Daily
headroom
headroomlabs-ai
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.
★ 77k↑ +549⑂ 6.0k
- Rank
- #10
- On board
- 3 days · first seen 10-19
- Move
- ▼3
Rank historyrank by day · 8 days archived
10-20Best #710-21
Repository panorama
from public APIs, independent of our rankingsHealth
activity, response time, maintainers- Last push
- 5h ago
- Issue response
- 3.2d
- Contributors
- 42
- Release cadence
- v0.5.28
median over 100 closed
top: 1346 commits
median 11d apart
Commit rhythmweekly commits, last 26 weeks
985 in 13w, fewer than the 13 before
Ecosystem
who uses it, what it depends on- Dependent repos
- —
- npm downloads
- 31k
- Depends on
- 16
headroom-ai · last week
PyPI · pyproject.toml
Depends on · pyproject.toml
tiktokenpydanticlitellmclickrichopentelemetry-apiast-grep-clipyyamls3.11,AMD64aarch64amd64arm64x86_64
Community
Hacker NewsApache-2.0Pythonagentaianthropiccompressioncontext-engineeringcontext-windowfastapilangchain