ratel

MCP serverGitHubActiveRust

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.

Description provenance: Original source

Open canonical source

Measured: Oct 20, 2026 · 68 observations

Domains & Uses

Domains: Agents, skills and MCP
Uses: Agent skills, Token efficiency, Retrieval-augmented generation (RAG)

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/ratel-ai/ratel

Classifications

Nature: Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

484stars · Oct 20, 2026

+42 (+9.5 %)since Sep 22, 2026

Exact values · 28 readings

Measured	stars	Change
Oct 20, 2026	484	+4
Oct 18, 2026	480	+2
Oct 17, 2026	478	0
Oct 16, 2026	478	+2
Oct 15, 2026	476	0
Oct 14, 2026	476	+1
Oct 13, 2026	475	+2
Oct 12, 2026	473	+2
Oct 11, 2026	471	+1
Oct 10, 2026	470	+1
Oct 9, 2026	469	0
Oct 8, 2026	469	+1
Oct 7, 2026	468	0
Oct 6, 2026	468	+2
Oct 5, 2026	466	0
Oct 4, 2026	466	+1
Oct 3, 2026	465	0
Oct 2, 2026	465	+2
Oct 1, 2026	463	+1
Sep 30, 2026	462	+1
Sep 29, 2026	461	+1
Sep 28, 2026	460	+1
Sep 27, 2026	459	+3
Sep 26, 2026	456	+8
Sep 25, 2026	448	+5
Sep 24, 2026	443	0
Sep 23, 2026	443	+1
Sep 22, 2026	442	·