Add 'Build your own AI Agent' category#1832
Open
TheSeydiCharyyev wants to merge 1 commit into
Open
Conversation
buvaneswaraneb
approved these changes
Jul 10, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a
Build your own AI Agentcategory: a table-of-contents entry (alphabetically between 3D Renderer and AI Model) and a section with five step-by-step, from-scratch tutorials covering the agent layer — the agent loop with tools, the Model Context Protocol, and token/cost accounting.Why this category
The list covers the model itself (
AI Model) and chat bots (Bot), but not the layer in between that so many people are building now: the loop that drives tool calls, the protocol agents use to discover tools, and the cost mechanics of running loops against an LLM. #1800 proposed the same category (its RAG entry has since been merged underAI Model), and #1697 gestures at it — this PR completes the idea with a formatted section, per-language sorting, and a TOC anchor that matches GitHub's generated heading id.Entries
All five build the thing from an empty file with no frameworks, matching the contribution bar: Thorsten Ball's canonical agent-in-Go walkthrough, Kevin Yank's JavaScript equivalent, and three Node.js tutorials with a runnable checkpoint at every step and zero dependencies — a coding agent (loop, tools, workspace sandboxing, raw-HTTP model adapter), an MCP server + client over bare JSON-RPC on stdio, and token accounting (cost math, prompt-cache economics, streaming metrics).
Disclosure: the three Node.js tutorials are mine.