ChatDev

ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration

Multi-Agent Systems Python Grade C Listed Apache-2.0
51.8/100
Rank #450 of 1308
Compare ChatDev

How does it stack up against its Multi-Agent Systems neighbours?

Pick any agent to compare →

Thin or incomplete trust evidence. Review carefully before production use.

Open compare tool Suggest correction
Listing state
Listed
Evidence coverage
Grade A · 4/5 signals
Last push
2026-07-24 · 32d ago
Recent change
Rank +1

Is ChatDev safe? ChatDev scores 51.8/100 (Grade C), ranked #450 of 1308 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 4.0/10; recent commits are unsigned; last pushed 2026-07-24. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Multi-Agent Systems

Quick Trust Read

What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-08-24
Rank Moved
Rank dropped 15 spots (#434 → #449)
2026-08-19
Rank Moved
Rank dropped 26 spots (#406 → #432)
2026-08-17
Rank Moved
Rank rose 22 spots (#427 → #405)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 4.0/10. Tighten the weakest checks to improve public safety evidence.
Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.
Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.
Refresh maintenance signals The repo was last pushed 32 days ago. Fresh activity helps separate stable projects from stale ones.
64.7
Activity sub-score · out of 100
#16

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 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 →

Signals refreshed 2026-08-25 08:32 UTC · Repo last pushed 32 days ago

Rank Trend

2026-08-11 2026-08-25

Activity & Reach

Stars
34.1k
Forks
4.3k
Last Push
2026-07-24
32 days ago
Commits (4 wk)
0
Downloads (7d)
22
pypi
HN mentions (30d)
16
Open Issues
47
Rank Change
▼1
was #449

Analysis

HVTrust Dimensions vs Multi-Agent Systems

51.8 / 100 · 100.0% confidence

ChatDev Multi-Agent Systems average (36 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
5.0 / 25
1.2 below avg 6.2
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
in line with avg 11.2
Transparency50% declared license · 50% OSSF Scorecard
11.9 / 17
1.0 above avg 10.9
Maintenance60% last-push freshness · 40% commit activity
9.9 / 20
2.6 below avg 12.5
AdoptionLog-scaled stars · package downloads
12.7 / 20
2.8 above avg 9.9

Activity Inputs

64.7 / 100
StarsRepository reach
27.2 / 30
FreshnessLast push recency
20.6 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
16.9 / 20

Supply Chain Trust

Package Provenance
None
No package attestations found
OSSF Scorecard
4.0 / 10
OpenSSF Scorecard · scanned Aug 24, 2026
Signed Commits
Unable to query
Binary-Artifacts 10
Branch-Protection 6
CI-Tests 1
CII-Best-Practices 0
Code-Review 6
Contributors 10
Dangerous-Workflow 10
Dependency-Update-Tool 0
Fuzzing 0
License 10
Maintained 10
Packaging -1
Pinned-Dependencies 1
SAST 0
Security-Policy 0
Signed-Releases 0
Token-Permissions 0
Vulnerabilities 0

Is ChatDev safe?

Public trust evidence for ChatDev is thin: several supply-chain signals are missing or weak. This does not mean the project is unsafe — it means an outside observer cannot easily verify the usual integrity checks. Treat with extra scrutiny.
Does ChatDev publish package provenance?
No published build provenance is currently detected for ChatDev. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does ChatDev have an OpenSSF Scorecard?
ChatDev has an OpenSSF Scorecard score of 4.0/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is ChatDev actively maintained?
Slowing down. Last push was 32 days ago — keep an eye on whether activity resumes.
What license does ChatDev use?
ChatDev ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

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
Scored in HVTrust

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 Server Support
high confidence
Implemented
ChatDev appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
2 detected
Public provider/service dependencies detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
None detected
No clear plugin system or broad tool surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
low confidence
Unknown
Package source metadata is missing or inconclusive
Detailed evidence is not shown in the public view.
  • 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
Rank 16Score 4HVTrust 3
2026-08-24
Rank Moved
Rank dropped 15 spots (#434 → #449)
2026-08-19
Rank Moved
Rank dropped 26 spots (#406 → #432)
2026-08-17
Rank Moved
Rank rose 22 spots (#427 → #405)
2026-08-16
Rank Moved
Rank dropped 10 spots (#417 → #427)
2026-08-13
Rank Moved
Rank dropped 14 spots (#402 → #416)
2026-08-12
Rank Moved
Rank rose 12 spots (#414 → #402)
2026-08-10
Rank Moved
Rank dropped 18 spots (#392 → #410)
2026-08-08
Rank Moved
Rank dropped 96 spots (#294 → #390)
2026-07-24
Rank Moved
Rank rose 22 spots (#282 → #260)
2026-07-24
HVTrust Changed
HVTrust up 3.2pts (52.8 → 56.0)
2026-07-24
Activity Score Changed
Activity score up 8pts (70 → 78)
2026-07-15
Rank Moved
Rank dropped 15 spots (#254 → #269)
2026-07-14
Rank Moved
Rank dropped 13 spots (#241 → #254)
2026-07-13
Rank Moved
Rank dropped 31 spots (#210 → #241)
2026-06-29
Rank Moved
Rank rose 16 spots (#230 → #214)
2026-06-29
HVTrust Changed
HVTrust up 4.0pts (50.3 → 54.3)
2026-06-29
Activity Score Changed
Activity score up 10pts (65 → 75)
2026-06-26
Activity Score Changed
Activity score down 8pts (72 → 65)
2026-06-24
Rank Moved
Rank dropped 27 spots (#187 → #214)
2026-06-18
Rank Moved
Rank dropped 12 spots (#140 → #152)
2026-06-01
Rank Moved
Rank dropped 12 spots (#96 → #108)
2026-05-29
HVTrust Changed
HVTrust up 9.8pts (47.5 → 57.3)
2026-05-28
Activity Score Changed
Activity score up 14pts (69 → 83)

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 51.8 Grade C
Markdown:
[![HVTrust](https://hvtracker.net/badge/chatdev.svg)](https://hvtracker.net/agents/chatdev)
HTML:
<a href="https://hvtracker.net/agents/chatdev"><img src="https://hvtracker.net/badge/chatdev.svg" alt="HVTrust"></a>

Other agents in Multi-Agent Systems

Data sources
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 v4.3 · Raw JSON