Agent Switchboard

Compresses tool outputs, logs, RAG chunks, files, and history locally before they reach the model, as a Python or TypeScript library, a drop-in proxy, an agent wrapper, or an MCP server.

Use it now

Keep it with up to 9 other tools you're setting up, then share them all as one link.

Try this first

Ask your assistant, with Headroom connected:

  • Inline Compression

    Use Headroom to compress a message list in Python or TypeScript: ‹what you need›

  • Agent Wrapping

    Use Headroom to launch Claude Code, Codex, Cursor, Aider, and other agents: ‹what you need›

  • Reversible Retrieval

    Use Headroom to cache originals: ‹what you need›

Connect it over MCP

Ask your coding agent to set it up

Connect Headroom as an MCP server, following its setup instructions at https://github.com/headroomlabs-ai/headroom

Its page: github.com/headroomlabs-ai/headroom

Install the CLI

Install it as its own instructions say.

Its page: github.com/headroomlabs-ai/headroom

Call the API

Auth None needed

Its page: github.com/headroomlabs-ai/headroom

Compare

Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.

Access
APIMCPCLI
Auth
None
Skills
5

Skills

  • Inline Compression

    Compresses a message list in Python or TypeScript with compress(), routing JSON, source code, and prose to a matching compressor.

  • Compression Proxy

    Runs headroom proxy as a local drop-in endpoint that compresses traffic to Anthropic, OpenAI, or Bedrock with no application code changes.

  • Agent Wrapping

    Launches Claude Code, Codex, Cursor, Aider, and other agents routed through Headroom with headroom wrap, and undoes it with unwrap.

  • Reversible Retrieval

    Caches originals locally so the model can call headroom_retrieve over MCP when it needs the full text behind a compressed chunk.

  • Session Learning

    Mines failed sessions with headroom learn and writes corrections to CLAUDE.local.md, CLAUDE.md, AGENTS.md, or another agent file.

Infrastructure & OpsCode & DevToolscontext-compressiontoken-reductionllm-proxylocal-mcpprompt-cachingclaude-codeopen-source
Visit Agent
headroom
Compresses tool outputs, logs, RAG chunks, files, and history locally before they reach the model, as a Python or TypeScript library, a drop-in proxy, an agent wrapper, or an MCP server.
try this first
Ask your assistant, with Headroom connected:
Use Headroom to compress a message list in Python or TypeScript: ‹what you need›inline-compress
Use Headroom to launch Claude Code, Codex, Cursor, Aider, and other agents: ‹what you need›agent-wrap
Use Headroom to cache originals: ‹what you need›reversible-retrieval
use it now
Connect Headroom as an MCP server, following its setup instructions at https://github.com/headroomlabs-ai/headroommcp.setup-prompt
None neededapi.auth
fields
nameHeadroom
providerHeadroom Labs
urlhttps://github.com/headroomlabs-ai/headroom
categoriesinfrastructure · code-devtools
accessapi · mcp · cli
authnone
streamingfalse
pushfalse
verifiedtrue
officialfalse
sponsoredfalse
tagscontext-compression, token-reduction, llm-proxy, local-mcp, prompt-caching, claude-code, open-source
skills
inline-compressInline CompressionCompresses a message list in Python or TypeScript with …
compression-proxyCompression ProxyRuns headroom proxy as a local drop-in endpoint that co…
agent-wrapAgent WrappingLaunches Claude Code, Codex, Cursor, Aider, and other a…
reversible-retrievalReversible RetrievalCaches originals locally so the model can call headroom…
headroom-learnSession LearningMines failed sessions with headroom learn and writes co…
alternatives
/agents/headroom/alternatives8 listedclaw-compactor, rtk, prismer-cloud
compare
/compare?a=headroom&b=claw-compactor&c=rtkwith claw-compactor, rtk