Skip to content

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.

3.4 KB
Raw Blame

AGENTS.md

If you landed here to use Headroom in an app

The PyPI package is headroom-ai; the import and the CLI are headroom.

pip install headroom-ai
from headroom import compress

result = compress(messages, model="gpt-4o")  # OpenAI or Anthropic message dicts
# send result.messages instead of messages; log result.tokens_before / tokens_after / tokens_saved

In-process, no API key, no model download. HEADROOM_OFFLINE=1 makes the run zero-network (no update check, no model or pricing-table downloads, no beacon). Verify without a provider key:

HEADROOM_OFFLINE=1 python -c "from headroom import compress; log='\n'.join(f'INFO step {i} ok' for i in range(3000))+'\nFATAL disk full'; r=compress([{'role':'user','content':'What failed?'},{'role':'assistant','content':None,'tool_calls':[{'id':'c1','type':'function','function':{'name':'logs','arguments':'{}'}}]},{'role':'tool','tool_call_id':'c1','content':log}], model='gpt-4o'); print(r.tokens_before, '->', r.tokens_after, 'FATAL kept:', 'FATAL' in str(r.messages))"
  • FastAPI example: https://docs.headroomlabs.ai/docs/fastapi
  • Full docs index for agents: https://docs.headroomlabs.ai/llms.txt (hand-curated subset: llms.txt in this repo)
  • Coding agents (Claude Code, Codex, Cursor, Copilot): uv tool install --python 3.13 "headroom-ai[all]" then headroom wrap claude
  • headroom.integrations.asgi.CompressionMiddleware is for apps that serve /v1/chat/completions-style routes, not for an app that calls a provider; use compress() for that
  • Canonical repo: https://github.com/headroomlabs-ai/headroom. github.com/chopratejas/headroom redirects here; there is no headroom-sdk org. The PyPI distribution named headroom is a different project.

If you are changing this repo

  • Layout: Python package in headroom/, Rust core and PyO3 extension in crates/ (built by maturin), TypeScript SDK in sdk/typescript/, docs site (Next.js + Fumadocs) in docs/content/docs/, agent plugins in plugins/, examples in examples/.
  • Setup: uv sync --extra dev and make install-git-hooks (pre-commit, commitlint, pre-push). Python checks: uv run ruff check ., uv run ruff format ., uv run pytest. Rust checks: make ci-precheck-rust. All gates: make ci-precheck. See CONTRIBUTING.md.
  • Commits and PR titles are Conventional Commits (feat:, fix:, docs:, ...). Never edit CHANGELOG.md; release-please writes it from PR titles.
  • Every external PR needs a "Real behavior proof" section (setup, exact commands, observed output, what was not tested). Bug fixes need a test that fails before the fix.
  • One docs site: docs/, deployed by Vercel to docs.headroomlabs.ai. wiki/ and the gh-pages branch are not published; do not add content there.
  • Public API examples in README.md, llms.txt, AGENTS.md and docs/ must use names that exist in headroom/compress.py (compress, CompressResult.messages, .tokens_before, .tokens_after, .tokens_saved, .compression_ratio, .transforms_applied).
  • Savings claims anywhere in the repo must match the measured table under "Proof" in README.md: 21-57% on the four agent scenarios, 90%+ on repeated JSON arrays and log lines, little on prose.
  • Version-carrying files (pyproject.toml, plugin and marketplace manifests, sdk/typescript/package.json, server.json) are kept in step by scripts/version-sync.py and gated by scripts/verify-versions.py; add any new one to both.