# okf-agent-memory

> okf-agent-memory — okf-memory-okf-agent-memory. Use this tool when you need to efficiently manage and search large amounts of data in a Git-native environment, solving problems of token bloat and slow search performance. It provides sub-300µs in-memory BM25 search and progressive disclosure, with inputs of Git data and outputs of relevant search results. Ideal for AI coding agents requiring fast and lightweight data management.

Canonical page: https://skillsregistry.net/skills/okf-memory-okf-agent-memory  
JSON: https://api.skillsregistry.net/v1/skills/okf-memory-okf-agent-memory

## Description

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.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/okf-memory/okf-agent-memory)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "okf-memory-okf-agent-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/okf-memory-okf-agent-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/okf-memory-okf-agent-memory/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt