Registry › Compare › Codex vs OpenHands

Codex vs OpenHands

Codex leads on trust: 89.9/100 (Grade A) against 74.9/100 (Grade B), a 15.0-point gap. Codex leads on supply-chain integrity and provenance; OpenHands rests on broader evidence. Note: Codex's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.

A Codex 89.9

Lightweight coding agent that runs in your terminal

openai/codex · #26 overall · #3 Coding Agents · coverage B (3/5)

Choose Codex if supply-chain integrity and provenance matter most.

  • +7.2Identity / Provenance: package provenance attested, against none
  • +4.5Safety / Integrity: OSSF Scorecard 5.9 against 4.3
  • +1.3Transparency: OSSF Scorecard 5.9 against 4.3
  • +1.1Adoption: 15.5M weekly downloads against 184.3k
B OpenHands 74.9

🙌 OpenHands: AI-Driven Development

OpenHands/OpenHands · #252 overall · #11 Coding Agents · coverage A (5/5)

Choose OpenHands if breadth of evidence matters most.

  • A vs BEvidence coverage: 5 of 5 independent signal types, against 3

Where they differ

14.9
Safety / IntegrityCodex +4.5
10.4
18.0
Identity / ProvenanceCodex +7.2
10.8
13.5
TransparencyCodex +1.3
12.2
20.0
MaintenanceCodex +0.1
19.9
20.0
AdoptionCodex +1.1
18.9
+3.5
Runtime calibrationCodex +0.8
+2.7

Full evidence table

An independent, evidence-based trust comparison of Codex and OpenHands, two Coding Agents projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal Codexopenai/codex OpenHandsOpenHands/OpenHands
HVTrust score 89.9 74.9
Evidence grade A B
Coverage grade B A
Overall rank #26 #252
Rank in Coding Agents #3 #11
GitHub stars 129.7k 91.2k
Last updated today 1d ago
Build provenance Yes No
OSSF Scorecard 5.9 / 10 4.3 / 10
License Apache-2.0 MIT
Downloads 15.5M/wk 184k/wk
Trust dimensions (points earned)
Safety / integrity / 25 14.9 10.4
Identity & provenance / 18 18.0 10.8
Transparency / 17 13.5 12.2
Maintenance / 20 20.0 19.9
Adoption / 20 20.0 18.9
Runtime capability surface (full matrix)
MCP server Implemented Declared
External providers 1 — OpenAI —
Requires API keys No Yes
Plugin surface extensions plugins
Provenance drift Match Match
Open in the live compare tool → Codex profile OpenHands profile More Coding Agents →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →