Back to directory

AOCI-CODE

AOCI-CODE maintains a persistent, Git-versioned index of a codebase's files and database schema, written by the coding agent itself, so agents such as Claude Code or Cursor can read the index once instead of re-exploring the repository on every task.

AOCI-CODE

AOCI-CODE runs a local-first MCP server and command-line tool that governs a repository index: one entry per file, written by the model from the real source, recording what the file is responsible for, what must be read alongside it, what callers depend on, and anything that cannot be inferred from the code but must not get wrong. The index lives in the repository and is versioned with Git, so it survives a change of people, agents or conversation.

The first index build takes time, about an hour per 200,000 lines of code, depending on the model, and can run in batches, resuming where it left off. It has been used to index a codebase of about 700,000 lines with an index of roughly 300,000 tokens. After the first index, the server detects code changes and marks entries for the agent to update as it finishes each task, so maintenance does not require a separate step.

It is written in Go and works with Claude Code, Codex, Cursor and OpenCode.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.