# ratel

> ratel — ratel-ai-ratel. Use this tool when you need to optimize context engineering for AI agents, reducing token overload and improving skills and memory retrieval. It solves problems of tool overload and inefficient information retrieval, providing a streamlined interface for in-process BM25 and semantic retrieval. Ideal for use cases where vector databases are not feasible, ratel offers a lightweight solution with progressive disclosure capabilities.

Canonical page: https://skillsregistry.net/skills/ratel-ai-ratel  
JSON: https://api.skillsregistry.net/v1/skills/ratel-ai-ratel

## Description

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/ratel-ai/ratel)

## 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": "ratel-ai-ratel"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ratel-ai-ratel` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ratel-ai-ratel/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