Skip to content
OKF Agent Memory

OKF Agent MemoryMCP Server

by okf-memory
Released
v0.4.2
MIT
Repository Docs
Databases & Data

Summary

Git-native persistent memory for coding agents — sub-300µs BM25 search over version-controlled plain text, with no embeddings, no database and no API costs.

Features

  • Dual memory: ~100-150 token behavioural codex plus on-demand knowledge bundle
  • Sub-300µs in-memory BM25 search, no vector database or embedding API
  • Git-native plain text: diffable, branch-scoped, no vendor lock-in
  • Implements Google OKF v0.2 with provenance and trust tiers
  • MCP server embedded in a single Go binary

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it.
  3. Restart the agent — the "OKF Agent Memory" tools will be available.
{
  "mcpServers": {
    "okf-agent-memory": {
      "command": "/path/to/okf-agent-memory/bin/okf",
      "args": [
        "mcp",
        "/path/to/project/knowledge"
      ]
    }
  }
}

Description

Most agent memory systems reach for a vector database and an embedding API. OKF Agent Memory takes the opposite position: memory is plain text in your git repository, searched lexically in process, and it costs nothing per query.

The design splits memory in two, which is the part that does the work. A compact behavioural codex — roughly 100–150 tokens — holds normative instructions and is always in context. Everything else lives in a searchable knowledge bundle that is retrieved on demand through progressive disclosure. That separation is what lets the project claim around 80% token reduction against a monolithic instructions file, because the agent no longer pays for domain knowledge it is not currently using.

Search is in-memory BM25 with sub-300µs latency and zero external databases, so there is nothing to run alongside the agent and nothing to pay an embedding provider for. Because every artefact is version-controlled plain text, memory diffs in review, travels with a branch, and carries no vendor lock-in. The MCP server is embedded in the same Go binary and works with Claude, Cursor and other compatible clients.

It implements Google's OKF v0.2, the open standard format for agent knowledge, including provenance metadata, trust tiers that distinguish generated from verified knowledge, and lifecycle tracking — so entries carry where they came from and how much they should be trusted. An Agent Action Grammar (AAG) gives instructions a deterministic, token-efficient syntax. Recent releases have concentrated on hardening the MCP server against input bounds violations, denial-of-service, Unicode spoofing and path traversal. MIT licensed; build with make build to produce a standalone bin/okf.

Related MCP Servers

See all OKF Agent Memory alternatives

MCP: Memory

by Model Context Protocol

A knowledge-graph-based persistent memory system that lets an agent remember entities and relations across sessions.

Databases & Data

MCP: Engram

by Gentleman Programming

Featured

Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.

Developer Tools

MCP: agentmemory

by rohitg00

Self-hosted persistent memory for coding agents: hooks capture what you do, and an MCP server lets any agent recall it across sessions and across tools.

Databases & Data

MCP: Graphicle

by Graphicle

Local-first Rust MCP server that maps your repo into a code graph and project memory, then hands coding agents cited file-and-line excerpts.

Developer Tools
Browse all MCP servers →