aoci-spec/aoci-code
1,489 stars · Last commit 2026-10-09
A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, Cursor, and opencode long-term context, memory, and code intelligence.
README preview
 # AOCI-CODE **A persistent, Git-versioned map of your entire codebase — written by your coding agent, governed by a local MCP server.** Agents read it once and know the system, instead of re-reading the repo on every task. 🇺🇸 English | [🇨🇳 简体中文](README.zh-CN.md)     <a href="https://trendshift.io/repositories/195419?utm_source=trendshift-badge&utm_medium=badge&utm_campaign=badge-trendshift-195419" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/195419/daily?language=Go" alt="aoci-spec%2Faoci-code | Trendshift" width="250" height="55"/></a> <a href="https://trendshift.io/repositories/195419?utm_source=trendshift-badge&utm_medium=badge&utm_campaign=badge-trendshift-195419" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/195419/weekly?language=Go" alt="aoci-spec%2Faoci-code | Trendshift" width="250" height="55"/></a> ## What it does **Build large systems without losing the plot.** In Codex, Claude Code, Cursor, OpenCode, and similar agents, your agent starts every task already knowing the whole system: what each file is for, what it depends on, and what must not break. It stops searching and re-reading the codebase for every request. People who are not professional developers can keep iterating on their own systems; professional developers can hand the whole system to an agent and keep their attention on architecture and design. **Take over an existing system in one step.** Point the agent at an existing codebase of up to about 500,000 lines and ask it to build the index. It reports how well it knows each area, then picks up development from there. The practical limit is the size of the index, not the line count: a 700,000-line commercial system is developed this way today, with an index of about 300K tokens.