SWE-AF

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

Coding Agents Go Grade D Listed Apache-2.0
20.7/100
Rank #447 of 468
Compare SWE-AF

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

Open compare tool Suggest correction
Listing state
Listed
Evidence coverage
Grade D · 1/5 signals
Last push
2026-08-03 · 1d ago
Recent change
New

Is SWE-AF safe? SWE-AF scores 20.7/100 (Grade D), ranked #447 of 468 tracked open-source AI agent projects, on evidence coverage D (1 of 5 independent signal types). The public evidence: no package-provenance attestation found; no OSSF Scorecard result yet; 64% of recent commits are signed; last pushed 2026-08-03. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Coding Agents

Quick Trust Read

What Would Improve It
Add or improve OSSF Scorecard coverage so safety checks are easier to verify.
Recent Changes
2026-08-03
Newly Listed
First tracked at rank #447
Maintainer Checklist
Add Scorecard coverage Expose the repository to OpenSSF Scorecard checks so supply-chain posture is easier to verify.
Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.
69.7
Activity sub-score · out of 100
#56

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 D is separate — it grades how many independent signal types back the score (1 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-08-04 02:30 UTC · Repo last pushed yesterday

Rank Trend

2026-08-03 2026-08-04

Activity & Reach

Stars
961
Forks
161
Last Push
2026-08-03
yesterday
Commits (4 wk)
20
Downloads (7d)
HN mentions (30d)
Open Issues
2
Rank Change
=
was #447

Analysis

HVTrust Dimensions vs Coding Agents

20.7 / 100 · 50.0% confidence

SWE-AF Coding Agents average (59 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
3.2 / 25
5.2 below avg 8.4
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
1.0 below avg 11.8
Transparency50% declared license · 50% OSSF Scorecard
8.5 / 17
2.9 below avg 11.4
Maintenance60% last-push freshness · 40% commit activity
17.2 / 20
2.4 above avg 14.8
AdoptionLog-scaled stars · package downloads
7.2 / 20
5.4 below avg 12.6

Activity Inputs

69.7 / 100
StarsRepository reach
17.9 / 30
FreshnessLast push recency
24.9 / 25
ActivityRecent commits
16.5 / 25
CommunityFork signal
10.3 / 20

Supply Chain Trust

Package Provenance
None
No package attestations found
OSSF Scorecard
Not available
Signed Commits
64%
of last 100 commits verified

Is SWE-AF safe?

Public trust evidence for SWE-AF 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 SWE-AF publish package provenance?
No published build provenance is currently detected for SWE-AF. 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-AF have an OpenSSF Scorecard?
No OpenSSF Scorecard data is currently published for SWE-AF. Maintainers can enable the Scorecard GitHub Action to get a public score; without it, automated supply-chain hygiene is harder for outsiders to verify.
Is SWE-AF actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does SWE-AF use?
SWE-AF ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are SWE-AF's commits signed?
64% of the last 100 commits to SWE-AF 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
None detected
No MCP server signal detected.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
4 detected
Public provider/service dependencies detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
medium confidence
Declared
Declared plugin/integration surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
N/A
No package source configured
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live

Maintain SWE-AF?

For maintainers

HVTrust scores SWE-AF 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
Listed 1
2026-08-03
Newly Listed
First tracked at rank #447

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 20.7 Grade D
Markdown:
[![HVTrust](https://hvtracker.net/badge/swe-af.svg)](https://hvtracker.net/agents/swe-af)
HTML:
<a href="https://hvtracker.net/agents/swe-af"><img src="https://hvtracker.net/badge/swe-af.svg" alt="HVTrust"></a>

Other agents in Coding Agents

Data sources
GitHub REST API (repo, commits, stars, forks, license)
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.2 · Raw JSON