Registry › Compare › ECC vs Qwen Code

ECC vs Qwen Code

Both are Grade A and 2.4 points apart, so choose on what you weigh most. ECC leads on adoption; Qwen Code rests on broader evidence. Note: ECC's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.

A ECC 91.0

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

affaan-m/ECC · #18 overall · #2 Coding Agents · coverage B (3/5)

Choose ECC if adoption matters most.

+1.3Adoption: 295.7k GitHub stars against 28.9k

A Qwen Code 88.6

An open-source AI coding agent that lives in your terminal.

QwenLM/qwen-code · #53 overall · #4 Coding Agents · coverage A (4/5)

Choose Qwen Code if breadth of evidence matters most.

A vs BEvidence coverage: 4 of 5 independent signal types, against 3

Where they differ

19.6

Safety / IntegrityECC +0.4

19.2

13.3

TransparencyECC +0.2

13.1

19.9

MaintenanceQwen Code +0.1

20.0

18.9

AdoptionECC +1.3

17.6

+1.3

Runtime calibrationECC +0.6

+0.7

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of ECC and Qwen Code, 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	ECCaffaan-m/ECC	Qwen CodeQwenLM/qwen-code
HVTrust score	91.0	88.6
Evidence grade	A	A
Coverage grade	B	A
Overall rank	#18	#53
Rank in Coding Agents	#2	#4
GitHub stars	295.7k	28.9k
Last updated	1d ago	today
Build provenance	Yes	Yes
OSSF Scorecard	5.7 / 10	5.4 / 10
License	MIT	Apache-2.0
Downloads	22k/wk	145k/wk
Trust dimensions (points earned)
Safety / integrity / 25	19.6	19.2
Identity & provenance / 18	18.0	18.0
Transparency / 17	13.3	13.1
Maintenance / 20	19.9	20.0
Adoption / 20	18.9	17.6
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	2 — Anthropic, OpenAI	3 — Anthropic, Google Gemini, OpenAI
Requires API keys	Yes	Yes
Plugin surface	plugins	extensions
Provenance drift	Match	Match

Open in the live compare tool → ECC profile Qwen Code 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 →