StackMap
Subscribe

ECC vs maggy

Cross-harness 'operating system' for coding agents — 268 skills, 66 agents, hooks, rules, memory persistence, instinct-based continuous learning and AgentShield security scanning. MIT. — versus — Claude Code config pack + optional local harness: TDD-enforcing hooks, 67 skills, quality gates, persistent memory — plus a dashboard routing each task across 13 models by cost-aware blast score.

The curated verdict

Both are kitchen-sink 'operating systems' over Claude Code — skills, hooks, rules, memory. ecc spreads across harnesses (268 skills, 66 agents); Maggy stays Claude-centric and adds a local server with cost-aware multi-model routing and a dashboard.

ECCmaggy
Stars234k704
Forks36k56
LanguageJavaScriptPython
LicenseMITMIT
Last activityyesterday14 days ago
Topicscoding, skillscoding, skills
Curated connections62

ECC — the curator's take

The kitchen-sink option, and the most popular one by a wide margin: one install gives Claude Code, Codex, Cursor, OpenCode and friends a full operating layer — session-memory hooks, learned instincts, quality gates, orch-* orchestrator commands, worktree lifecycle, security scanning — plus three genuinely good guides on token optimization, memory and agentic security. When NOT: it's maximalist. Hundreds of skills and global hooks add context weight, and the README's own top warning is about broken stacked installs — start with the minimal/no-hooks profile and never mix the plugin with the manual installer. If you only want one capability, take the surgical tool instead: claude-reflect for learning-from-corrections, pro-workflow for session memory, asm or skillkit for skill management. Watch the upsell surface (Pro app, sponsors) — the OSS core is MIT and complete.

maggy — the curator's take

Two products in one repo — know which you're installing. Bootstrap is 30 seconds of files in ~/.claude and gives you the enforcement layer: stop-hooks that hold 'done' hostage to passing tests, quality gates, memory that survives compaction. Maggy is a bigger commitment — a FastAPI server, dashboard and 13-tier router sending ~80% of tasks to DeepSeek, a cost bet you should verify on your own work. 1100+ tests at ★704 is a real signal. Same warning as every kitchen-sink: 67 skills and hooks change how Claude behaves everywhere — read them before they run your sessions.