MCP servers and skills: search, filter by where they run, and compare.
StructAI offers a robust toolkit for LLM interaction—such as structured outputs, context management, and parallel execution.
SkillMIT★ 8No key
CLIC (Agentic CLI like ClaudeCode) — Command Line Intelligence Companion
SkillMIT★ 1Few starsNo key
Context-aware autonomous coding loop for Claude Code. Fresh context per wave, parallel execution, deep verification, pattern memory.
SkillMIT★ 1Few starsNo key
A Model Context Protocol (MCP) server that provides a managed skill file system for AI assistants.
SkillMIT★ 3Few starsNo key
Agent Smith has taken over your terminal: he recursively breaks down tasks and mercilessly executes them with Claude Code CLI/Opencode/openclaw until your project is "assimilated." Red pill or blue pi
SkillMIT★ 26No key
Builds agent-proof project architecture for long-horizon multi-track (frontend/backend/integration) development. Invoke when planning any project that LLM agents will work on across many sessions, esp
SkillAGPL-3.0★ 4Few starsNo key
Multi-agent autonomous development loop for Claude Code — 17 agents, review pipeline, context management, and parallel execution
SkillLink only★ 7
Open-source harness engineering platform — define, compose, and sync AI skills across providers (Claude, Cursor, Copilot, Windsurf, Cline, OpenAI) from a single source of truth.
SkillMIT★ 2Few starsNo key
Master orchestrator plugin with Context-Driven Development, multi-project workspaces, git submodule support, and 100+ specialized sub-agents
SkillMITFew starsNo key
A reusable contextual engineering framework for Claude Code. Structured workflows, Agent Teams for parallel execution, persistent project knowledge, and auto-learning from every session.
SkillLink only★ 1Few stars
Agent runtime for reinforced ability in complex task decomposition and DAG-style parallel execution. Autonomous task-claiming sub agents and on-demand previous-context fetching enable an efficient and
SkillLink onlyFew stars
Graph Engineering for Agent Skills: a specification and toolchain for dynamically discovering context and building observable, testable, and recoverable agent workflows.
SkillMIT★ 16No key
Autonomous AI coding agent — 126 skills, 7 subagents, 5 platforms. Iterative optimization with automatic rollback, failure memory, and parallel multi-agent execution. Plugin for Claude Code, Cursor, C
SkillMIT★ 27No key
⚡ Competitive multi-wallet NFT auto-minting agent for OpenSea/SeaDrop & direct contracts — low-latency fast-mint (raw EIP-1559, multi-RPC fan-out, RBF), scheduled drops, browser fallback & listing. Ru
SkillMIT★ 6No key
OpsIntelligence is a multi-agent autonomous intelligence platform for DevOps—coordinating specialized agents to monitor systems, analyze context, and execute workflows across infrastructure, repos, an
SkillMIT★ 7No key
pi extension for harness self-improvement (Harness²-style Propose–Probe–Compose) with enforced context economy
SkillMIT★ 3Few starsNo key
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
SkillMIT★ 7No key
A next-gen version control system: in-memory worktrees for parallel agents, native committed secrets, per-file encryption, and signed + intent-deep provenance. Interops with Git.
SkillApache-2.0★ 3Few starsNo key
From raw concept to finished deliverables. A collection of general-purpose autonomous methodologies that execute complex tasks driven purely by your intent.
SkillMIT★ 6No key
Crash-resilient, agent-agnostic project harness built on 12 harness engineering principles. The only AI dev tool that refuses to write code until it knows what done means — and builds a queryable know
SkillMIT★ 4Few starsNo key
Curated Pi package bundling useful extensions, skills, and recovery docs: memory, session notebooks, Magic Docs, Codex UI gallery, and frontend UI workflows.
SkillMIT★ 2Few starsNo key
Enterprise-grade multi-pillar orchestration framework for AI agents (Claude, Gemini, Cursor, Codex, Antigravity). Integrates AST Knowledge Graphs, persistent memory, tool-specific prompt engineering (
SkillMIT★ 3Few starsNo key
Save Codex Plus/Pro allowance with smarter model routing, focused context, minimal edits, and layered verification.
SkillMIT★ 4Few starsNo key
Ground GitHub spec-kit's spec-driven-development loop in a graphify codebase knowledge graph
SkillMIT★ 3Few starsNo key
Who stands behind it
