CowAgent
Website
Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.
Is CowAgent safe? Promising trust profile, but some evidence still deserves review.
Compare CowAgent
How does it stack up against its Agent Frameworks neighbours?
Pick any agent to compare →In detail: CowAgent scores 62.1/100 (Grade C), ranked #596 of 1346 tracked open-source AI agent projects, on evidence coverage C (2 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 4.1/10; 73% of recent commits are signed; last pushed 2026-10-05. Every point is earned from checkable signals — never paid placement. How scoring works →
How CowAgent 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 4.1 to 9.0lowest checks: Branch-Protection 0, CII-Best-Practices 0, Dependency-Update-Tool 0 +10.2 → 72.3 B · #21 of 124
- Sign every commit73% signed today +1.3 → 63.4 C · #47 of 124
Chain of custody
Scanners check what the code says. This traces who ships CowAgent and whether that has changed: from the source repository, through how changes are reviewed and released, to the code you run. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Partly signed
github.com/zhayujie/CowAgent, MIT, last pushed 2026-10-05. 73% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Mixed
OpenSSF Scorecard rates the repository's practices 4.1/10 (scanned Oct 2, 2026). The checks that decide who can get a change released:
- Code Review7
- Branch Protection0
- Signed Releases0
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 0CI-Tests 10CII-Best-Practices 0Code-Review 7Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 0Fuzzing 0License 10Maintained 10Packaging 10Pinned-Dependencies 0SAST 0Security-Policy 0Signed-Releases 0Token-Permissions 0Vulnerabilities 0 -
Published packages None
No registry package. CowAgent is used from its repository, so what you run is whatever you check out: pin a release tag or commit.
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of CowAgent.
Evidence behind this score
Coverage C: 2 of 5 independent evidence types found.
- GitHub repository data
- Package downloads (missing)
- Supply-chain checks
- Public actions (missing)
- Community mentions (missing)
Verify this score yourself
Every build re-issues CowAgent’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 CowAgent compares in Agent Frameworks
- #52 SandBase Harness 62.6 +0.5
- #53 DocsGPT 62.5 +0.4
- #54 CowAgent 62.1 this agent
- #55 Google AX 61.6 −0.5
- #56 Omnigent 61.3 −0.8
Bars show each HVTrust score; the tick marks CowAgent’s 62.1.
Where the 62.1 comes from
HVTrust dimensions vs the Agent Frameworks average
62.1 / 100 · 100.0% confidenceCowAgent Agent Frameworks average (124 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 C reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage C is separate — it grades how many independent signal types back the score (2 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
96.7 / 100Common questions about CowAgent
Does CowAgent publish package provenance?
Does CowAgent have an OpenSSF Scorecard?
Is CowAgent actively maintained?
What license does CowAgent use?
Are CowAgent'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.
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 →
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Detected changes to CowAgent'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 CowAgent?
For maintainers
HVTrust scores CowAgent 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/cowagent)
<a href="https://hvtracker.net/agents/cowagent"><img src="https://hvtracker.net/badge/cowagent.svg" alt="HVTrust"></a>
Other agents in Agent Frameworks
GitHub REST API (repo, commits, stars, forks, license) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON