OKF Agent Memory

Git-native dual-memory for agents — OKF v0.2 + embedded MCP

AI Agents / Agents · OSS/MIT · 824

Reviewed 2026-09-21 · last push 2026-10-12 · repo checked 2026-10-19

What's Good

MIT (okf-memory/okf-agent-memory). Pure Go, zero external database deps. Dual-memory shape: a tiny normative push layer (~100–150 tokens of invariants) plus an OKF v0.2 knowledge/ pull layer with sub-millisecond BM25 search and an embedded MCP server (okf_search / okf_show). Progressive disclosure is the point — baseline context stays near zero until the agent asks.

The Catch

Vs Engram / Mem0 / Supermemory / Letta: OKF is the git-native OKF+AAG dual-memory recipe with MCP, not a hosted memory SaaS or paging OS. You still author the Domain Codex and decide write discipline; empty knowledge/ stays empty.

Verdict

MIT git-native agent memory. Use when you want OKF bundles and MCP retrieval without another database.

Embed

Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.

Markdown

[![Reviewed on Stack Gems](https://stackgems.com/badge/okf-agent-memory.svg)](https://stackgems.com/gems/okf-agent-memory)

HTML

<a href="https://stackgems.com/gems/okf-agent-memory"><img src="https://stackgems.com/badge/okf-agent-memory.svg" alt="OKF Agent Memory reviewed on Stack Gems" height="20"></a>

AI Agents →

Related