OKF Agent Memory: Git-native memory for AI agents cuts token bloat by 80%

OKF Agent Memory – Git-native persistent memory for AI coding agents

OKF Agent Memory is a Git-native, persistent memory layer for AI coding agents, built in pure Go. It implements Google's OKF v0.2 spec, storing knowledge as plain Markdown with YAML frontmatter in your repo. It offers sub-300µs in-memory BM25 search, an embedded MCP server, and progressive disclosure to slash token usage by 80%—with zero external databases or dependencies.

Conversations with AI agents reset when context windows close. Valuable architectural decisions, domain discoveries, and operational facts are lost unless stored persistently.
  1. calebkaiser

    Love seeing projects like this. The performance benchmarks are nice to see. Have you done any benchmarks against approaches like OpenAI's Symphony for things like token usage or task completion?

  2. practicalsystem

    cool going to check it out, I've got an opensource project that might compliment it that I'm excited to try

    https://github.com/ucsandman/declick

  3. rogeliodh

    How does it compare to https://github.com/scaccogatto/okf-skills ?

More from this day

2026-09-06