ECC Model Card
这是可索引项目报告证据页：它保留 ECC Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
ECC Model Card
| Field | Value |
|---|---|
| Repository | affaan-m/ECC |
| Category | Agent Harness Optimization System |
| Stars / forks snapshot | 191000 / 29500 |
| Language | JavaScript/Rust/Python/Shell/TypeScript |
| License | MIT |
| Raw capture | raw-github/affaan-m_ecc.md |
| Updated by | hourly public metadata update, 2026-05-25 12:21 +0800 |
1. Role in Self Evolve
ECC is an agent harness optimization system that packages skills, instincts, memory, security review, context monitoring and research-first workflows for Claude Code, Codex, OpenCode, Cursor and related coding agents.
2. Working Principle
skills + instincts + memory + hooks + context monitor -> coding-agent performance governance
3. Evidence Path
web GitHub page observed 1,976 commits, MIT license, JavaScript/Rust/Python/Shell/TypeScript stack, 191k stars and 29.5k forks; README describes skills, instincts, memory, security, research-first development, context monitor, strategic compaction and v1.10.0 release on 2026-04-05. Shell GitHub API access remained DNS-blocked and the local gh token was invalid in this run, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain how ECC fits the raw -> classification -> project card -> site/report pipeline. It is useful for comparing whether self-evolution is implemented as skill supply, memory substrate, planning persistence, harness governance, multi-agent orchestration, or benchmark/evaluation infrastructure.
5. Limits
当前未克隆源码，未运行 benchmark、skill install flows、memory experiments、MCP servers、agent evolution loops、security scanners 或 production deployments；star/fork/commit/release 快照来自公开 GitHub 页面文本或可见页面片段。