# OKF Agent Memory — AI Coding Tool Review & Pricing

> OKF Agent Memory is a Git-native persistent memory layer for AI coding agents that uses the Google Open Knowledge Format (OKF) v0.2. It organizes project knowledge into a structured, searchable Markdown bundle to reduce token bloat while providing auditable, version-controlled context for agents.

Source: https://ai.dosa.dev/tools/okf-agent-memory · Updated Oct 15, 2026 · Category: AI Codebase Knowledge & Generation · Published by dosa.dev

## At a glance

- **Tool**: OKF Agent Memory
- **Company**: okf-memory
- **Category**: [AI Codebase Knowledge & Generation](https://ai.dosa.dev/category/codebase-ai)
- **Pricing model**: Open Source
- **Official website**: https://github.com/okf-memory/okf-agent-memory

## Key features

- In-memory BM25 lexical search with sub-300µs latency
- Dual-Memory Agent Architecture (DMAA) for context efficiency
- Embedded MCP server for integration with Cursor, Claude Code, and Windsurf
- Git-native auditing using standard diff and log commands
- Trust tiers for distinguishing human-verified decisions from agent-generated drafts

## Pricing

**Model**: Open Source

Free and open-source under the MIT license with no external database, API, or embedding costs.

## Who it is for

- **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.

## Verdict

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.

## Recent updates

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.

## Frequently asked questions

### 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.

## Top alternatives

- [Greptile](https://ai.dosa.dev/tools/greptile) (Freemium) — Engineering teams needing consistent, context-aware code reviews and automated validation that integrates across multiple AI coding agents.
- [Fern](https://ai.dosa.dev/tools/fern) (Freemium) — Teams needing to keep SDKs, documentation, and AI-agent knowledge bases in sync with their API specifications.
- [remio](https://ai.dosa.dev/tools/remio) (Freemium) — Knowledge workers such as consultants, researchers, product managers, and strategists who need to synthesize large volumes of internal documentation, meetings, and research into actionable outputs.
- [ContextStream](https://ai.dosa.dev/tools/contextstream) (Freemium) — Developers seeking to maintain consistent project context, reasoning, and decision history across different AI coding sessions and tools without repeating instructions.
- [Tseha](https://ai.dosa.dev/tools/tseha) (Freemium) — Engineering teams that want to ensure AI coding agents consistently follow internal architectural rules, use approved components, and apply current design tokens across multiple repositories.
- [Brain Scanner](https://ai.dosa.dev/tools/brain-scanner) (Free) — Developers working with AI coding agents who need to track project evolution, maintain context across multiple sessions, and audit changes.
- Full alternatives guide: https://ai.dosa.dev/tools/okf-agent-memory/alternatives