11
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).
fkiene/llmtrim is an MCP server distributed on github, maintained by fkiene, tracked here since June 2026. It has shipped 11 releases. No risk grade is shown: the source hasn't been analyzed deeply enough to stand behind one.
11
0
0
| version | date | src |
|---|---|---|
| v0.1.10 | 2026-06-14 | github |
| v0.1.9 | 2026-06-13 | github |
| v0.1.8 | 2026-06-13 | github |
| v0.1.7 | 2026-06-13 | github |
| v0.1.6 | 2026-06-12 | github |
| v0.1.5 | 2026-06-12 | github |
| v0.1.4 | 2026-06-12 | github |
| v0.1.3 | 2026-06-12 | github |
| v0.1.2 | 2026-06-12 | github |
| v0.1.1 | 2026-06-12 | github |
no related servers found.