Registry › Compare › ECC vs Gemini CLI

ECC vs Gemini CLI

ECC leads on trust: 90.6/100 (Grade A) against 77.3/100 (Grade B), a 13.3-point gap. ECC leads on supply-chain integrity and provenance; Gemini CLI leads on adoption and 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 90.6

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 · #22 overall · #2 Coding Agents · coverage B (3/5)

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

+8.4Safety / Integrity: OSSF Scorecard 5.5 against 4.7
+7.2Identity / Provenance: package provenance attested, against none
+0.7Transparency: OSSF Scorecard 5.5 against 4.7

B Gemini CLI 77.3

An open-source AI agent that brings the power of Gemini directly into your terminal.

google-gemini/gemini-cli · #235 overall · #10 Coding Agents · coverage A (4/5)

Choose Gemini CLI if adoption matters most.

+0.8Adoption: 445.9k weekly downloads against 18.4k
A vs BEvidence coverage: 4 of 5 independent signal types, against 3

Where they differ

19.3

Safety / IntegrityECC +8.4

10.9

18.0

Identity / ProvenanceECC +7.2

10.8

13.2

TransparencyECC +0.7

12.5

19.9

MaintenanceGemini CLI +0.1

20.0

18.8

AdoptionGemini CLI +0.8

19.6

+1.4

Runtime calibrationGemini CLI +2.1

+3.5

Full evidence table

An independent, evidence-based trust comparison of ECC and Gemini CLI, 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	Gemini CLIgoogle-gemini/gemini-cli
HVTrust score	90.6	77.3
Evidence grade	A	B
Coverage grade	B	A
Overall rank	#22	#235
Rank in Coding Agents	#2	#10
GitHub stars	300.3k	108.7k
Last updated	1d ago	today
Build provenance	Yes	No
OSSF Scorecard	5.5 / 10	4.7 / 10
License	MIT	Apache-2.0
Downloads	18k/wk	446k/wk
Trust dimensions (points earned)
Safety / integrity / 25	19.3	10.9
Identity & provenance / 18	18.0	10.8
Transparency / 17	13.2	12.5
Maintenance / 20	19.9	20.0
Adoption / 20	18.8	19.6
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	2 — Anthropic, OpenAI	1 — Google Gemini
Requires API keys	Yes	Yes
Plugin surface	plugins	extensions
Provenance drift	Match	Match

Open in the live compare tool → ECC profile Gemini CLI 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 →