like score propagation across blocks frequently retrieved together	Surfaces structurally relevant blocks with zero lexical overlap (+2.0pp accuracy)
Fact card sub-block indexing	Atomic fact extraction → small-to-big retrieval with parent score blending	Catches fine-grained facts that full-block BM25 misses (+2.6pp accuracy)
Adaptive knee cutoff	Score-drop-based truncation instead of fixed top-K	Eliminates noise that hurts LLM judges — returns 3-15 results adaptively
Hard negative mining	Logs BM25-high / cross-encoder-low blocks as misleading, penalizes in future queries	Self-improving retrieval: precision increases over time without retraining
Deterministic abstention	Pre-LLM confidence gate using 5-signal scoring (entity, BM25, speaker, evidence, negation)	Prevents hallucinated answers to unanswerable questions — no ML required
Governance pipeline	Contradiction detection + drift analysis + safe apply with audit trail	Only memory system that detects when stored knowledge is wrong
Agent-agnostic shared memory	Single MCP workspace shared across Claude Code, Codex, Gemini, Cursor, Windsurf, Zed	Memory compounds across tools instead of fragmenting

Features

Hybrid BM25+Vector Search with RRF Fusion

Thread-parallel BM25 and vector search with Reciprocal Rank Fusion (k=60). Configurable weights per signal. Vector is optional — works with just BM25 out of the box.

RM3 Dynamic Query Expansion

Pseudo-relevance feedback using JM-smoothed language models. Expands queries with top terms from initial result set. Falls back to static synonyms for adversarial queries. Zero dependencies.

9-Type Intent Router

Classifies queries into WHY, WHEN, ENTITY, WHAT, HOW, LIST, VERIFY, COMPARE, or TRACE. Each intent type maps to optimized retrieval parameters (limits, expansion settings, graph traversal depth).

A-MEM Metadata Evolution

Auto-maintained per-block metadata: access counts, importance scores (clamped to [0.8, 1.5] reranking boost), keyword evolution, and co-occurrence tracking. Importance decays with exponential recency.

Deterministic Reranking

Four-signal reranking pipeline: negation awareness (penalizes contradicting results), date proximity (Gaussian decay), 20-category taxonomy matching, and recency boosting. No ML required.

Optional Cross-Encoder

Drop-in ms-marco-MiniLM-L-6-v2 cross-encoder (80MB). Blends 0.6 * CE + 0.4 * original score. Falls back gracefully when unavailable. Enabled via config.

MIND Kernels (Optional, Native Speed — forward-looking)

26 .mind configuration files at mind/ that tune the scoring pipeline (BM25F, RRF fusion, reranking, negation penalty, date proximity, category boost, importance, entity overlap, confidence, top-k, weighted rank, category affinity, query-category relevance, category assignment, and others). Currently INI-format declarative configuration parsed by mind_ffi.py; the MIND-language port that compiles to native .so via the MIND compiler is the forward-looking story — see docs/MIND_CONFIG_VS_MIND_LANG.md for the disambiguation. The pure-Python scoring logic in src/mind_mem/mind_kernels.py is the authoritative implementation today.

MIC/MAP — MIND IR graph serialization

Pure-Python codec for the STARGA wire formats: mic@2 (line-oriented text, LLM-readable, git-friendly) and MIC-B (varint binary, ~4× smaller). Both encode typed dataflow graphs (symbols + types + values + output) with byte-identical round-trip. Streaming parser for bounded peak memory; optional Cython accelerator via mind-mem[accelerated] (+16/+20/+36 % on parse). Two MCP tools (mic_convert, mic_inspect) and a mm mic CLI surface it for agents and operators. See docs/mic-map.md. Note that the canonical IR per RFC 0021 is mic@1 text + mic@3 binary (see mindlang.dev/docs/mic); the mic@2/MIC-B codec mind-mem ships is the back-compat lineage.

BM25F Hybrid Recall

BM25F field-weighted scoring (k1=1.2, b=0.75) with per-field weighting (Statement: 3x, Title: 2.5x, Name: 2x, Summary: 1.5x), Porter stemming, bigram phrase matching (25% boost per hit), overlapping sentence chunking (3-sentence windows with 1-sentence overlap), domain-aware query expansion, and optional 2-hop graph-based cross-reference neighbor boosting. Zero dependencies. Fast and deterministic.

Graph-Based Recall

2-hop cross-reference neighbor boosting — when a keyword match is found, blocks that reference or are referenced by the match get boosted (1-hop: 0.3x decay, 2-hop: 0.1x decay). Surfaces related decisions, tasks, and entities that share no keywords but are structurally connected. Auto-enabled for multi-hop queries.

Vector Recall (optional)

Pluggable embedding backend — local ONNX (all-MiniLM-L6-v2, no server needed) or cloud (Pinecone). Falls back to BM25 when unavailable.

Persistent Memory

Structured, validated, append-only decisions / tasks / entities / incidents with provenance and supersede chains. Plain Markdown files — readable by humans, parseable by machines.

Immune System

Continuous integrity checking: contradictions, drift, dead decisions, orphan tasks, coverage scoring, regression detection. 74+ structural validation rules.

Safe Governance

All changes flow through graduated modes: detect_only → propose → enforce. Apply engine with snapshot, receipt, DIFF, and automatic rollback on validation failure.

Adversarial Abstention Classifier

Deterministic pre-LLM confidence gate for adversarial/verification queries. Computes confidence from entity overlap, BM25 score, speaker coverage, evidence density, and negation asymmetry. Below threshold → forces abstention without calling the LLM, preventing hallucinated answers to unanswerable questions.

Auto-Capture with Structured Extraction

Session-end hook detects decision/task language (26 patterns with confidence classification), extracts structured metadata (subject, object, tags), and writes to SIGNALS.md only. Never touches source of truth directly. All signals go through /apply.

Concurrency Safety

Cross-platform advisory file locking (fcntl/msvcrt/atomic create) protects all concurrent write paths. Stale lock detection with PID-based cleanup. Zero dependencies.

Compaction & GC

Automated workspace maintenance: archive completed blocks, clean up old snapshots, compact resolved signals, archive daily logs into yearly files. Configurable thresholds with dry-run mode.

Observability

Structured JSON logging (via stdlib), in-process metrics counters, and timing context managers. All scripts emit machine-parseable events. Controlled via MIND_MEM_LOG_LEVEL env var.

Multi-Agent Namespaces & ACL

Workspace-level + per-agent private namespaces with JSON-based ACL. fnmatch pattern matching for agent policies. Shared fact ledger for cross-agent propagation with dedup and review gate.

Automated Conflict Resolution

Graduated resolution pipeline: timestamp priority, confidence priority, scope specificity, manual fallback. Generates supersede proposals with integrity hashes. Human veto loop — never auto-applies without review.

Write-Ahead Log (WAL) + Backup/Restore

Crash-safe writes via journal-based WAL. Full workspace backup (tar.gz), git-friendly JSONL export, selective restore with conflict detection and path traversal protection.

Transcript JSONL Capture

Scans Claude Code transcript files for user corrections, convention discoveries, bug fix insights, and architectural decisions. 16 transcript-specific patterns with role filtering and confidence classification.

MCP Server (84 tools, 8 resources)

Full Model Context Protocol server with 84 tools and 8 read-only resources. Works with Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP-compatible client. HTTP and stdio transports; HTTP requires bearer-token auth (fail-closed) — see Token Auth (HTTP). v3.8.11 added mic_convert_tool / mic_inspect_tool (MIC/MAP wire format); v3.9.0 added compile_truth_walkthrough, recall_with_persona, pipeline_status, and reindex_dirty; v3.11.0 added validate_block, block_lineage, and add_block_edge (deterministic quality gates + typed lineage edges).

74+ Structural Checks + 3024 Unit Tests

validate.sh checks schemas, cross-references, ID formats, status values, supersede chains, ConstraintSignatures, and more. Backed by 3024 pytest unit tests covering all core modules.

Audit Trail

Every applied proposal logged with timestamp, receipt, and DIFF. Full traceability from signal → proposal → decision.

Calibration Feedback Loop

Per-block quality tracking with Bayesian weight computation. When users provide feedback (thumbs up/down) via calibration_feedback, the system maintains a rolling quality score per block over a 30-day window. Bayesian smoothing constrains calibration weights to the 0.5-1.5 range, preventing any single block from dominating or being silenced. Calibration weights integrate directly into the BM25 + FTS5 retrieval pipeline — high-quality blocks rank higher, low-quality blocks are naturally demoted. Use calibration_stats to inspect per-block quality distributions and global calibration health.

LLM-Guided Multi-Query Expansion

Generates semantically diverse query reformulations before search — synonym expansion, specificity shifts, temporal rephrasing, and negation variants. Combines all reformulated queries with Reciprocal Rank Fusion for broader recall without sacrificing precision. Runs locally with zero API calls.

4-Layer Search Deduplication

Post-retrieval dedup pipeline: best-chunk-per-source (keeps highest-scoring chunk from each file), cosine similarity dedup (>0.85 threshold), type diversity capping (max 3 results per block type), and per-source chunk limiting. Eliminates redundant results that waste LLM context.

LLM-Guided Smart Chunking

Content-aware chunking that splits at semantic boundaries (headers, paragraph breaks, list items, code blocks) instead of fixed character counts. Produces variable-size chunks with overlap for continuity. Supports markdown, code, and prose with format-specific splitting rules.

Compiled Truth Pages

Per-entity knowledge compilation: current-best-understanding on top, timestamped evidence trail below. Contradiction detection across evidence entries with automatic flagging. Entities accumulate knowledge from all sessions — each new evidence entry is checked against existing facts.

Dream Cycle (Autonomous Memory Enrichment)

Scheduled background enrichment: scans recent memory for missing cross-references, broken citations, orphan entities, and consolidation opportunities. Generates repair proposals for stale links, detects implicit entities not yet formalized, and compacts redundant entries. Runs during idle periods with configurable depth.

Feature Completeness Matrix

Capability	MIND-Mem	Mem0	Zep	Letta	LangMem
BM25 lexical search	Y	—	—	—	—
Vector semantic search	Y	Y	Y	Y	Y
Hybrid BM25+Vector+RRF	Y	—	—	—	—
Cross-encoder reranking	Y	—	—	—	—
Intent-aware routing (9 types)	Y	—	—	—	—
RM3 query expansion	Y	—	—	—	—
Co-retrieval graph (PageRank)	Y	—	—	—	—
Fact sub-block indexing	Y	—	—	—	—
Hard negative mining	Y	—	—	—	—
Adaptive knee cutoff	Y	—	—	—	—
Contradiction detection	Y	—	—	—	—
Drift analysis	Y	—	—	—	—
Governance pipeline (propose/apply)	Y	—	—	—	—
Multi-agent shared memory (MCP)	Y	—	—	Y	—
Zero core dependencies	Y	—	—	—	—
Local-only (no cloud required)	Y	—	—	—	—
Compiled native kernels (MIND)	Y	—	—	—	—
Backup/restore with zip-slip protection	Y	—	—	—	—
Multi-query expansion with RRF	Y	—	—	—	—
4-layer search deduplication	Y	—	—	—	—
Semantic-aware smart chunking	Y	—	—	—	—
Compiled truth pages (per-entity)	Y	—	—	—	—
Dream cycle (autonomous enrichment)	Y	—	—	—	—

Integrations are the substrate working

Because the substrate is deterministic, integrating with 17 different CLIs produces the same answers on each. That is not a coincidence — it is the point. MIND-Mem can be the canonical memory layer across heterogeneous agent stacks precisely because recall is deterministic and its audit/replay chain is byte-identical regardless of which client is asking. The 17-CLI surface is a consequence of the substrate, not a feature in itself.

Honest positioning: the integrations below are software-level — the named tool talks to MIND-Mem via the Model Context Protocol. They are not commercial-customer relationships with any vendor. Full positioning policy: docs/integrations.md.

Native MCP integration with 17 AI development tools

pip install mind-mem
mm install-all

mm install-all auto-detects every supported client on your machine and writes the appropriate config file for each. MIND-Mem speaks the Model Context Protocol — any MCP-compatible client connects with one command.

Client	Vendor	Client	Vendor
Claude Code	Anthropic	Cline	Cline.bot
Claude Desktop	Anthropic	Roo	Roo Code
Codex CLI	OpenAI	GitHub Copilot	GitHub / Microsoft
Grok Build CLI	xAI	Cody	Sourcegraph
Gemini CLI	Google
Vibe (Mistral CLI)	Mistral	Qodo	Qodo
Cursor	Anysphere	aider	aider-chat
Windsurf	Codeium	OpenClaw	OpenAI (Peter Steinberger)
Zed	Zed Industries	NemoClaw / Nemo	NVIDIA
Continue	Continue.dev	NanoClaw	Anthropic

Compatible with major LLM providers

MIND-Mem's recall pipeline is provider-agnostic. Tested against Anthropic Claude (3.5 Sonnet, 4.x), OpenAI GPT (4o, 5.4), Google Gemini (2.0 Flash, 3.1 Pro), Mistral Large, and local endpoints (Ollama, vLLM, llama.cpp). Compatibility is at the API contract level — the same MIND-Mem server returns the same answers regardless of which LLM is asking.

Production usage at STARGA

MIND-Mem is the daily-driver memory layer for STARGA's six active projects: mind, mind-runtime, mindlang.dev, mind-inference, mind-fleet, arch-mind. First-party, verifiable in our own commit history.

What we do not claim

❌ "OpenAI / Microsoft / Anthropic / Google is a customer" — false. These are software-level MCP integrations, not commercial relationships.
❌ "Used by N production teams outside STARGA" — we have no telemetry. PyPI download counts measure installs, not active use.

If a future integration becomes a real commercial relationship (signed contract, paid pilot, named reference), it will appear in the press release first — not in the README.

Benchmark Results

MIND-Mem's recall engine evaluated on standard long-term memory benchmarks using multiple configurations — from pure BM25 to full hybrid retrieval with neural reranking.

Needle In A Haystack (NIAH)

250/250 — 100% retrieval across all haystack sizes, burial depths, and needle types.

A single fact is planted at a controlled depth within a haystack of semantically diverse filler blocks. The system must retrieve the needle in its top-5 results using only a natural-language query.

Haystack Size	Depths Tested	Needles	Passed	Rate
10 blocks	0/25/50/75/100%	10	50/50	100%
50 blocks	0/25/50/75/100%	10	50/50	100%
100 blocks	0/25/50/75/100%	10	50/50	100%
250 blocks	0/25/50/75/100%	10	50/50	100%
500 blocks	0/25/50/75/100%	10	50/50	100%

Config: Hybrid BM25 + BAAI/bge-large-en-v1.5 + RRF (k=60) + sqlite-vec. Full details: benchmarks/NIAH.md

LoCoMo LLM-as-Judge

Same pipeline as Mem0 and Letta evaluations: retrieve context, generate answer with LLM, score against gold reference with judge LLM. Directly comparable methodology.

v1.0.7 — Hybrid + top_k=18 (Mistral answerer + judge, conv-0, 199 questions):

Category	N	Acc (>=50)	Mean Score
Overall	199	92.5%	76.7
Adversarial	47	97.9%	89.8
Multi-hop	37	91.9%	74.3
Open-domain	70	92.9%	72.7
Temporal	13	92.3%	76.2
Single-hop	32	84.4%	68.9

Pipeline: BM25 + Qwen3-Embedding-8B (4096d) vector search → RRF fusion (k=60) → top-18 evidence blocks → observation compression → answer → judge. A/B validated: +2.8 mean vs top_k=10 baseline.

v1.1.1 — BM25 + top_k=18 (Mistral Large answerer + judge, 10 conversations, 1986 questions):

Category	N	Acc (>=50)	Mean Score
Overall	1986	73.8%	70.5
Adversarial	446	92.4%	87.2
Single-hop	282	80.9%	68.7
Open-domain	841	71.2%	70.3
Temporal	96	66.7%	65.9
Multi-hop	321	50.5%	51.1

Pipeline: BM25 + RM3 query expansion → top-18 evidence blocks → observation compression → answer → judge. Full 10-conversation benchmark with Mistral Large as both answerer and judge.

v1.0.0 — BM25-only baseline (gpt-4o-mini answerer + judge, 10 conversations):

Category	N	Acc (>=50)	Mean Score
Overall	1986	67.3%	61.4
Open-domain	841	86.6%	78.3
Temporal	96	78.1%	65.7
Single-hop	282	68.8%	59.1
Multi-hop	321	55.5%	48.4
Adversarial	446	36.3%	39.5

Key improvements since v1.0.0: Adversarial accuracy tripled from 36.3% to 92.4% via abstention classifier + hybrid retrieval. Overall Acc≥50 improved from 67.3% to 73.8% (+6.5pp).

Competitive Landscape

System	Score	Approach
MIND-Mem	76.7%	Hybrid BM25 + Qwen3-8B vector + RRF fusion (local-only)
Memobase	75.8%	Specialized extraction
Letta	74.0%	Files + agent tool use
MIND-Mem	73.8%	BM25-only, full 10-conv (1986 questions, Mistral Large)
Mem0	68.5%	Graph + LLM extraction

MIND-Mem now surpasses Mem0 and Letta with local-only retrieval — no cloud calls, no graph DB, no LLM in the retrieval loop. MIND-Mem's unique value is governance (contradiction detection, drift analysis, audit trails) and agent-agnostic shared memory via MCP — areas these benchmarks don't measure.

Competitive Landscape (LoCoMo)

System	LoCoMo Acc>=50	Infrastructure	Dependencies
MIND-Mem (hybrid)	76.7%	Local-only	Zero core (optional: llama.cpp, sentence-transformers)
Memobase	75.8%	Cloud + GPU	embeddings + vector DB
Letta	74.0%	Cloud	embeddings + vector DB
MIND-Mem (BM25)	73.8%	Local-only	Zero core
full-context	72.9%	N/A	LLM context window
Mem0	68.5%	Cloud (managed)	graph DB + embeddings

MIND-Mem surpasses Mem0 (68.5%), Letta (74.0%), and Memobase (75.8%) with zero cloud infrastructure. Full 10-conversation benchmark (1986 questions) validates this at scale. Note: benchmarks measure retrieval accuracy. The substrate properties (byte-identical replay, governed-write, audit chain) are not captured by any of these benchmarks — they are properties of the architecture, not the recall scores.

LongMemEval (held pending reconciliation)

Provenance hold active. The LongMemEval R@5 numbers below are pending reconciliation against a higher-iteration run. They are not part of the MIND-Mem positioning until the hold is resolved. See benchmarks/STATUS.md for the current status and methodology.

Category	N	R@1	R@5	R@10	MRR
Overall	470	73.2	(held)	88.1	.784
Multi-session	121	83.5	(held)	95.9	.885
Temporal	127	76.4	(held)	92.9	.826
Knowledge update	72	80.6	(held)	91.7	.844
Single-session	56	82.1	(held)	89.3	.847

Performance (Latency & Throughput)

Measured on a 65-block workspace (typical personal workspace) with SQLite FTS5 backend:

Operation	Metric	Value
Query (FTS5 + rerank)	p50 latency	2.1 ms
Query (FTS5 + rerank)	p95 latency	4.9 ms
Query (FTS5 + rerank)	mean latency	2.6 ms
Incremental reindex	elapsed	32 ms (13 blocks indexed)
Full index build	elapsed	48 ms (65 blocks)
MCP tool overhead	stdio round-trip	< 15 ms
Memory footprint	RSS (idle MCP server)	~28 MB

Query latency scales as O(log N) with SQLite FTS5 (vs O(corpus) for scan backend). The co-retrieval graph adds < 1ms per query. Knee cutoff and fact aggregation add negligible overhead (< 0.5ms).

Run Benchmarks Yourself

# Retrieval-only (R@K metrics)

## Install in 3 commands

```bash
pip install mind-mem
mm install-all --force      # auto-wires every detected AI CLI
mm install-model            # downloads mind-mem-4b GGUF + imports to Ollama

Full options + Postgres setup + troubleshooting: docs/install-guide.md

python3 benchmarks/locomo_harness.py python3 benchmarks/longmemeval_harness.py

LLM-as-judge (accuracy metrics, requires API key)

python3 benchmarks/locomo_judge.py --dry-run python3 benchmarks/locomo_judge.py --answerer-model gpt-4o-mini --output results.json

Hybrid retrieval with any model pair (BM25 + vector + cross-encoder)

python3 benchmarks/locomo_judge.py --hybrid --compress --answerer-model mistral-large-latest --judge-model mistral-large-latest --output results.json

Selective conversations

python3 benchmarks/locomo_harness.py --conv-ids 4,7,8


---

## Quick Start

### One-line install (recommended)

```bash
pipx install "mind-mem[mcp]"
mind-mem-mcp --help          # smoke-test

pipx keeps MIND-Mem in its own venv, exposes the mind-mem-mcp console script on PATH, and avoids polluting your system Python. If you don't have pipx, pip install --user "mind-mem[mcp]" works too.

Then wire it into every AI coding client on your machine:

git clone https://github.com/star-ga/mind-mem.git
cd mind-mem
./install.sh --all --no-install   # Already installed via pipx, just wire clients

Or do both in one shot (the installer will auto-pick pipx if available, else fall back to pip):

git clone https://github.com/star-ga/mind-mem.git
cd mind-mem
./install.sh --all

This auto-detects every AI coding client on your machine and configures MIND-Mem for all of them. Each client launches the same mind-mem-mcp binary, so all agents share one workspace. Supported clients:

Client	Config Location	Format
Claude Code CLI	`~/.claude/mcp.json`	JSON
Claude Desktop	`~/.config/Claude/claude_desktop_config.json`	JSON
Codex CLI (OpenAI)	`~/.codex/config.toml`	TOML
Gemini CLI (Google)	`~/.gemini/settings.json`	JSON
Cursor	`~/.cursor/mcp.json`	JSON
Windsurf	`~/.codeium/windsurf/mcp_config.json`	JSON
Zed	`~/.config/zed/settings.json`	JSON
OpenClaw	`~/.openclaw/hooks/mind-mem/`	JS hook

Selective install:

./install.sh --claude-code --codex --gemini         # Only specific clients
./install.sh --all --workspace ~/my-project/memory  # Custom workspace path

Uninstall:

./uninstall.sh          # Remove from all clients (keeps workspace data)
./uninstall.sh --purge  # Remove everything including workspace data

Manual Setup

For manual or per-project setup:

1. Clone into your project

cd /path/to/your/project
git clone https://github.com/star-ga/mind-mem.git .mind-mem

2. Initialize workspace

python3 .mind-mem/src/mind_mem/init_workspace.py .

Creates 12 directories, 19 template files, and mind-mem.json config. Never overwrites existing files.

3. Validate

bash .mind-mem/src/mind_mem/validate.sh .
# or cross-platform:
python3 .mind-mem/src/mind_mem/validate_py.py .

Expected: 74 checks | 74 passed | 0 issues.

4. First scan

python3 .mind-mem/src/mind_mem/intel_scan.py .

Expected: 0 critical | 0 warnings on a fresh workspace.

5. Verify recall + capture

python3 .mind-mem/src/mind_mem/recall.py --query "test" --workspace .
# → No results found. (empty workspace — correct)

python3 .mind-mem/src/mind_mem/capture.py .
# → capture: no daily log for YYYY-MM-DD, nothing to scan (correct)

6. Add hooks (optional)

Option A: Claude Code hooks (recommended)

Merge into your .claude/hooks.json:

{
  "hooks": [
    {
      "event": "SessionStart",
      "command": "bash .mind-mem/hooks/session-start.sh"
    },
    {
      "event": "Stop",
      "command": "bash .mind-mem/hooks/session-end.sh"
    }
  ]
}

Option B: OpenClaw hooks (for OpenClaw 2026.2+)

cp -r .mind-mem/hooks/openclaw/mind-mem ~/.openclaw/hooks/mind-mem
openclaw hooks enable mind-mem

7. Smoke Test (optional)

bash .mind-mem/src/mind_mem/smoke_test.sh

Creates a temp workspace, runs init → validate → scan → recall → capture → pytest, then cleans up.

Health Summary

After setup, this is what a healthy workspace looks like:

$ python3 -m mind_mem.intel_scan .

mind-mem Intelligence Scan Report v2.0
Mode: detect_only

=== 1. CONTRADICTION DETECTION ===
  OK: No contradictions found among 25 signatures.

=== 2. DRIFT ANALYSIS ===
  OK: All active decisions referenced or exempt.
  INFO: Metrics: active_decisions=17, active_tasks=7, blocked=0,
        dead_decisions=0, incidents=3, decision_coverage=100%

=== 3. DECISION IMPACT GRAPH ===
  OK: Built impact graph: 11 decision(s) with edges.

=== 4. STATE SNAPSHOT ===
  OK: Snapshot saved.

=== 5. WEEKLY BRIEFING ===
  OK: Briefing generated.

TOTAL: 0 critical | 0 warnings | 16 info

Commands

Command	What it does
`/scan`	Run integrity scan — contradictions, drift, dead decisions, impact graph, snapshot, briefing
`/apply`	Review and apply proposals from scan results (dry-run first, then apply)
`/recall <query>`	Search across all memory files with ranked results (add `--graph` for cross-reference boosting)

Architecture

your-workspace/
├── mcp_server.py            # MCP server (FastMCP, 81 tools, 8 resources)
├── mind-mem.json             # Config
├── MEMORY.md                # Protocol rules
│
├── mind/                    # 26 INI-style config files (.mind, see docs/MIND_CONFIG_VS_MIND_LANG.md)
│   ├── bm25.mind           # BM25F scoring kernel
│   ├── rrf.mind            # Reciprocal Rank Fusion kernel
│   ├── reranker.mind        # Deterministic reranking
│   ├── abstention.mind      # Confidence gating
│   ├── ranking.mind         # Evidence ranking
│   ├── importance.mind      # A-MEM importance scoring
│   ├── category.mind        # Category relevance scoring
│   ├── recall.mind          # Combined recall scoring
│   ├── hybrid.mind          # BM25 + vector hybrid fusion
│   ├── rm3.mind             # RM3 pseudo-relevance feedback
│   ├── rerank.mind          # Score combination pipeline
│   ├── adversarial.mind     # Adversarial query detection
│   ├── temporal.mind        # Time-aware scoring
│   ├── prefetch.mind        # Context pre-assembly
│   ├── intent.mind          # Intent classification
│   └── cross_encoder.mind   # Cross-encoder blending
│
├── lib/                     # Compiled MIND kernels (optional)
│   └── libmindmem.so       # mindc output — not required for operation
│
├── decisions/
│   └── DECISIONS.md         # Formal decisions [D-YYYYMMDD-###]
├── tasks/
│   └── TASKS.md             # Tasks [T-YYYYMMDD-###]
├── entities/
│   ├── projects.md          # [PRJ-###]
│   ├── people.md            # [PER-###]
│   ├── tools.md             # [TOOL-###]
│   └── incidents.md         # [INC-###]
│
├── memory/
│   ├── YYYY-MM-DD.md        # Daily logs (append-only)
│   ├── intel-state.json     # Scanner state + metrics
│   └── maint-state.json     # Maintenance state
│
├── summaries/
│   ├── weekly/              # Weekly summaries
│   └── daily/               # Daily summaries
│
├── intelligence/
│   ├── CONTRADICTIONS.md    # Detected contradictions
│   ├── DRIFT.md             # Drift detections
│   ├── SIGNALS.md           # Auto-captured signals
│   ├── IMPACT.md            # Decision impact graph
│   ├── BRIEFINGS.md         # Weekly briefings
│   ├── AUDIT.md             # Applied proposal audit trail
│   ├── SCAN_LOG.md          # Scan history
│   ├── proposed/            # Staged proposals + resolution proposals
│   │   ├── DECISIONS_PROPOSED.md
│   │   ├── TASKS_PROPOSED.md
│   │   ├── EDITS_PROPOSED.md
│   │   └── RESOLUTIONS_PROPOSED.md
│   ├── applied/             # Snapshot archives (rollback)
│   └── state/snapshots/     # State snapshots
│
├── shared/                  # Multi-agent shared namespace
│   ├── decisions/
│   ├── tasks/
│   ├── entities/
│   └── intelligence/
│       └── LEDGER.md        # Cross-agent fact ledger
│
├── agents/                  # Per-agent private namespaces
│   └── <agent-id>/
│       ├── decisions/
│       ├── tasks/
│       └── memory/
│
├── mind-mem-acl.json        # Multi-agent access control
├── .mind-mem-wal/           # Write-ahead log (crash recovery)
│
└── src/mind_mem/
    ├── mind_ffi.py          # MIND FFI bridge (ctypes)
    ├── hybrid_recall.py     # Hybrid BM25+Vector+RRF orchestrator
    ├── block_metadata.py    # A-MEM metadata evolution
    ├── cross_encoder_reranker.py  # Optional cross-encoder
    ├── intent_router.py     # 9-type intent classification (adaptive)
    ├── recall.py            # BM25F + RM3 + graph scoring engine
    ├── recall_vector.py     # Vector/embedding backends
    ├── sqlite_index.py      # FTS5 + vector + metadata index
    ├── connection_manager.py # SQLite connection pool (WAL read/write separation)
    ├── block_store.py       # BlockStore protocol + MarkdownBlockStore
    ├── corpus_registry.py   # Central corpus path registry
    ├── abstention_classifier.py  # Adversarial abstention
    ├── evidence_packer.py   # Evidence assembly and ranking
    ├── intel_scan.py        # Integrity scanner
    ├── apply_engine.py      # Proposal apply engine (delta-based snapshots)
    ├── block_parser.py      # Markdown block parser (typed)
    ├── capture.py           # Auto-capture (26 patterns)
    ├── compaction.py        # Compaction/GC/archival
    ├── mind_filelock.py     # Cross-platform advisory file locking
    ├── observability.py     # Structured JSON logging + metrics
    ├── namespaces.py        # Multi-agent namespace & ACL
    ├── conflict_resolver.py # Automated conflict resolution
    ├── backup_restore.py    # WAL + backup/restore + JSONL export
    ├── transcript_capture.py  # Transcript JSONL signal extraction
    ├── validate.sh          # Structural validator (74+ checks)
    └── validate_py.py       # Structural validator (Python, cross-platform)

How It Compares

Quick Comparison

Feature	MIND-Mem	Mem0	Letta	Zep/Graphiti
Local-only	Yes	No (cloud API)	No (runtime)	No (Neo4j)
Zero infrastructure	Yes	No	No	No
Hybrid retrieval	BM25F + vector + RRF	Vector only	Hybrid	Graph + vector
Governance (propose/review/apply)	Yes	No	No	No
Contradiction detection	Yes	No	No	No
Tests	3,600+	-	-	-
LoCoMo benchmark	86.33 conv-0 (v3.6, Mistral-Large)	66.88	74.0%	-
MCP tools	81 (58 legacy + 7 dispatchers + 16 v3.7→v3.9 additions)	-	-	-
Core dependencies	0	Many	Many	Many

At a Glance

Tool	Strength	Trade-off
Mem0	Fast managed service, graph memory, multi-user scoping	Cloud-dependent, no integrity checking
Supermemory	Fastest retrieval (ms), auto-ingestion from Drive/Notion	Cloud-dependent, auto-writes without review
claude-mem	Purpose-built for Claude Code, ChromaDB vectors	Requires ChromaDB + Express worker, no integrity
Letta	Self-editing memory blocks, sleep-time compute, 74% LoCoMo	Full agent runtime (heavy), not just memory
Zep	Temporal knowledge graph, bi-temporal model, sub-second at scale	Cloud service, complex architecture
LangMem	Native LangChain/LangGraph integration	Tied to LangChain ecosystem
Cognee	Advanced chunking, web content bridging	Research-oriented, complex setup
Graphlit	Multimodal ingestion, semantic search, managed platform	Cloud-only, managed service
ClawMem	Full ML pipeline (cross-encoder + QMD + beam search)	4.5GB VRAM, 3 GPU processes required
MemU	Hierarchical 3-layer memory, multimodal ingestion, LLM-based retrieval	Requires LLM for extraction and retrieval, no hybrid search
MIND-Mem	Integrity + governance + zero core deps + hybrid search + MIND kernels + 84 MCP tools (incl. MIC/MAP, walkthrough, persona, pipeline-hash) + 10-LLM consensus audit per release	Lexical recall by default (vector/CE optional)

Full Feature Matrix

Compared against every major memory solution for AI agents (as of 2026):

	Mem0	Supermemory	claude-mem	Letta	Zep	LangMem	Cognee	Graphlit	ClawMem	MemU	MIND-Mem
Recall
Vector	Cloud	Cloud	Chroma	Yes	Yes	Yes	Yes	Yes	Yes	—	Optional
Lexical	Filter	—	—	—	—	—	—	—	BM25	—	BM25F
Graph	Yes	—	—	—	Yes	—	Yes	Yes	Beam	—	2-hop
Hybrid + RRF	Part	—	—	—	Yes	—	Yes	Yes	Yes	—	Yes
Cross-encoder	—	—	—	—	—	—	—	—	qwen3 0.6B	—	MiniLM 80MB
Intent routing	—	—	—	—	—	—	—	—	Yes	—	9 types
Query expansion	—	—	—	—	—	—	—	—	QMD 1.7B	—	RM3 (zero-dep)
Persistence
Structured	JSON	JSON	SQL	Blk	Grph	KV	Grph	Grph	SQL	Markdown	Markdown
Entities	Yes	Yes	—	Yes	Yes	Yes	Yes	Yes	—	Yes	Yes
Temporal	—	—	—	—	Yes	—	—	—	—	—	Yes
Supersede	—	—	—	Yes	Yes	—	—	—	—	—	Yes
Append-only	—	—	—	—	—	—	—	—	—	—	Yes
A-MEM metadata	—	—	—	—	—	—	—	—	Yes	—	Yes
Integrity
Contradictions	—	—	—	—	—	—	—	—	—	—	Yes
Drift detection	—	—	—	—	—	—	—	—	—	—	Yes
Validation	—	—	—	—	—	—	—	—	—	—	74+ rules
Impact graph	—	—	—	—	—	—	—	—	—	—	Yes
Coverage	—	—	—	—	—	—	—	—	—	—	Yes
Multi-agent	—	—	—	Yes	—	—	—	—	—	—	ACL-based
Conflict res.	—	—	—	—	—	—	—	—	—	—	Automatic
WAL/crash	—	—	—	—	—	—	—	—	—	—	Yes
Backup/restore	—	—	—	—	—	—	—	—	—	—	Yes
Abstention	—	—	—	—	—	—	—	—	—	—	Yes
Governance
Auto-capture	Auto	Auto	Auto	Self	Ext	Ext	Ext	Ing	Auto	LLM Ext	Propose
Proposal queue	—	—	—	—	—	—	—	—	—	—	Yes
Rollback	—	—	—	—	—	—	—	—	—	—	Yes
Mode governance	—	—	—	—	—	—	—	—	—	—	3 modes
Audit trail	—	Part	—	—	—	—	—	—	—	—	Full
Operations
Local-only	—	—	Yes	—	—	—	—	—	Yes	Yes	Yes
Zero core deps	—	—	—	—	—	—	—	—	—	—	Yes
No daemon	—	—	—	—	—	Yes	—	—	—	Yes	Yes
GPU required	—	—	—	—	—	—	—	—	4.5GB	No	No
Git-friendly	—	—	—	Part	—	—	—	—	—	Yes	Yes
MCP server	—	—	—	—	—	—	—	—	—	—	81 tools
MIND kernels	—	—	—	—	—	—	—	—	—	—	16 source

The Gap MIND-Mem Fills

Every tool above does storage + retrieval. None of them answer:

"Do any of my decisions contradict each other?"
"Which decisions are active but nobody references anymore?"
"Did I make a decision in chat that was never formalized?"
"What's the downstream impact if I change this decision?"
"Is my memory state structurally valid right now?"

MIND-Mem focuses on memory governance and integrity — the critical layer most memory systems ignore entirely.

Why Plain Files Outperform Fancy Retrieval

Letta's August 2025 analysis showed that a plain-file baseline (full conversations stored as files + agent filesystem tools) scored 74.0% on LoCoMo with gpt-4o-mini — beating Mem0's top graph variant at 68.5%. Key reasons:

LLMs excel at tool-based retrieval. Agents can iteratively query/refine file searches better than single-shot vector retrieval that might miss subtle connections.
Benchmarks reward recall + reasoning over storage sophistication. Strong judge LLMs handle the rest once relevant chunks are loaded.
Overhead hurts. Specialized pipelines introduce failure modes (bad embeddings, chunking errors, stale indexes) that simple file access avoids.
For text-heavy agentic use cases, "how well the agent manages context" > "how smart the retrieval index is."

MIND-Mem's deterministic retrieval pipeline validates these findings: 67.3% on LoCoMo with zero dependencies, no embeddings, and no vector database — within 1.2pp of Mem0's graph-based approach. The key insight: treating retrieval as a reasoning pipeline (wide candidate pool → deterministic rerank → context packing) closes most of the gap without any ML infrastructure. Unlike plain-file baselines, MIND-Mem adds integrity checking, governance, and agent-agnostic shared memory via MCP that no other system provides.

Recall

Default: BM25 Hybrid

python3 -m mind_mem.recall --query "authentication" --workspace .
python3 -m mind_mem.recall --query "auth" --json --limit 5 --workspace .
python3 -m mind_mem.recall --query "deadline" --active-only --workspace .

BM25F scoring (k1=1.2, b=0.75) with per-field weighting, bigram phrase matching, overlapping sentence chunking, and query-type-aware parameter tuning. Searches across all structured files.

BM25F field weighting: Terms in Statement fields score 3x higher than terms in Context (0.5x). This naturally prioritizes core content over auxiliary metadata.

RM3 query expansion: Pseudo-relevance feedback from top-k initial results. JM-smoothed language model extracts expansion terms, interpolated with the original query at configurable alpha. Falls back to static synonyms for adversarial queries.

Adversarial abstention: Deterministic pre-LLM confidence gate. Computes confidence from entity overlap, BM25 score, speaker coverage, evidence density, and negation asymmetry. Below threshold → forces abstention.

Stemming: "queries" matches "query", "deployed" matches "deployment". Simplified Porter stemmer with zero dependencies.

Hybrid Search (BM25 + Vector + RRF)

{
  "recall": {
    "backend": "hybrid",
    "vector_enabled": true,
    "rrf_k": 60,
    "bm25_weight": 1.0,
    "vector_weight": 1.0
  }
}

Thread-parallel BM25 and vector retrieval fused via RRF: score(doc) = bm25_w / (k + bm25_rank) + vec_w / (k + vec_rank). Deduplicates by block ID. Falls back to BM25-only when vector backend is unavailable.

Graph-Based (2-hop cross-reference boost)

python3 -m mind_mem.recall --query "database" --graph --workspace .

2-hop graph traversal: 1-hop neighbors get 0.3x score boost, 2-hop get 0.1x (tagged [graph]). Surfaces structurally connected blocks via AlignsWith, Dependencies, Supersedes, Sources, and ConstraintSignature scopes. Auto-enabled for multi-hop queries.

Vector (pluggable)

{
  "recall": {
    "backend": "vector",
    "vector_enabled": true,
    "vector_model": "all-MiniLM-L6-v2",
    "onnx_backend": true
  }
}

Supports ONNX inference (local, no server) or cloud embeddings. Falls back to BM25 automatically if unavailable.

MIND Kernels

MIND-Mem ships 26 .mind configuration files under mind/ that tune the scoring pipeline at runtime. These files are INI-style declarative configuration (e.g. [fusion] / rrf_k = 60), parsed by load_kernel_config() in src/mind_mem/mind_ffi.py. They are not the MIND programming language — see docs/MIND_CONFIG_VS_MIND_LANG.md for the disambiguation. The Python runtime (in src/mind_mem/mind_kernels.py) implements the actual scoring logic; the .mind files only carry numerical knobs.

Compilation (forward-looking — not yet wired)

The roadmap moves these numerical hot paths to true MIND-language kernels that compile to a native shared library via mindc (see mindlang.dev). When that integration lands, the build command will look like:

# Once the MIND-language port ships (not currently supported):
mindc mind/*.mind --emit=shared -o lib/libmindmem.so

Until then, the Python fallback in mind_kernels.py is the authoritative implementation. pip install mind-mem is fully functional without mindc. The 26 config files themselves ship in the wheel under <sys.prefix>/share/mind-mem/kernels/ for forward-compatibility tooling.

Kernel Index

File	Functions	Purpose
`bm25.mind`	`bm25f_doc`, `bm25f_batch`, `apply_recency`, `apply_graph_boost`	BM25F scoring with field boosts
`rrf.mind`	`rrf_fuse`, `rrf_fuse_three`	Reciprocal Rank Fusion
`reranker.mind`	`date_proximity_score`, `category_boost`, `negation_penalty`, `rerank_deterministic`	Deterministic reranking
`rerank.mind`	`rerank_scores`	Score combination pipeline
`abstention.mind`	`entity_overlap`, `confidence_score`	Confidence gating
`ranking.mind`	`weighted_rank`, `top_k_mask`	Evidence ranking
`importance.mind`	`importance_score`	A-MEM importance scoring
`category.mind`	`category_affinity`, `query_category_relevance`, `category_assign`	Category distillation scoring
`prefetch.mind`	`prefetch_score`, `prefetch_select`	Signal-based context pre-assembly
`recall.mind`	`recall_score`	Combined recall scoring
`hybrid.mind`	`hybrid_fuse`	BM25 + vector hybrid fusion
`rm3.mind`	`rm3_weight`	RM3 pseudo-relevance feedback
`adversarial.mind`	`adversarial_gate`	Adversarial query detection
`temporal.mind`	`temporal_decay`	Time-aware scoring
`intent.mind`	`intent_params`	Intent classification parameters
`cross_encoder.mind`	`ce_blend`	Cross-encoder blending configuration

Performance

Compiled MIND kernels vs pure Python — 9 core scoring functions (200 iterations, perf_counter)

Function	N=100	N=1,000	N=5,000
`rrf_fuse`	10.8x	69.0x	72.5x
`bm25f_batch`	13.2x	113.8x	193.1x
`negation_penalty`	3.3x	7.0x	18.4x
`date_proximity`	10.7x	15.3x	26.9x
`category_boost`	3.3x	19.8x	17.7x
`importance_batch`	22.3x	46.2x	48.6x
`confidence_score`	0.9x	0.8x	0.9x
`top_k_mask`	3.1x	8.1x	11.8x
`weighted_rank`	5.1x	26.6x	121.8x
Overall			49.0x

49x faster end-to-end at production scale (N=5,000). Individual kernels reach up to 193x speedup. The compiled library includes 14 runtime protection layers with near-zero overhead.

FFI Bridge

The compiled .so exposes a C99-compatible ABI. Python calls via ctypes through src/mind_mem/mind_ffi.py:

from mind_ffi import get_kernel, is_available, is_protected

if is_available():
    kernel = get_kernel()
    scores = kernel.rrf_fuse_py(bm25_ranks, vec_ranks, k=60.0)
    print(f"Protected: {is_protected()}")  # True with the hardened build

Without MIND

If lib/libmindmem.so is not present, MIND-Mem uses pure Python implementations. The Python fallback produces identical results (within f32 epsilon). No functionality is lost — MIND is a performance optimization, not a requirement.

Auto-Capture

Session end
    ↓
capture.py scans daily log (or --scan-all for batch)
    ↓
Detects decision/task language (26 patterns, 3 confidence levels)
    ↓
Extracts structured metadata (subject, object, tags)
    ↓
Classifies confidence (high/medium/low → P1/P2/P3)
    ↓
Writes to intelligence/SIGNALS.md ONLY
    ↓
User reviews signals
    ↓
/apply promotes to DECISIONS.md or TASKS.md

Batch scanning: python3 -m mind_mem.capture . --scan-all scans the last 7 days of daily logs.

Safety guarantee: capture.py never writes to decisions/ or tasks/ directly. All signals must go through the apply engine.

Multi-Agent Memory

Namespace Setup

python3 -m mind_mem.namespaces workspace/ --init coder-1 reviewer-1

Creates shared/ (visible to all) and agents/coder-1/, agents/reviewer-1/ (private) directories with ACL config.

Access Control

{
  "default_policy": "read",
  "agents": {
    "coder-1": {"namespaces": ["shared", "agents/coder-1"], "write": ["agents/coder-1"], "read": ["shared"]},
    "reviewer-*": {"namespaces": ["shared"], "write": [], "read": ["shared"]},
    "*": {"namespaces": ["shared"], "write": [], "read": ["shared"]}
  }
}

Shared Fact Ledger

High-confidence facts proposed to shared/intelligence/LEDGER.md become visible to all agents after review. Append-only with dedup and file locking.

Conflict Resolution

python3 -m mind_mem.conflict_resolver workspace/ --analyze
python3 -m mind_mem.conflict_resolver workspace/ --propose

Graduated resolution: confidence priority > scope specificity > timestamp priority > manual fallback.

Transcript Capture

python3 -m mind_mem.transcript_capture workspace/ --transcript path/to/session.jsonl
python3 -m mind_mem.transcript_capture workspace/ --scan-recent --days 3

Scans Claude Code JSONL transcripts for user corrections, convention discoveries, and architectural decisions. 16 patterns with confidence classification.

Backup & Restore

python3 -m mind_mem.backup_restore backup workspace/ --output backup.tar.gz
python3 -m mind_mem.backup_restore export workspace/ --output export.jsonl
python3 -m mind_mem.backup_restore restore workspace/ --input backup.tar.gz
python3 -m mind_mem.backup_restore wal-replay workspace/

Governance Modes

Mode	What it does	When to use
`detect_only`	Scan + validate + report only	Start here. First week after install.
`propose`	Report + generate fix proposals in `proposed/`	After a clean observation week with zero critical issues.
`enforce`	Bounded auto-supersede + self-healing within constraints	Production mode. Requires explicit opt-in.

Recommended rollout:

Install → run in detect_only for 7 days
Review scan logs → if clean, switch to propose
Triage proposals for 2-3 weeks → if confident, enable enforce

Block Format

All structured data uses a simple, parseable markdown format:

[D-20260213-001]
Date: 2026-02-13
Status: active
Statement: Use PostgreSQL for the user database
Tags: database, infrastructure
Rationale: Better JSON support than MySQL for our use case
ConstraintSignatures:
- id: CS-db-engine
  domain: infrastructure
  subject: database
  predicate: engine
  object: postgresql
  modality: must
  priority: 9
  scope: {projects: [PRJ-myapp]}
  evidence: Benchmarked JSON performance
  axis:
    key: database.engine
  relation: standalone
  enforcement: structural

Blocks are parsed by block_parser.py — a zero-dependency markdown parser that extracts [ID] headers and Key: Value fields into structured dicts.

Configuration

All settings in mind-mem.json (created by init_workspace.py):

{
  "version": "2.8.0",
  "workspace_path": ".",
  "auto_capture": true,
  "auto_recall": true,
  "governance_mode": "detect_only",
  "recall": {
    "backend": "bm25",
    "rrf_k": 60,
    "bm25_weight": 1.0,
    "vector_weight": 1.0,
    "vector_model": "all-MiniLM-L6-v2",
    "vector_enabled": false,
    "onnx_backend": false
  },
  "proposal_budget": {
    "per_run": 3,
    "per_day": 6,
    "backlog_limit": 30
  },
  "compaction": {
    "archive_days": 90,
    "snapshot_days": 30,
    "log_days": 180,
    "signal_days": 60
  },
  "scan_schedule": "daily"
}

Key	Default	Description
`version`	`"2.8.0"`	Config file version
`auto_capture`	`true`	Run capture engine on session end
`auto_recall`	`true`	Show recall context on session start
`governance_mode`	`"detect_only"`	Governance mode (`detect_only`, `propose`, `enforce`)
`recall.backend`	`"scan"`	`"scan"` (BM25), `"hybrid"` (BM25+Vector+RRF), or `"vector"`
`recall.rrf_k`	`60`	RRF fusion parameter k
`recall.bm25_weight`	`1.0`	BM25 weight in RRF fusion
`recall.vector_weight`	`1.0`	Vector weight in RRF fusion
`recall.vector_model`	`"all-MiniLM-L6-v2"`	Embedding model for vector search
`recall.vector_enabled`	`false`	Enable vector search backend
`recall.onnx_backend`	`false`	Use ONNX for local embeddings (no server needed)
`proposal_budget.per_run`	`3`	Max proposals generated per scan
`proposal_budget.per_day`	`6`	Max proposals per day
`proposal_budget.backlog_limit`	`30`	Max pending proposals before pausing
`compaction.archive_days`	`90`	Archive completed blocks older than N days
`compaction.snapshot_days`	`30`	Remove apply snapshots older than N days
`compaction.log_days`	`180`	Archive daily logs older than N days
`compaction.signal_days`	`60`	Remove resolved/rejected signals older than N days
`scan_schedule`	`"daily"`	`"daily"` or `"manual"`

MCP Server

MIND-Mem ships with a Model Context Protocol server that exposes memory as resources and tools to any MCP-compatible client.

Pair with mind-nerve for token-cheap routing. When your agent host loads many skills/tools/MCP servers, mind-nerve sits in front and returns only the top-K relevant to each request — typically a 95%+ reduction in skill-listing tokens. Apache-2.0 wheel, pip install mind-nerve. See star-ga/mind-nerve.

Install

pipx install "mind-mem[mcp]"   # preferred — isolated venv with mind-mem-mcp on PATH
# or
pip install --user "mind-mem[mcp]"

The [mcp] extra pulls fastmcp>=3.2.0 (the version line declared in pyproject.toml) and registers the mind-mem-mcp console script.

Automatic Setup (Recommended)

./install.sh --all

Configures all detected clients automatically. See Quick Start.

Manual Setup

For Claude Code, Claude Desktop, Cursor, Windsurf, and Gemini CLI, add to the respective JSON config under mcpServers:

{
  "mcpServers": {
    "mind-mem": {
      "command": "mind-mem-mcp",
      "args": [],
      "env": {"MIND_MEM_WORKSPACE": "/path/to/your/workspace"}
    }
  }
}

mind-mem-mcp is the console script registered by pipx install "MIND-Mem[mcp]" (or pip install --user "MIND-Mem[mcp]"). If you're running out of a source checkout instead, replace "command": "mind-mem-mcp" with "command": "python3", "args": ["/path/to/mind-mem/mcp_server.py"].

Client	Config File
Claude Code CLI	`~/.claude/mcp.json`
Claude Desktop	`~/.config/Claude/claude_desktop_config.json`
Gemini CLI	`~/.gemini/settings.json`
Cursor	`~/.cursor/mcp.json`
Windsurf	`~/.codeium/windsurf/mcp_config.json`

For Codex CLI (TOML format), add to ~/.codex/config.toml:

[mcp_servers.mind-mem]
command = "mind-mem-mcp"
args = []

[mcp_servers.mind-mem.env]
MIND_MEM_WORKSPACE = "/path/to/your/workspace"

For Zed, add to ~/.config/zed/settings.json under context_servers:

{
  "context_servers": {
    "mind-mem": {
      "command": {
        "path": "mind-mem-mcp",
        "args": [],
        "env": {"MIND_MEM_WORKSPACE": "/path/to/your/workspace"}
      }
    }
  }
}

Direct (stdio / HTTP)

# stdio transport (default)
MIND_MEM_WORKSPACE=/path/to/workspace mind-mem-mcp

# HTTP transport (multi-client / remote) — requires MIND_MEM_TOKEN per v3.7.0 fail-closed contract
MIND_MEM_WORKSPACE=/path/to/workspace MIND_MEM_TOKEN=$(openssl rand -hex 32) \
  mind-mem-mcp --transport http --host 127.0.0.1 --port 8765

Resources (read-only)

URI	Description
`mind-mem://decisions`	Active decisions
`mind-mem://tasks`	All tasks
`mind-mem://entities/{type}`	Entities (projects, people, tools, incidents)
`mind-mem://signals`	Auto-captured signals pending review
`mind-mem://contradictions`	Detected contradictions
`mind-mem://health`	Workspace health summary
`mind-mem://recall/{query}`	BM25 recall search results
`mind-mem://ledger`	Shared fact ledger (multi-agent)

Tools (21)

Tool	Description
`recall`	Search memory with BM25 (query, limit, active_only)
`propose_update`	Propose a decision/task — writes to SIGNALS.md only
`approve_apply`	Apply a staged proposal (dry_run=True by default)
`rollback_proposal`	Rollback an applied proposal by receipt timestamp
`scan`	Run integrity scan (contradictions, drift, signals)
`list_contradictions`	List contradictions with auto-resolution analysis
`hybrid_search`	Hybrid BM25+Vector search with RRF fusion
`find_similar`	Find blocks similar to a given block
`intent_classify`	Classify query intent (9 types with parameter recommendations)
`index_stats`	Index statistics, MIND kernel availability, block counts
`retrieval_diagnostics`	Pipeline rejection rates, intent histogram, hard negatives
`reindex`	Rebuild FTS5 index (optionally including vectors)
`memory_evolution`	View/trigger A-MEM metadata evolution for a block
`list_mind_kernels`	List available MIND kernel configurations
`get_mind_kernel`	Read a specific MIND kernel configuration as JSON
`category_summary`	Category summaries relevant to a given topic
`prefetch`	Pre-assemble context from recent conversation signals
`delete_memory_item`	Delete a memory block by ID (admin-scope)
`export_memory`	Export workspace as JSONL (user-scope)
`calibration_feedback`	Submit quality feedback for a retrieved block (thumbs up/down)
`calibration_stats`	View per-block and global calibration statistics

Token Auth (HTTP)

MIND_MEM_TOKEN=your-secret mind-mem-mcp --transport http --port 8765

As of v3.7.0, HTTP authentication fails CLOSED. If neither MIND_MEM_TOKEN nor MIND_MEM_ADMIN_TOKEN is set, the server refuses to start. For local development you can opt back into the legacy behaviour, but only on a loopback bind:

MIND_MEM_ALLOW_UNAUTHENTICATED_LOCALHOST=1 \
  mind-mem-mcp --transport http --host 127.0.0.1 --port 8765 \
               --allow-unauthenticated-localhost

The flag is a no-op if the bind host isn't 127.0.0.1 / ::1 / localhost — the server still refuses to start. Production deployments should always set a token.

Safety Guarantees

propose_update never writes to DECISIONS.md or TASKS.md. All proposals go to SIGNALS.md.
approve_apply defaults to dry_run=True. Creates a snapshot before applying for rollback.
All resources are read-only. No MCP client can mutate source of truth through resources.
Namespace-aware. Multi-agent workspaces scope resources by agent ACL.

Security

Threat Model

What we protect	How
Memory integrity	74+ structural checks, ConstraintSignature validation
Accidental overwrites	Proposal-based mutations only (never direct writes)
Rollback safety	Snapshot before every apply, atomic `os.replace()`
Symlink attacks	Symlink detection in restore paths
Path traversal	All paths resolved via `os.path.realpath()`, workspace-relative only

What we do NOT protect against	Why
Malicious local user	Single-user CLI tool — filesystem access = data access
Network attacks	No network calls, no listening ports, no telemetry
Encrypted storage	Files are plaintext Markdown — use disk encryption if needed

No Network Calls

MIND-Mem makes zero network calls from its core. No telemetry, no phoning home, no cloud dependencies. Optional features (vector embeddings, cross-encoder) may download models on first use.

Requirements

Python 3.10+
No external packages — stdlib only for core functionality

Optional Dependencies

Package	Purpose	Install
`fastmcp`	MCP server	`pip install mind-mem[mcp]`
`onnxruntime` + `tokenizers`	Local vector embeddings	`pip install mind-mem[embeddings]`
`sentence-transformers`	Cross-encoder reranking	`pip install mind-mem[cross-encoder]`
`ollama`	LLM extraction (local)	`pip install ollama`

mind-mem:4b — Purpose-Trained LLM

For best LLM extraction quality, use mind-mem:4b — a full fine-tune of Qwen3.5-4B on MIND-Mem's 8 extraction tasks (entity extraction, fact extraction, observation compression, contradiction detection, governance analysis, intent classification, axis-aware retrieval, LLM reranking). Empirical on RTX 3080 (Q4_K_M, 2.6GB VRAM): 104 tok/s generation, 1585 tok/s prefill.

Ollama (recommended):

# Download the GGUF from HuggingFace
wget https://huggingface.co/star-ga/mind-mem-4b/resolve/main/mind-mem-4b-Q4_K_M.gguf

# Create Ollama model
cat > Modelfile << 'EOF'
FROM ./mind-mem-4b-Q4_K_M.gguf
SYSTEM "You are mind-mem, a governance-aware memory extraction assistant."
PARAMETER temperature 0.1
PARAMETER num_ctx 8192
PARAMETER num_predict 1024
PARAMETER stop "<|im_end|>"
PARAMETER stop "<|endoftext|>"
EOF
ollama create mind-mem:4b -f Modelfile

Then set in mind-mem.json:

{
  "extraction": {
    "enabled": true,
    "model": "mind-mem:4b",
    "backend": "ollama"
  }
}

Empirical on RTX 3080 (Q4_K_M, 2.6GB VRAM): 104 tok/s generation, 1585 tok/s prefill.

Full fine-tune (transformers, no adapter):

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("star-ga/mind-mem-4b", device_map="auto", torch_dtype="bfloat16")
tokenizer = AutoTokenizer.from_pretrained("star-ga/mind-mem-4b")

Resource	Link
Model (GGUF + bf16 safetensors)	star-ga/mind-mem-4b
Base model	Qwen/Qwen3.5-4B
Training	Full fine-tune on Runpod H200 SXM (141 GB HBM3e), v3.12.0 corpus (4,392 examples), bf16, paged-AdamW-8bit, batch 2 × accum 16, max_length 2048, LR 1.5e-5 cosine + 3% warmup
Eval (v3.12.0-fullft, shipped in v3.12.1)	95/95 = 100% across ten categories — tool_call (20/20), block_schema (10/10), workflow (5/5), v39_new_tools (13/13), v39_transform_hash (3/3), v39_transport_guard (4/4), v311_new_tools (10/10), v311_explain_field (10/10), v312_quality_gate_strict_mode (10/10), v312_lineage_staleness (10/10). Two probes intentionally softened — see HF model card "Known model errors" section.

Platform Support

Platform	Status	Notes
Linux	Full	Primary target
macOS	Full	POSIX-compliant shell scripts
Windows (WSL/Git Bash)	Full	Use WSL2 or Git Bash for shell hooks
Windows (native)	Python only	Use `validate_py.py`; hooks require WSL

Troubleshooting

Problem	Solution
`validate.sh` says "No mind-mem.json found"	Run in a workspace, not the repo root. Run `init_workspace.py` first.
`recall` returns no results	Workspace is empty. Add decisions/tasks first.
`capture` says "no daily log"	No `memory/YYYY-MM-DD.md` for today. Write something first.
`intel_scan` finds 0 contradictions	Good — no conflicting decisions.
Tests fail on Windows	Use `validate_py.py` instead of `validate.sh`. Hooks require WSL.
MIND kernel not loading	Expected — the `.mind` files are INI configs, not yet MIND-language source. Pure-Python scoring (in `mind_kernels.py`) is the authoritative path. See `docs/MIND_CONFIG_VS_MIND_LANG.md`.

FAQ

No results from recall? Check that the workspace path is correct and points to an initialized workspace containing decisions, tasks, or entities. If the FTS5 index is stale or missing, run the reindex MCP tool to rebuild it.

MCP connection failed? Verify that fastmcp is installed (pip install fastmcp). Check the transport configuration in your client's MCP config (stdio vs HTTP). Ensure the MIND_MEM_WORKSPACE environment variable points to a valid workspace directory.

MIND kernels not loading? Run bash src/mind_mem/build.sh to compile the MIND source files (requires mindc). If the MIND compiler is not available, MIND-Mem automatically uses the pure Python fallback with identical results.

Index corrupt? Run the reindex MCP tool, or from the command line: python3 -m mind_mem.sqlite_index --rebuild --workspace /path/to/workspace. This drops and recreates the FTS5 index from all workspace files.

Specification

For the formal grammar, invariant rules, state machine, and atomicity guarantees, see SPEC.md.

Built in MIND lang

mind-mem's scoring kernels live in the mind/ directory of this repo. The BM25F field-weighting, RRF fusion, reranking, negation penalty, date proximity, category boost, importance decay, entity overlap, confidence gating, and top-k selection are all written in MIND source and compiled to native shared libraries via the MIND compiler. The pure Python fallback mirrors them exactly — same results, no compilation required.

The MIND language compiler is at github.com/star-ga/mind. The formal specification is at github.com/star-ga/mind-spec. The agent CLI being built on the same substrate is at github.com/star-ga/mind (RFC 0013, in development). Visit mindlang.dev to see the substrate that makes byte-identical replay possible.

For many developers, pip install mind-mem is their first encounter with a MIND-native system. The scoring kernels in mind/ are readable MIND source — the language is approachable, and the compiler produces output that is byte-identical on every architecture mind-mem CI targets.

Contributing

Contributions welcome. Please open an issue first to discuss what you'd like to change.

See CONTRIBUTING.md for guidelines.

Name		Name	Last commit message	Last commit date
Latest commit History 973 Commits
.agents/skills/mind-mem-development		.agents/skills/mind-mem-development
.arch-mind		.arch-mind
.gemini		.gemini
.githooks		.githooks
.github		.github
.mind-mem-audit		.mind-mem-audit
.roo		.roo
assets		assets
audits		audits
benchmarks		benchmarks
deploy		deploy
docs		docs
examples		examples
hooks		hooks
intelligence		intelligence
lib		lib
mind		mind
scripts		scripts
sdk		sdk
security		security
skills		skills
src		src
templates		templates
tests		tests
train		train
web		web
.cursorrules		.cursorrules
.dockerignore		.dockerignore
.editorconfig		.editorconfig
.gitattributes		.gitattributes
.gitignore		.gitignore
.gitleaks.toml		.gitleaks.toml
.pre-commit-config.yaml		.pre-commit-config.yaml
.python-version		.python-version
.run-ledger.jsonl		.run-ledger.jsonl
.windsurfrules		.windsurfrules
AGENTS.md		AGENTS.md
ANATOMY.md		ANATOMY.md
AUDIT_FINDINGS_FOR_CLAUDE.md		AUDIT_FINDINGS_FOR_CLAUDE.md
CHANGELOG.md		CHANGELOG.md
CLAUDE.md		CLAUDE.md
CONTRIBUTING.md		CONTRIBUTING.md
Dockerfile		Dockerfile
LICENSE		LICENSE
Makefile		Makefile
README.md		README.md
ROADMAP.md		ROADMAP.md
SECURITY.md		SECURITY.md
SECURITY_AUDIT_2026-04.md		SECURITY_AUDIT_2026-04.md
SPEC.md		SPEC.md
conftest.py		conftest.py
demo-setup.sh		demo-setup.sh
demo.tape		demo.tape
generate_mind7b_training.py		generate_mind7b_training.py
install-bootstrap.sh		install-bootstrap.sh
install.sh		install.sh
libmindmem.so		libmindmem.so
mcp_server.py		mcp_server.py
mind-mem.example.json		mind-mem.example.json
pyproject.toml		pyproject.toml
requirements-optional.txt		requirements-optional.txt
setup.py		setup.py
train_mind7b_runpod.py		train_mind7b_runpod.py
uninstall.sh		uninstall.sh

Folders and files

Latest commit

History

Repository files navigation

MIND-Mem

30-Second Demo

Substrate Properties

Table of Contents

Deep-dive docs

Why MIND-Mem

Novel Contributions

Features

Hybrid BM25+Vector Search with RRF Fusion

RM3 Dynamic Query Expansion

9-Type Intent Router

A-MEM Metadata Evolution

Deterministic Reranking

Optional Cross-Encoder

MIND Kernels (Optional, Native Speed — forward-looking)

MIC/MAP — MIND IR graph serialization

BM25F Hybrid Recall

Graph-Based Recall

Vector Recall (optional)

Persistent Memory

Immune System

Safe Governance

Adversarial Abstention Classifier

Auto-Capture with Structured Extraction

Concurrency Safety

Compaction & GC

Observability

Multi-Agent Namespaces & ACL

Automated Conflict Resolution

Write-Ahead Log (WAL) + Backup/Restore

Transcript JSONL Capture

MCP Server (84 tools, 8 resources)

74+ Structural Checks + 3024 Unit Tests

Audit Trail

Calibration Feedback Loop

LLM-Guided Multi-Query Expansion

4-Layer Search Deduplication

LLM-Guided Smart Chunking

Compiled Truth Pages

Dream Cycle (Autonomous Memory Enrichment)

Feature Completeness Matrix

Integrations are the substrate working

Native MCP integration with 17 AI development tools

Compatible with major LLM providers

Production usage at STARGA

What we do not claim

Benchmark Results

Needle In A Haystack (NIAH)

LoCoMo LLM-as-Judge

Competitive Landscape

Competitive Landscape (LoCoMo)

LongMemEval (held pending reconciliation)

Performance (Latency & Throughput)

Run Benchmarks Yourself

LLM-as-judge (accuracy metrics, requires API key)

Hybrid retrieval with any model pair (BM25 + vector + cross-encoder)

Selective conversations

Manual Setup

Health Summary

Commands

Architecture

How It Compares

Quick Comparison

At a Glance

Full Feature Matrix

The Gap MIND-Mem Fills

Why Plain Files Outperform Fancy Retrieval

Recall

Default: BM25 Hybrid

Hybrid Search (BM25 + Vector + RRF)

Graph-Based (2-hop cross-reference boost)

Vector (pluggable)

MIND Kernels

Compilation (forward-looking — not yet wired)

Kernel Index

Performance

Packages