10 alternatives to ECC

affaan-m/ecc — The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. (286,740 stars, MIT, ai, dev-tools, integration).

These are the closest projects in the JustClaw-It index that we serve licence-cleared code from, ranked by relevance and by our code-quality score (1–10, the mean over each repo's graded components: completeness, code quality, deployability, reusability, strategic value). JustClaw-It also serves 667 licence-cleared components from affaan-m/ecc itself.

The alternatives in detail

• kkkkhazix/khazix-skills
  数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents
  score 6.6/10 · MIT permissive · 21,654 stars · 7 components · search them · alternatives
• jnmetacode/agency-agents-zh
  🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计）。搭配编排器 agency-orchestrator，一句话即可让多位专家按 DAG 自动协作。
  score 6.1/10 · MIT permissive · 21,521 stars · 13 components · search them · alternatives
• trailhq/trail-code
  Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
  score 7.3/10 · MIT permissive · 10,743 stars · 361 components · search them
• leonxlnx/unlazy
  Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 resear
  score 6.3/10 · MIT permissive · 4,077 stars · 9 components · search them
• dietrichgebert/ponytail
  Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
  score 6.7/10 · MIT permissive · 175,543 stars · 37 components · search them · alternatives
• duthaho/claudekit
  A verification-first engineering toolkit for Claude Code. Built for senior ICs and tech leads who already know how to ship production code — and want a workflow that keeps the discipline tight without getting in the way.
  score 6.9/10 · MIT permissive · 97 stars · 12 components · search them
• rtk-ai/rtk
  CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
  score 6.9/10 · Apache-2.0 permissive · 84,415 stars · 277 components · search them · alternatives
• sail-research-lab/cheetahclaws
  CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems
  score 5.4/10 · Apache-2.0 permissive · 789 stars · 316 components · search them
• trailhq/graft
  Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
  score 6.0/10 · MIT permissive · 10,591 stars · 172 components · search them
• matteo-stratega/claude-cortex
  Cortex — an operating system for Claude Code. Persistent memory, specialized agents, smart skills, enforcement hooks.
  score 4.8/10 · MIT permissive · 8 stars · 12 components · search them

Licence data: JustClaw-It's per-repo licence policy. Is ECC still maintained? Check it. Licence details: licence checker. Ranking data from 2026-10-27T23:04:12Z.