ChatDev
Website
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
Is ChatDev safe? Thin or incomplete trust evidence. Review carefully before production use.
Compare ChatDev
How does it stack up against its Multi-Agent Systems neighbours?
Pick any agent to compare →In detail: ChatDev scores 49.8/100 (Grade D), ranked #967 of 1371 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 3.5/10; 42% of recent commits are signed; no published advisory affects its latest release (chatdev); last pushed 2026-07-24. Every point is earned from checkable signals — never paid placement. How scoring works →
How ChatDev 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.
- Publish build provenance for its packagesPyPI Trusted Publishing attestations +14.7 → 64.5 C · #11 of 43
- Raise the OSSF Scorecard from 3.5 to 9.0lowest checks: CII-Best-Practices 0, Dependency-Update-Tool 0, Fuzzing 0 +11.5 → 61.3 C · #15 of 43
- Sign every commit42% signed today +2.9 → 52.7 C · #24 of 43
Chain of custody
Scanners check what the code says. This traces who ships ChatDev 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 Partly signed
github.com/OpenBMB/ChatDev, Apache-2.0, last pushed 2026-07-24. 42% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Weak
OpenSSF Scorecard rates the repository's practices 3.5/10 (scanned Oct 8, 2026). The checks that decide who can get a change released:
- Code Review6
- Branch Protection6
- Signed Releases0
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies1
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 6CI-Tests 1CII-Best-Practices 0Code-Review 6Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 0Fuzzing 0License 10Maintained 3Packaging -1Pinned-Dependencies 1SAST 0Security-Policy 0Signed-Releases 0Token-Permissions 0Vulnerabilities 0 -
Published packages Not linked
- PyPI chatdev Source link isn't a GitHub repo No build attestation
Without a build attestation, nothing proves the published files were built from this repository.
-
What you install today No known advisories
Latest release checked: chatdev 0.1.0. No published advisory affects it (OSV, checked 2026-10-09).
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of ChatDev.
Evidence behind this score
Coverage A: 4 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions
Verify this score yourself
Every build re-issues ChatDev’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 ChatDev compares in Multi-Agent Systems
- #27 BettaFish 50.8 +1.0
- #28 mateclaw 50.8 +1.0
- #29 ChatDev 49.8 this agent
- #30 Swarm by OpenAI 44.3 −5.5
- #31 MiroFlow 41.5 −8.3
Bars show each HVTrust score; the tick marks ChatDev’s 49.8.
Where the 49.8 comes from
HVTrust dimensions vs the Multi-Agent Systems average
49.8 / 100 · 100.0% confidenceChatDev Multi-Agent Systems average (43 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 D reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
58.4 / 100Common questions about ChatDev
Does ChatDev publish package provenance?
Does ChatDev have an OpenSSF Scorecard?
Is ChatDev actively maintained?
What license does ChatDev use?
Are ChatDev'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
Maintain ChatDev?
For maintainers
HVTrust scores ChatDev 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/chatdev)
<a href="https://hvtracker.net/agents/chatdev"><img src="https://hvtracker.net/badge/chatdev.svg" alt="HVTrust"></a>
Other agents in Multi-Agent Systems
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON