Git-native persistent memory for AI coding agents. The project implements Google OKF v0.2 and ships sub-300 microsecond in-memory BM25 search, an embedded MCP server and progressive disclosure. Written in pure Go with no external database, it is built to cut the token bloat that re-reading a codebase into context normally costs.
Be the first to rate OKF Agent Memory. Your feedback helps other users decide.
Store decisions, conventions and file facts in a git-native store the agent can query at the start of every session instead of re-deriving them.
Search accumulated notes with in-memory BM25 so the agent retrieves only the handful of entries relevant to the current task.
Use progressive disclosure so the agent loads a short index first and pulls full entries only when it actually needs them.
Similar tools in the same category — compare side-by-side
An OKF-backed Model Context Protocol server that gives AI agents persistent long-term memory with SQ...
A skill that stops your coding agent from burying the answer. It reshapes agent output so the result...
A small Go utility that cleans up Claude's token vomit with a separate LLM. It routes verbose model ...
Guides and comparisons about code tools
Ten Hacker News launches that treat agent context, persistent memory and token accounting as first-class problems instead of afterthoughts.
Compare Cursor, GitHub Copilot and Devin to find the best AI coding assistant. Learn how each fits different developer workflows, plus Cody and Codeium.
Build mobile apps faster with 7 AI code tools in 2026. From AI-assisted coding and UI generation to automated testing and deployment.
Discover the best AI code tools for DevOps engineers in 2026. Infrastructure as code, CI/CD optimization, monitoring and incident response compared.
AI coding assistants are transforming software development. Should developers be worried? An honest look at what AI changes and what it cannot replace.
