Headroom 0.42.0 released
A feature and stability release adding token savings tracking, turn hook request rewriting, and numerous fixes across caching, compression, and API integrations.
What changed in 0.42.0
- Token savings now tracked per-request on outcome snapshots and reported consistently across gateway and proxy paths.
- Turn hooks can rewrite OpenAI Responses requests over HTTP and WebSocket connections.
- Cache improvements: compression cache bounded in memory with rest in SQLite, prefix-tracker state preserved across restarts, indented lines kept intact in OpenAI normalization.
- Fixes for Gemini continuation tools, image encoding, CCR streaming, memory retrieval queries, and multiple API-specific handling issues.
- Security updates: rustls bumped for RUSTSEC-2026-0346..0349 and mcp updated for CVE-2026-59951.
Summarised by AgentGid from Headroom Labs's official release notes on GitHub, as reported there; read the original before relying on it. Price, status and release dates come from our daily data.
Headroom at a glance
| What it is | Compresses tool outputs, logs, files, RAG chunks and conversation history before they reach the model, so agents use fewer tokens. Runs locally as a library, a proxy, an agent wrapper or an MCP server; originals stay ca… |
|---|---|
| Latest version | 0.44.0, Nov 10, 2026. This page is about an earlier release. |
| Release pace | 5 stable releases in the last 30 days; 0.42.0 came 12 days after the previous one |
| Price | Free (OSS). Free and open source (Apache-2.0). Compression runs on your machine. Official pricing ↗ (checked Oct 9, 2026) |
| Downloads, last 7 days | 143K down 10.2% |
| Gid Score | 54 #8 in Agent tooling for cost, context and memory |
