headroom

Read the source on GitHub Project homepage

What it does

An editorial selection.

Compression layer for everything an agent reads: tool outputs, logs, RAG chunks, files and history. Runs locally as a library or a proxy.

Why it is listed

Same answers on fewer tokens, and no content leaves your machine. The proxy mode needs no code changes.

GitHub describes it as: 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.

Counts were observed on 27/10/2026, 23:15:40 UTC. Observations older than 36 hours are excluded from current movement rankings.

Repository at a glance

Stars: 78,040
Forks: 6,071
Open issues: 291
Merged PRs: 2,197
Commits, last 30 days: 439
Stars, 7 days: unavailable
Stars, 30 days: unavailable

Counts observed on 27/10/2026, 23:15:40 UTC. Growth uses complete dated windows; see Methodology.

History

History: 2 observations, 2026-10-27 to 2026-10-28. Dots are observations; lines connect consecutive daily observations only.

Project details

Language: Python
Licence: Apache-2.0
Created: 7 Jan 2026
Last push: 27 Oct 2026
Latest release: v0.42.0 · 26 Oct 2026
Category: Context, Memory & Cost
Topics: agent ai anthropic compression context-engineering context-window fastapi langchain llm mcp
Observed: 2026-10-27 23:15:40 UTC

Explore and get started

Use the project's own documentation for supported platforms, dependencies and installation steps. The README and release notes are maintained by headroomlabs-ai.

Read the README and setup instructionsFeatures, prerequisites, examples and documentation links.
Browse releases and changelogsPublished versions and the changes made between releases.
Check licence and usage termsApache-2.0 is the licence reported by GitHub; read the repository terms before use.
Read pull requestsProposed changes and development discussions.
Browse reported issuesKnown problems, feature requests and maintainer responses.

Development context

These are observations of work in the repository. They do not establish quality, security or support commitments.

Total commits on default branch: 3,377
Open pull requests: 287
Closed issues, lifetime: 1,000
Median time to close an issue: 2.5 days
Median time to merge a pull request: 2.6 days

Close and merge times use up to 20 most recently updated closed issues or merged pull requests. They omit unresolved work and are context, not a maintenance score. Sample limits.

Other projects in Context, Memory & Cost, ordered by shared topics and then name. These are discovery links, not equivalence claims.