Headroom Marketplace
- 62.8k repo stars
- Updated July 28, 2026
- headroomlabs-ai/headroom
headroom-marketplace installs Headroom hooks; Headroom is a context-compression layer that shrinks what an AI agent reads before it reaches the LLM.
About
headroom-marketplace installs Headroom's startup hooks for Claude Code and GitHub Copilot CLI. Headroom is a context-compression layer that shrinks everything an AI agent reads (tool outputs, logs, RAG chunks, files, and conversation history) before it reaches the LLM, aiming for the same answers with fewer tokens. It ships as a library, a proxy, and an MCP server exposing headroom_compress, headroom_retrieve, and headroom_stats, and the compression is reversible. Developers use it to cut token spend and stay within context limits on long agent sessions.
- Context-compression layer that runs before the LLM
- Claims 60-95% fewer tokens for JSON data, 15-20% for coding agents
- MCP tools headroom_compress, headroom_retrieve, headroom_stats
- Local-first and reversible; this plugin adds startup hooks
Headroom Marketplace by the numbers
- Data as of Jul 28, 2026 (Skillselion catalog sync)
/plugin marketplace add headroomlabs-ai/headroomAdd your badge
Show developers this marketplace is listed on Skillselion. Paste this into your README.
| repo stars | ★ 62.8k |
|---|---|
| Last updated | July 28, 2026 |
| Repository | headroomlabs-ai/headroom ↗ |
How do I cut the token cost and context bloat of everything my AI agent reads without losing answers?
token-optimization
Who is it for?
Developers running long or token-heavy agent sessions who want lower cost while keeping the same answers.
Skip if: Short one-off prompts where token spend is negligible and compression overhead is not worth it.
What you get
Tool outputs, logs, RAG chunks, files, and history are compressed before the LLM, with reversible originals cached for retrieval.
By the numbers
- 60-95% fewer tokens for JSON data
- 15-20% fewer tokens for coding agents
- Apache 2.0 licensed
headroom-marketplace capabilities & compatibility
Free, open-source (Apache 2.0); library, proxy, and MCP run local-first.
- Capabilities
- context compression · token optimization · mcp integration · cross agent memory
- Use cases
- token optimization · memory
- Runs
- Runs locally
- Pricing
- Free
What headroom-marketplace says it does
Headroom startup hooks for Claude Code and GitHub Copilot CLI.
Plugins in this marketplace
1 plugin - install individually after you add the marketplace.
Recommended Marketplaces
FAQ
What does the headroom marketplace plugin do?
It exposes lightweight startup hooks for Claude Code and GitHub Copilot CLI that ensure a matching durable headroom deployment is running.
How does Headroom reduce tokens?
It compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach the LLM, and the compression is reversible.