You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: ANALYSIS.md
+6-4Lines changed: 6 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -26,6 +26,7 @@ Research synthesis across all analyzed tools and papers. Updated as individual `
26
26
|[rtk](analysis/ANALYSIS-rtk.md)| Claude Code hook-based CLI proxy; two-track filter pipeline (69 Rust handlers + 58 TOML filters) | 60–90% on dev commands (as reported; chars/4 heuristic) | None — passthrough proxy |`scripts/benchmark.sh` runnable; live fixtures; 80% improvement CI gate | v0.35.0; Apache-2.0; TOML filter correctness enforced at compile time | No direct peer — transparent CLI-proxy hook architecture is unique. Use if goal is passive token reduction on Claude Code dev commands without changing agent behavior. Complementary to all MCP-layer tools. |
27
27
|[socraticode](analysis/ANALYSIS-giancarloerra-socraticode.md)| Qdrant-backed hybrid search (dense + BM25 via Qdrant RRF); AST-aware chunking (18+ languages); polyglot dependency graph | 61.5% (as reported; bytes not tokens; single live session; no harness) | None | No harness; 3 narrative case studies | Docker required; Qdrant v1.15.2+ required; MIT | Overlaps codebase-memory-mcp and code-review-graph for code search. Prefer code-review-graph (no Docker/Qdrant dep, stronger benchmarks). Use socraticode only if Qdrant is already in the infrastructure stack and RRF hybrid search is needed. |
28
28
| [sdl-mcp](analysis/ANALYSIS-glitterkill-sdl-mcp.md) | LadybugDB knowledge graph; Symbol Cards (~100 tokens/symbol, LLM summary, ETag re-fetch); Iris Gate Ladder 4-rung escalation; Delta Packs blast-radius; SCIP compiler-grade edges; 38 tool surfaces | 81% `tools/list` overhead (gateway mode, as reported); no end-to-end session figure | Implicit: Iris Gate Ladder prompts cheapest-first retrieval; `max-cards` on slices | No harness; no end-to-end benchmark; all figures author-run | LLM summary cost at index time undisclosed; LadybugDB opaque (no schema/SQL/Cypher); source-available license; 12 languages (Rust indexer); 125 stars | **Watch.** Iris Gate Ladder + ETag conditional re-fetch are architecturally novel — the most disciplined context-escalation model in this survey. But no end-to-end token savings figure exists, LadybugDB is opaque, and LLM index-time costs are undisclosed. Overlaps codebase-memory-mcp and code-review-graph for graph-based code intelligence; prefer those (MIT, transparent storage, broader languages) until SDL-MCP provides a reproducible end-to-end benchmark and documents summary costs. |
29
+
| [osgrep](analysis/ANALYSIS-ryandonofrio3-osgrep.md) | npm CLI; LanceDB vector store; Granite 30M dense + mxbai ColBERT 17M (int8) late-interaction reranking; tree-sitter AST chunking; FTS + vector → RRF → two-stage ColBERT pipeline | ~20% cost reduction / ~30% speedup (as reported; 10-query, single-codebase CSV; no answer quality assessment) | None — result set size is the bound | 10-query CSV (opencode corpus, cost-only); internal MRR harness (`eval.ts`, 70+ cases, self-referential); not reproduced | MCP server is a non-functional stub as of commit 9f2faf7; last push 2026-01-17; 1,128 stars; Apache-2.0 | Overlaps socraticode and codebase-memory-mcp for semantic code search. Unique: richest hybrid retrieval pipeline in the survey (dense + FTS + two-stage ColBERT) in a zero-external-service npm package. MCP stub rules out MCP-framework integration currently. Prefer socraticode if Qdrant is already in the stack and RRF hybrid search is sufficient; prefer codebase-memory-mcp if graph queries are needed. Use osgrep if the call-stack trace + skeleton compression commands are the target use case or if a pure-npm zero-dep installation is required. |
29
30
30
31
---
31
32
@@ -49,7 +50,8 @@ Research synthesis across all analyzed tools and papers. Updated as individual `
49
50
10.**n2-arachne** — read for the fixed-percentage budget allocation model; chars/3.5 heuristic and non-commercial license are the two primary risks.
50
51
11.**jdocmunch-mcp** — read for the O(1) byte-offset retrieval pattern; note the savings accounting flaw (counts all sections, not returned) and opt-out telemetry before adopting.
51
52
12.**socraticode** — Qdrant-backed hybrid search (dense + BM25 via RRF); Docker required; the 61.5% figure is bytes not tokens from a single session — important methodological caveat shared with jdocmunch.
52
-
13.**qmd** — most sophisticated retrieval pipeline in this survey (8 steps: BM25 probe → LLM query expansion → vec → RRF → rerank); relevant primarily when the agent's knowledge base is markdown, not code.
53
-
14.**caveman** — output-style compression is a different category from all others; useful when output verbosity rather than input retrieval is the token budget bottleneck.
54
-
15.**Understand-Anything** — read if developer comprehension (domain mapping, not token reduction) is the target; different value proposition from every other tool in this list.
55
-
16.**git-semantic-bun** — borderline scope; read only if semantic retrieval from git commit history is specifically needed.
53
+
13.**osgrep** — read alongside socraticode; richest hybrid retrieval pipeline in the survey (FTS + dense + two-stage ColBERT reranking) with zero external service dependencies; key caveat: MCP server is a non-functional stub as of last commit, and the 10-query benchmark covers cost only with no answer quality assessment.
54
+
14.**qmd** — most sophisticated retrieval pipeline in this survey (8 steps: BM25 probe → LLM query expansion → vec → RRF → rerank); relevant primarily when the agent's knowledge base is markdown, not code.
55
+
15.**caveman** — output-style compression is a different category from all others; useful when output verbosity rather than input retrieval is the token budget bottleneck.
56
+
16.**Understand-Anything** — read if developer comprehension (domain mapping, not token reduction) is the target; different value proposition from every other tool in this list.
57
+
17.**git-semantic-bun** — borderline scope; read only if semantic retrieval from git commit history is specifically needed.
|[git-semantic-bun](https://github.com/danjdewhurst/git-semantic-bun)| Local vector index over git commit history; hybrid BM25 + semantic ranking |[analysis](analysis/ANALYSIS-danjdewhurst-git-semantic-bun.md)|
0 commit comments