Alternatives to headroomlabs-ai/headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Source: headroomlabs-ai/headroom · SPDX licence: Apache-2.0

Comparable repositories

  • jettison-ai/jettison · Token optimizer for AI coding agents. Repo map, read pruning, prose compression — client-side, no proxy. 20-25% fewer turns, measured by live A/B. Verify it on your own repo. · Apache-2.0
  • zhayujie/cowagent · Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install. · MIT
  • juliusbrussee/caveman · 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman. · Apache-2.0
  • snchimata/tokenfold · Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls. · Apache-2.0
  • ojuschugh1/sqz · Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls. · Apache-2.0
  • 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). · MPL-2.0
  • sentelabsai/openexecutive · AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js). · Apache-2.0
  • jgravelle/jcodemunch-mcp · Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Tree-sitter powered, ~95% fewer tokens per lookup. Works with Claude Code, Cursor, Codex & any MCP client. 1.3T+ tokens saved. · MIT
  • agentdeskai/browser-tools-mcp · Monitor browser logs directly from Cursor and other MCP compatible IDEs. · MIT
  • diegosouzapw/omniglyph · Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-provider billing math (Anthropic/OpenAI/Gemini), fail-closed gates, measured benchmarks. CLI + proxy + Cloudflare Workers. Docs in 42 languages. Part of the OmniRoute family. · MIT

Comparison from the dated registry snapshot. Review each project and licence independently.