A Domain-Neutral, Git-Native Persistent Project Memory for AI Agents based on the Open Knowledge Format (OKF) v0.2.
Conversations with AI agents reset when context windows close. Valuable architectural decisions, domain discoveries, and operational facts are lost unless stored persistently.
OKF Agent Memoryprovides a standardized, vendor-neutral memory layer that lives directly in your repository (knowledge/) as plain Markdown files with YAML frontmatter. It bridges the gap between unstructured ad-hoc markdown files (CLAUDE.md,AGENTS.md) and complex, black-box vector databases.
Built in Go with zero external dependencies,okfis engineered for high-frequency agent tool calling loops:
Reproduce Locally with your own LLM: We provide an automated benchmark runner in pure Go to verify Time-To-First-Token (TTFT) speedups and -80% token reduction on your local hardware (LM Studio / Ollama with Gemma, Qwen, Llama). Runmake benchmarkor explore theProgressive Disclosure Benchmark Suite.
Clone the repository and compile the standaloneokfexecutable:
This generates the standalone binary atbin/okf.
Scaffold the complete OKF Agent Memory architecture into any new or existing repository with a single command:
okfships with a native Model Context Protocol (MCP) server overstdioto seamlessly connect with Claude Code, Cursor, Codex, and other agent platforms:
Run the full test suite and validate the repository’s self-documenting knowledge bundle:
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.