llmtrim
mcp-serverNo score yet
Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).
Stars
157
Δ stars 7d
—
Δ stars 30d
—
Forks
7
Contributors
2
npm DL / wk
—
PyPI DL / wk
—
Language
Rust
Last push
2026-07-10
About llmtrim
llmtrim is a local proxy that compresses your LLM API requests so you pay less, with no change to the answers. It sits between your AI tools and the provider, strips the wasted tokens out of every request, and forwards it on. You get the same answers for a smaller bill. −31% input and −74% output tokens, measured live across 112 A/B cases, with no change in answer quality. Use it as a proxy, a CLI, an MCP server, or a library (Python · Ruby · Swift · Kotlin · JS · TS · WASM).
Read the full README on GitHub →
llmtrim alternatives
Projects in the same category, closest in size — picked by data, not opinion.
See all mcp-server projects ranked by growth →
Frequently asked questions
- Is llmtrim still maintained?
- Yes — actively maintained. The last push was on 2026-07-10, with 2 contributors.
- What are the best llmtrim alternatives?
- Closest by category and size in our data: MCP ABAP ADT, LinkedIn MCP Server, fradser/mcp-server-apple-reminders — full list with live signals above.
Topics
Embed this badge
Show your project's live signal in your README — it updates weekly with the data.
Tracked since 2026-06-30 · data as of 2026-07-10 · 3 open issues · 30 releases