No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by fkiene · MCP Server · ★ 239
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is llmtrim safe to install? View the security audit →
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. What it does • See it in action • Get started • CLI & library • Works with • Configuration • Numbers What it actually do
| Stars | 239 |
| Forks | 23 |
| Language | Rust |
| Category | MCP Server |
| License | MPL-2.0 |
| Quality Score | 65.6706521654121/100 |
| Open Issues | 9 |
| Last Updated | 2026-09-30 |
| Created | 2026-06-07 |
| Platforms | claude-code, mcp, rust |
| Est. Tokens | ~27k |
These tools work well together with llmtrim for enhanced workflows:
Looking for a llmtrim alternative? If you're comparing llmtrim with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Menu Bar App on MacOS and Windows that cuts Claude Code and Codex token costs by ~50%
Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twi
Automatic prompt caching for Claude Code. Cuts token costs by up to 90% on repeated file reads, bug fix sessio
A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without los
The Distillery. A Token Optimization Proxy
The context intelligence layer for AI coding agents. Compressing noise, routing content to the right strategy,
Explore other popular mcp server tools:
llmtrim is 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. It is categorized as a MCP Server with 239 GitHub stars.
llmtrim is primarily written in Rust. It covers topics such as agentic-coding, ai, anthropic.
You can find installation instructions and usage details in the llmtrim GitHub repository at github.com/fkiene/llmtrim. The project has 239 stars and 23 forks, indicating an active community.
llmtrim is released under the MPL-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to llmtrim on Agent Skills Hub include headroom-desktop, omni, prompt-caching. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: