I kept hitting context limits building coding agents because tool outputs explode (search/log/API payloads), and prompt compression breaks strict tool calling.

Headroom is a local proxy / SDK wrapper that:

- compresses tool outputs (schema-preserving subset of JSON arrays; keeps errors/anomalies/top/relevant)

- trims history as whole tool-call units (no broken function calls)

- stabilizes prefixes so provider caching stops getting invalidated by drift

Try it locally: pip install "headroom-ai[proxy]" && headroom proxy --port 8787 then point your client’s base URL at it.

Repo: https://github.com/chopratejas/headroom

Limitations: best on JSON arrays; text compression is opt-in; if you truly need every row, you’ll need the retrieval escape hatch or per-tool disable.

Do give it a 'star' if you like it.