okf-agent-memory
Gives AI agents a lasting, version-controlled memory stored as plain Markdown files in your own repo, with fast local BM25 search and no vector database or embedding API costs.
View okf-memory/okf-agent-memory on GitHub- GitHub stars
- 866
- Forks
- —
- Language
- Go
Project details
- Repository
- okf-memory/okf-agent-memory
- Licence
- MIT
- Primary language
- Go
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Explore by topic
More tools in Knowledge & documents
- graphicle
graphicle-ai · Apache-2.0
Maps your codebase into a local graph and remembers your project's docs and past agent sessions, so your coding agent gets cited file-and-line answers instead of…
- recollect
mikek184 · Apache-2.0
A self-hosted, Rust-built memory and MCP coordination layer that gives coding agents persistent context across repos and sessions.
- xerj
xerj-org · Apache-2.0
One command indexes your code, docs, logs and PDFs so AI agents can search and remember your data using far fewer tokens than grep, while staying Elasticsearch…
- agent-cockpit
chutingyean · AGPL-3.0
A local whiteboard and MCP server where AI coding/research agents log every claim and the exact code run that produced it, so if the underlying code changes, the claims…