- proxy: read HEADROOMLICENSE and make usage reporting opt-in
- drop the crewai extra to remove chromadb from the lockfile
- compress: add per-message compression diagnostics (#3058) (fef99cc)
- compress: live-agent densify mode, lossless and cache-safe (#1402) (84f0e84)
- dashboard: add CO₂ Saved card to dashboard and /stats API (#1369) (2bc9419)
- dashboard: give savings metrics one canonical home (#3320) (6af7efe)
Headroom by Headroom Labs
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 cached and can be retrieved on demand.
Agent tooling for cost, context and memory
New · Added to AgentGid on Oct 8, 2026Context compression library and proxyOpen source · Apache-2.0Free to start
Price
Free (OSS)
free and open source
Popularity
#11 in Agent tooling
Gid Score 42 / 100 · #91 of 283 overall
Trend
Slowing down
usage down 20.1% over 30 days
Development
Actively updated
latest 0.40.0, 3d ago
Community
74.8K GitHub stars
143K package downloads a week
What Headroom does
Key facts
| Maker | Headroom Labs |
|---|---|
| Type | Context compression library and proxy |
| License | Apache-2.0 |
| Interfaces | Python library, TypeScript library, CLI, Local proxy, MCP server |
| Works with | Wraps Claude Code, Codex, Cursor, Copilot, Aider, OpenCode, Cline and other agents; works with Anthropic, OpenAI, Bedrock and other providers |
| Main language | Python |
| Open issues and PRs | 379 |
Pricing
Free and open source (Apache-2.0). Compression runs on your machine.
Vendor claim: Vendor says about 20% fewer tokens for coding agents and 60-95% fewer for repetitive JSON, with the same answers (GitHub README); its own benchmarks show 21-57% across four agent scenarios.
Source: official pricing page, checked Oct 9, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (Apache-2.0)
- Where you use itPython library, TypeScript library, CLI, Local proxy, MCP server
- Closest alternativeLiteLLM · all alternatives
Get started with Headroom
| npm | npm install headroom-ai |
|---|---|
| PyPI | pip install headroom-ai |
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Headroom works with
Claude Code OpenAI Codex GitHub Copilot CLI Cursor CLI Cursor Aider OpenCode Cline Goose OpenHands Mistral Vibe Oh My Pi ZCode Agent frameworks and SDKs
Headroom alternatives
Best Headroom alternatives compared · All agent tooling for cost, context and memory
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | ||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 8 |
|
73 | 23.1M | up 1.8% | — | — | 60.4K+60/day | 1.104.2yesterday | Free (OSS) | ||
| 14 |
|
63 | 2.7M | down 3.5% | down 5.6% | — | 190K+368/day | 2.11.03mo ago | Free + $16/mo | ||
| 15 |
|
63 | 8.7M | up 11.2% | down 1.9% | — | 35.5K+39/day | 4.55.0yesterday | Free (OSS) | ||
| 21 |
|
60 | 3.7M | up 2.6% | up 13.7% | — | 14.2K+24/day | 2.53.13d ago | Free + $150/mo | ||
| 34 |
|
55 | 1.7M | up 8.4% | up 33.7% | — | 30.5K+16/day | 0.13.010d ago | Free + $29/mo | ||
| 35 |
|
55 | 351K | up 5.9% | down 6.5% | — | 85K+61/day | 0.9.416d ago | Free (OSS) | ||
| No agents match that filter. | |||||||||||
Headroom news
-
25 agents added to AgentGid
LiteLLM, Firecrawl, Langfuse, E2B, Composio, Crawl4AI, Mem0, Repomix, CodeGPT, Context7, Phoenix, Headroom and 13 more
-
Headroom 0.40.0 released
proxy: read HEADROOMLICENSE and make usage reporting opt-in; drop the crewai extra to remove chromadb from the lockfile; compress: add per-message compression diagnostics (#3058) (fef99cc)
-
Headroom downloads up 37% in a week
143K npm and PyPI downloads in the 7 days to Oct 4, against 104K the week before.
-
Headroom downloads up 28% in a week
104K npm and PyPI downloads in the 7 days to Sep 27, against 81.3K the week before.
-
Headroom 0.39.1 released
proxy: stop the 0.39.0 TPM limiter from refusing large-context requests forever (#3806) (7968122)
What changed: recent Headroom releases
15 stable releases in the last 90 days · Full changelog
- proxy: stop the 0.39.0 TPM limiter from refusing large-context requests forever (#3806) (7968122)
- compression: describe what CCR compression dropped, not just how much (#3635) (62d1cc0)
- hooks: add protectmessages, a hard per-message compression veto (#3772) (d17ac6a)
- opencode: exclude hosts from transport plugin routing (#3668) (0024b57)
- proxy: let /transformations/feed omit message bodies for number-only pollers (#3672) (46ac52d)
- savings: carry exact cache-read cost in history rollups (#3734) (1cb779e)
- savings: show the new-input savings basis beside the whole-wire figure (#3485) (e92cccc)
- beacon: schema v2 — routing/compression training signal, gzip transport (#3253) (67eb910)
- cache: add the headroom-cache-ttl offline TTL estimator the docs reference (#2670) (52c7aa2)
- dashboard: Cost Saved headline card; label per-row savings as message-only (#3353) (17b0412)
- dashboard: show routing savings for this session and all time (#3362) (a811984)
- proxy/model-router: add requiretools route condition (#2362) (ae75ca4)
- proxy: accept the OpenAI Responses shape on the gateway turn (#3661) (be00a79)
- compress: session-aware /v1/compress (sidecar mode) + /v1/usage relay (#3270) (4fa8802)
- proxy: self-limiting session state for the compression-cache registry (#3261) (826b600)
- proxy: unify proxy and sidecar compression on one session engine (#3271) (d12ea50)
- cache/semantic: don't semantic-match an empty query across contexts (#3226) (455f4f2)
- copilot: preserve native enterprise model routing (#2998) (997a479)
- kimi: route managed Kimi Code through the proxy (#3223) (701e461)
- codex: detect ChatGPT auth from idtoken claims so wrap/init emit requiresopenaiauth (#3212) (2f81fa5)
- doctor: report project-scoped Claude routing instead of a false negative (#3213) (8f3e33a)
Headroom popularity and usage data
Headroom was downloaded 143K times from npm and PyPI in the week ending Oct 5, 2026, up 25.5% on the week before and down 20.1% over the last 30 days compared with the 30 before. The GitHub repository has 74.8K stars, 4,616 of them added in the last 30 days. The latest stable release is 0.40.0, published Oct 6, 2026; there were 4 stable releases in the past 30 days. It was mentioned in 1 Hacker News posts and comments over the last 30 days.
Download the raw daily series: headroom.csv
Gid Score breakdown
Adoption48
Community78
Attention0
Momentum30
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
Headroom FAQ
How much does Headroom cost?
Free and open source (Apache-2.0). Compression runs on your machine.
Is Headroom open source?
Yes. Headroom is open source, released under the Apache-2.0 license.
How popular is Headroom?
Headroom was downloaded 143K times from npm and PyPI in the week ending Oct 5, 2026, up 25.5% on the week before and down 20.1% over the last 30 days compared with the 30 before. The GitHub repository has 74.8K stars, 4,616 of them added in the last 30 days. The latest stable release is 0.40.0, published Oct 6, 2026; there were 4 stable releases in the past 30 days.
What is the latest version of Headroom?
The latest stable release we track is 0.40.0, published on Oct 6, 2026.
What are the alternatives to Headroom?
The closest alternatives in the same category by Gid Score are LiteLLM, Firecrawl, Langfuse, E2B.
For the makers of Headroom badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/headroom/)[](https://agentgid.com/agents/headroom/)Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
npm: headroom-ai. PyPI: headroom-ai. GitHub: headroomlabs-ai/headroom. See data sources for how each one is collected.
Product facts and pricing were checked against: github.com, headroomlabs.ai, docs.headroomlabs.ai.