OKF Agent Memory is a Git-native persistent memory layer for AI coding agents that uses the Google Open Knowledge Format (OKF) v0.2.
Follow OKF Agent Memory to get an email when its listing changes, such as new pricing or features. One digest a day at most, and you can unsubscribe anytime.
It organizes project knowledge into a structured, searchable Markdown bundle to reduce token bloat while providing auditable, version-controlled context for agents.
- 01
In-memory BM25 lexical search with sub-300µs latency
- 02
Dual-Memory Agent Architecture (DMAA) for context efficiency
- 03
Embedded MCP server for integration with Cursor, Claude Code, and Windsurf
- 04
Git-native auditing using standard diff and log commands
- 05
Trust tiers for distinguishing human-verified decisions from agent-generated drafts
Open Source
Free and open-source under the MIT license with no external database, API, or embedding costs.
Best for
Software engineering teams and developers needing auditable, version-controlled AI agent memory without the latency or recurring costs of vector databases.
Not ideal for
Projects requiring semantic (vector-based) search across synonyms, cross-repository memory sharing, or small projects where structured knowledge management is overkill.
A high-performance, developer-centric tool that effectively solves context bloat by moving agent memory into Git-versioned Markdown, offering a robust alternative to hosted vector databases.
Version v0.6.1 released on 2026-10-12, introducing hub sync state persistence, improved BM25 scoring, and metadata caps. v0.6.0 added symlinked bundle roots and strict filter keys.
As of
Is OKF Agent Memory free?+
Yes - OKF Agent Memory is Open Source. Free and open-source under the MIT license with no external database, API, or embedding costs.
Is OKF Agent Memory open source?+
Yes - OKF Agent Memory is open source. Free and open-source under the MIT license with no external database, API, or embedding costs.
Who is OKF Agent Memory best for?+
Software engineering teams and developers needing auditable, version-controlled AI agent memory without the latency or recurring costs of vector databases.
Who is OKF Agent Memory not ideal for?+
Projects requiring semantic (vector-based) search across synonyms, cross-repository memory sharing, or small projects where structured knowledge management is overkill.
What are the best OKF Agent Memory alternatives?+
The closest OKF Agent Memory alternatives on ai.dosa.dev are Greptile, Fern, remio - all listed under AI Codebase Knowledge & Generation.
Who makes OKF Agent Memory?+
OKF Agent Memory is developed by okf-memory. It is listed in the AI Codebase Knowledge & Generation category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.