Tier 2 · Harness engineering Harness engineering · fetched 2026-07-02

ai-coding-agent-open-source-analysis

A comparative research repository on AI coding agents, full-source scanning, spec-driven development, and LLM wiki/RAG trends, with analysis reports, category READMEs, CSV tables, and a data/source-inventory.json cataloging the analyzed agents. Useful as the index that cross-references the Tier 4 agents.

View source on GitHub

Key takeaways

01
source-inventory.json is a machine-readable catalog of coding agents
02
Covers spec-driven development as an emerging agent workflow
03
Good comparative axes: context strategy, edit format, verification

Flows built on this research

Agent Architecture

Single-Agent vs Multi-Agent: Decide and Design

A decision flow for the most expensive architecture choice in agent systems - grounded in what actually ships versus what demos well.

4 steps · 45-75 minutes

Agent Architecture

Design the Agent-Computer Interface (ACI)

Apply SWE-agent's key finding: agents perform dramatically better when their commands, viewers, and feedback are designed for models, not humans.

5 steps · 90-120 minutes

From the archive

Verbatim excerpts mined from our local archive of this repository — the prompts, schemas, and patterns worth stealing.

MCP & tools

The seven MCP reference servers, and what they teach

Reference servers remaining in modelcontextprotocol/servers:

| Everything | TypeScript | Comprehensive MCP feature demo |
| Filesystem | TypeScript | Allowed-directory file read/write |
| Memory | TypeScript | JSONL-based knowledge-graph memory |
| Sequential Thinking | TypeScript | Step-by-step reasoning state recorder |
| Fetch | Python | URL fetch + markdown conversion |
| Git | Python | Git repository read/manipulation |
| Time | Python | Current time and timezone conversion |

GitHub, GitLab, Slack, SQLite, Puppeteer, Postgres servers were moved to servers-archived; the repo shifted from 'catalog of all MCP servers' to 'a small set of maintained references', pointing users to the MCP Registry.

[translated from Korean] SECURITY.md explicitly warns these are educational references, not production security baselines - adapt them to your own threat model.

reports/repositories/modelcontextprotocol-servers.md

Insight

Context7: freshen the docs, not the model

Context7's problem statement: AI coding agents are frequently wrong about package versions, API changes, and framework-recommended patterns. The way to reduce this without retraining is to fetch documentation at execution time.

It exposes two MCP tools - resolve-library-id and query-docs - and its server instructions explicitly restrict scope: "do not use for refactoring, script writing, business-logic debugging, code review, or general programming concepts."

It is not a coding agent but an external-memory/document-retrieval adapter for coding agents.

[translated from Korean] Two lessons: staleness is a retrieval problem not a training problem, and good tools tell the model when NOT to use them.

reports/repositories/upstash-context7.md