SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for o

Coding Agents Python Grade C Listed MIT
Listing state
Listed
HVTrust
61.1/100 · Grade C
Last push
2026-06-01 · 3d ago
Recent change
Rank +8

Quick Trust Read

Verdict
Promising trust profile, but some evidence still deserves review.
61.1/100 · Grade C
Strongest Signal
Transparency
13.4/17
Weakest Signal
Safety / Integrity
11.6/25
What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-06-04
Rank Moved
Rank dropped 14 spots (#105 → #119)
2026-06-02
Rank Moved
Rank dropped 10 spots (#97 → #107)
2026-06-01
Rank Moved
Rank dropped 16 spots (#81 → #97)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 5.8/10. 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.
69.7
Activity Score · out of 100
61.1
HVTrust Score · out of 100
#119
Global Rank · of 206
#14

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. Full methodology →

Signals refreshed 2026-06-04 18:04 UTC · Repo last pushed 3 days ago

Rank Trend

2026-05-23 2026-06-04

Activity & Reach

Stars
19.4k
Forks
2.1k
Last Push
2026-06-01
3 days ago
Commits (4 wk)
1?
Downloads (7d)
92
pypi
HN mentions (30d)
2
Open Issues
37
Rank Change
▼14
was #105

Analysis

HVTrust Dimensions

61.1 / 100 · 100.0% confidence
Safety / IntegrityOSSF, provenance, signatures
11.6 / 25
Identity / ProvenanceListing and build link
10.8 / 18
TransparencyLicense and public checks
13.4 / 17
MaintenanceFreshness and commits
12.4 / 20
AdoptionStars and downloads
12.9 / 20

Activity Inputs

69.7 / 100
StarsRepository reach
25.7 / 30
FreshnessLast push recency
24.6 / 25
ActivityRecent commits
3.8 / 25
CommunityFork signal
15.5 / 20

Supply Chain Trust

Package Provenance
None
No package attestations found
OSSF Scorecard
5.8 / 10
via deps.dev · OpenSSF
Signed Commits
87%
of last 100 commits verified
Binary-Artifacts 6
Branch-Protection 3
CI-Tests 8
CII-Best-Practices 0
Code-Review 5
Contributors 10
Dangerous-Workflow 10
Dependency-Update-Tool 10
Fuzzing 0
License 10
Maintained 8
Packaging -1
Pinned-Dependencies 0
SAST 0
Security-Policy 10
Signed-Releases -1
Token-Permissions 0
Vulnerabilities 10

Is SWE-agent safe?

SWE-agent 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 SWE-agent publish package provenance?
No published build provenance is currently detected for SWE-agent. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does SWE-agent have an OpenSSF Scorecard?
SWE-agent has an OpenSSF Scorecard score of 5.8/10. 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 SWE-agent actively maintained?
Actively maintained. The repository was pushed to within the last 3 day(s).
What license does SWE-agent use?
SWE-agent ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are SWE-agent's commits signed?
87% of the last 100 commits to SWE-agent 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.

Runtime trust — coming soon

HVTrust currently scores supply-chain signals. We're adding runtime trust next: what an agent actually does when it runs — what it can reach, which tools it carries, what external services it depends on. Track progress on the roadmap →

  • MCP support
  • Tool / plugin surface
  • External service deps
  • Package provenance drift

Maintain SWE-agent?

HVTrust scores SWE-agent 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

Rank 6HVTrust 2Scorecard 1
2026-06-04
Rank Moved
Rank dropped 14 spots (#105 → #119)
2026-06-02
Rank Moved
Rank dropped 10 spots (#97 → #107)
2026-06-01
Rank Moved
Rank dropped 16 spots (#81 → #97)
2026-05-29
HVTrust Changed
HVTrust up 9.8pts (50.4 → 60.2)
2026-05-28
Rank Moved
Rank dropped 24 spots (#64 → #88)
2026-05-27
Scorecard Added
OSSF Scorecard: 5.9/10
2026-05-27
HVTrust Changed
HVTrust up 15.9pts (36.2 → 52.1)
2026-05-25
Rank Moved
Rank dropped 23 spots (#42 → #65)
2026-05-24
Rank Moved
Rank dropped 15 spots (#27 → #42)

Embed Badge Badge guide for maintainers →

HVTrust 61.1 Grade C
Markdown:
[![HVTrust](https://hvtracker.net/badge/swe-agent.svg)](https://hvtracker.net/agents/swe-agent)
HTML:
<a href="https://hvtracker.net/agents/swe-agent"><img src="https://hvtracker.net/badge/swe-agent.svg" alt="HVTrust"></a>

Other agents in Coding Agents

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OSSF Scorecard via deps.dev · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v3.1 · Raw JSON