updated 2026-08-11 20:32 UTC

AutoGen

microsoft/autogen

A programming framework for agentic AI

Agent Frameworks Python Grade B Listed CC-BY-4.0
74.2/100
Rank #99 of 1283
Compare AutoGen

How does it stack up against its Agent Frameworks neighbours?

Pick any agent to compare →

Promising trust profile, but some evidence still deserves review.

Open compare tool Suggest correction
Listing state
Listed
Evidence coverage
Grade A · 4/5 signals
Last push
2026-04-15 · 118d ago
Recent change
No recent signal change

Is AutoGen safe? AutoGen scores 74.2/100 (Grade B), ranked #99 of 1283 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 5.7/10; 100% of recent commits are signed; last pushed 2026-04-15. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Agent Frameworks

#15 Agent Governance Toolkit — 76.2 (B) → #16 DSPy — 75.0 (B) → #18 Microsoft Agent Framework — 73.8 (B) → #19 Pyod — 72.2 (B) →

Quick Trust Read

What Would Improve It
Improve maintenance to lift the weakest part of the trust profile.
Recent Changes
2026-07-14
Activity Went Stale
No commits for 90 days
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 5.7/10. Tighten the weakest checks to improve public safety evidence.
Refresh maintenance signals The repo was last pushed 118 days ago. Fresh activity helps separate stable projects from stale ones.
Compare with another agent Get email alerts for AutoGen View Agent Frameworks Report missing data
55.7
Activity sub-score · out of 100
#17
In Agent Frameworks

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade B 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 2026-08-11 20:32 UTC · Repo last pushed 118 days ago

Activity & Reach

Stars
60.4k
Forks
9.1k
Last Push
2026-04-15
118 days ago
Commits (4 wk)
0
Downloads (7d)
306,076
pypi
HN mentions (30d)
2
Open Issues
555
Rank Change
▼2
was #97

Analysis

HVTrust Dimensions vs Agent Frameworks

74.2 / 100 · 100.0% confidence

AutoGen Agent Frameworks average (118 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
19.6 / 25
11.5 above avg 8.1
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
6.4 above avg 11.6
Transparency50% declared license · 50% OSSF Scorecard
13.3 / 17
1.8 above avg 11.6
Maintenance60% last-push freshness · 40% commit activity
4.1 / 20
10.3 below avg 14.4
AdoptionLog-scaled stars · package downloads
18.8 / 20
7.4 above avg 11.4

Activity Inputs

55.7 / 100
StarsRepository reach
28.7 / 30
FreshnessLast push recency
8.6 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
18.4 / 20

Supply Chain Trust

Package Provenance
Verified
pypi attestation
OSSF Scorecard
5.7 / 10
OpenSSF Scorecard · scanned Aug 10, 2026
Signed Commits
100%
of last 100 commits verified
Binary-Artifacts 10
Branch-Protection 5
CI-Tests 10
CII-Best-Practices 0
Code-Review 6
Contributors 10
Dangerous-Workflow 10
Dependency-Update-Tool 10
Fuzzing 0
License 10
Maintained 0
Packaging 10
Pinned-Dependencies 0
SAST 10
Security-Policy 10
Signed-Releases -1
Token-Permissions 0
Vulnerabilities 0

Is AutoGen safe?

AutoGen has a mixed signal profile. Some trust indicators are present, others are missing. Whether it is safe for your use case depends on which gaps matter to you — review the breakdown below before adopting in production.
Does AutoGen publish package provenance?
Yes. AutoGen's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does AutoGen have an OpenSSF Scorecard?
AutoGen has an OpenSSF Scorecard score of 5.7/10. 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 AutoGen actively maintained?
Slowing down. Last push was 118 days ago — keep an eye on whether activity resumes.
What license does AutoGen use?
AutoGen ships under CC-BY-4.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are AutoGen's commits signed?
100% of the last 100 commits to AutoGen are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

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
AutoGen appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
1 detected
Public provider/service dependencies detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
high confidence
Extensions
Extension based plugin/integration 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
How this surface has changed

Detected changes to AutoGen'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.

2026-07-14
Activity Went Stale
No commits for 90 days
2026-05-24
Provenance Added
Package provenance attestation detected

Maintain AutoGen?

For maintainers

HVTrust scores AutoGen 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.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
Scorecard 1Provenance 1Rank 1HVTrust 1Stale 1
2026-07-14
Activity Went Stale
No commits for 90 days
2026-05-29
HVTrust Changed
HVTrust up 10.0pts (68.2 → 78.2)
2026-05-25
Rank Moved
Rank dropped 26 spots (#36 → #62)
2026-05-24
Provenance Added
Package provenance attestation detected
2026-05-24
Scorecard Added
OSSF Scorecard: 5.9/10
GitHub → PyPI: autogen-agentchat

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 74.2 Grade B
Markdown:
[![HVTrust](https://hvtracker.net/badge/autogen.svg)](https://hvtracker.net/agents/autogen)
HTML:
<a href="https://hvtracker.net/agents/autogen"><img src="https://hvtracker.net/badge/autogen.svg" alt="HVTrust"></a>

Other agents in Agent Frameworks

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