Registry › Compare › CodeWhale vs Codex

CodeWhale vs Codex

Codex leads on trust: 89.9/100 (Grade A) against 83.3/100 (Grade A), a 6.6-point gap. CodeWhale leads on supply-chain integrity; Codex leads on adoption.

A CodeWhale 83.3

Open-source agent for the terminal written in Rust. Use any provider or model. Issues & PRs always welcome

Hmbown/CodeWhale · #114 overall · #8 Coding Agents · coverage B (3/5)

Choose CodeWhale if supply-chain integrity matters most.

+1.1Safety / Integrity: 22% of recent commits signed, against 0%

A Codex 89.9

Lightweight coding agent that runs in your terminal

openai/codex · #24 overall · #3 Coding Agents · coverage B (3/5)

Choose Codex if adoption matters most.

+3.9Adoption: 28.2M weekly downloads against 5.6k

Where they differ

16.0

Safety / IntegrityCodeWhale +1.1

14.9

16.1

AdoptionCodex +3.9

20.0

-0.3

Runtime calibrationCodex +3.8

+3.5

3 dimensions identical: Identity 18.0 · Transparency 13.5 · Maintenance 20.0 · Full evidence table

An independent, evidence-based trust comparison of CodeWhale and Codex, 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	CodeWhaleHmbown/CodeWhale	Codexopenai/codex
HVTrust score	83.3	89.9
Evidence grade	A	A
Coverage grade	B	B
Overall rank	#114	#24
Rank in Coding Agents	#8	#3
GitHub stars	41.2k	132.7k
Last updated	today	today
Build provenance	Yes	Yes
OSSF Scorecard	5.9 / 10	5.9 / 10
License	MIT	Apache-2.0
Downloads	6k/wk	28.2M/wk
Trust dimensions (points earned)
Safety / integrity / 25	16.0	14.9
Identity & provenance / 18	18.0	18.0
Transparency / 17	13.5	13.5
Maintenance / 20	20.0	20.0
Adoption / 20	16.1	20.0
Runtime capability surface (full matrix)
MCP server	Declared	Implemented
External providers	—	1 — OpenAI
Requires API keys	No	No
Plugin surface	plugins	extensions
Provenance drift	Unknown	Match

Open in the live compare tool → CodeWhale profile Codex 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 →