Headroom
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.
Is Headroom safe? Strong public trust posture, backed by multiple independent signals.
Compare Headroom
How does it stack up against its LLM Gateways & Infra neighbours?
Pick any agent to compare →In detail: Headroom scores 89.4/100 (Grade A), ranked #31 of 1378 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 6.5/10; 100% of recent commits are signed; no published advisory affects its latest release (headroom-ai); last pushed 2026-10-17. Every point is earned from checkable signals — never paid placement. How scoring works →
What Headroom can reach, and who runs it
Checked 2026-10-09, each with its source. PUBLISHER is the company's or project's own statement, which we haven't verified; CHECKED is something we observed ourselves. These facts describe the product. They don't change its score.
What it can reach
- PUBLISHER Runs locally as a proxy between your agent and the model provider, so prompts, tool outputs, logs and files pass through it.
Where your data goes
- PUBLISHER An anonymous telemetry beacon is on by default. It reports compression ratios, counters, provider and model IDs, operating system and architecture, and never prompts, completions, code or file paths. HEADROOM_BEACON=off, DO_NOT_TRACK=1 or HEADROOM_OFFLINE=1 turns it off.
Security practice
- CHECKED Its maintainers have published 1 security advisory (high), in the last 12 months. The repository has a SECURITY.md and GitHub private vulnerability reporting is enabled.
How Headroom could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Raise the OSSF Scorecard from 6.5 to 9.0lowest checks: CII-Best-Practices 0, Fuzzing 0, Pinned-Dependencies 0 +4.3 → 93.7 A · #1 of 14
Chain of custody
Scanners check what the code says. This traces who ships Headroom and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Signed
github.com/headroomlabs-ai/headroom, Apache-2.0, last pushed 2026-10-17. 100% of the last 100 commits carry a verified signature, so changes trace to a verified account.
-
Review and release Mixed
OpenSSF Scorecard rates the repository's practices 6.5/10 (scanned Oct 17, 2026). The checks that decide who can get a change released:
- Code Review10
- Branch Protection8
- Signed Releases0
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 8CI-Tests 10CII-Best-Practices 0Code-Review 10Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 10Fuzzing 0License 10Maintained 10Packaging 10Pinned-Dependencies 0SAST 10Security-Policy 10Signed-Releases 0Token-Permissions 0Vulnerabilities 0 -
Published packages Partly attested
- npm headroom-ai No source link declared No build attestation
- PyPI headroom-ai Source link points back to this repo Build provenance attested
-
What you install today No known advisories
Latest release checked: headroom-ai 0.41.0. No published advisory affects it (OSV, checked 2026-10-17).
Changes to this chain
- 2026-10-15 Package provenance attestation detected
- 2026-10-02 Provenance drift warning cleared (now: unknown)
- 2026-09-23 Package-provenance drift warning: package metadata no longer clearly points at this repo
- 2026-09-02 Package provenance attestation no longer detected
Evidence behind this score
Coverage B: 3 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions (missing)
Verify this score yourself
Every build re-issues Headroom’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.
What this score doesn’t check
It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.
How Headroom compares in LLM Gateways & Infra
- #1 Bifrost 90.3 +0.9
- #2 Headroom 89.4 this agent
- #3 vLLM 81.0 −8.4
- #4 LiteLLM 78.3 −11.1
- #5 Ollama 66.4 −23.0
Bars show each HVTrust score; the tick marks Headroom’s 89.4.
Where the 89.4 comes from
HVTrust dimensions vs the LLM Gateways & Infra average
89.4 / 100 · 100.0% confidenceHeadroom LLM Gateways & Infra average (14 agents)
Quick Trust Read
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
96.8 / 100Common questions about Headroom
Does Headroom publish package provenance?
Does Headroom have an OpenSSF Scorecard?
Is Headroom actively maintained?
What license does Headroom use?
Are Headroom's commits signed?
Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.
Compare Headroom head-to-head
AI agent surface
MCP, providers, tool surface
These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →
- database
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Detected changes to Headroom's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.
Maintain Headroom?
For maintainers
HVTrust scores Headroom from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/headroom)
<a href="https://hvtracker.net/agents/headroom"><img src="https://hvtracker.net/badge/headroom.svg" alt="HVTrust"></a>
Other agents in LLM Gateways & Infra
GitHub REST API (repo, commits, stars, forks, license) · npm Registry (downloads, provenance) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON