All tools
Headroom
v0.25.0 · Apache 2.0
The context compression layer for AI agents. Compresses tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers.
Quick Start
$ pip install "headroom-ai[all]"
$ headroom wrap claude
$ headroom wrap claude
Location in QuantWise OS:
quantwiseiq-tools/headroom/
Integration Modes
Library
compress(messages) in Python or TypeScript
Proxy
headroom proxy --port 8787, zero code changes
Agent Wrap
headroom wrap claude|codex|cursor|aider
MCP Server
headroom_compress, headroom_retrieve, headroom_stats
Token Savings (Real Workloads)
| Workload | Before | After | Savings |
|---|---|---|---|
| Code search (100 results) | 17,765 | 1,408 | 92% |
| SRE incident debugging | 65,694 | 5,118 | 92% |
| GitHub issue triage | 54,174 | 14,761 | 73% |
| Codebase exploration | 78,502 | 41,254 | 47% |
Repository
github.com/chopratejas/headroomAgent Support
Claude CodeCodexCursorAiderCopilot CLIOpenClawLangChainAgno
Key Features
- • 60-95% token reduction, same accuracy
- • Reversible compression (CCR)
- • Cross-agent shared memory
- • headroom learn — auto-fixes from failures
- • MCP server integration
- • 27.1k GitHub stars
Tech Stack
PythonRustTypeScriptONNXHF Transformers