fkiene / llmtrim
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).
Why this job: says: mcp server; topics: mcp
What it does
Using Claude Code? One install also gets you /sub to serve it through CLIProxyAPI.
Get started
npm install -g @llmtrim/cli@latest && llmtrim setup
# open a new terminal, then keep working
llmtrim status - Maintenance
- Active
- Last commit 7 days ago
- Stars
- 270
- +5 this week
- Licence
- MPL-2.0
- Share-alike for changes
- Downloads for
- 3 systems
- Mac, Windows, Linux
- Latest version
- v0.13.8
- Released 7 days ago
- Built with
- Rust
- 92% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 88% closed
- 4 still open
- Pull requests
- 241 merged
- 6 waiting
- Releases
- 65
- 30+ in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| ojuschugh1 / sqz | 675 | 18 days ago | Apache-2.0 | Mac, Windows, Linux |
More: download files, languages, topics and project record
Download files, v0.13.8
- Mac4 files, 13 downloads
- Windows5 files, 40 downloads
- Linux6 files, 71 downloads
Languages
- Rust 92%
- Python 5%
- Shell 1%
- TypeScript 1%
Topics
- agentic-coding
- ai
- anthropic
- claude-code
- cost-reduction
- developer-tools
- llm
- llmops
- mcp
- mitm-proxy
- openai
- prompt
Project record
- JobMCP servers
- StatusListed
- Commits699
- Forks23
- Watching4
- Stars in 28 days+26
- CreatedJun 7, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026