Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Repository Index
47,133 repositories indexed
1–16 of 16 · Most stars
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
2,884+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection and plan preview. CLI, MCP and plugins.
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them into replayable regression tests, and block PRs that regress. Self-hostable.
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
The foundation layer for agentic intelligence.
MCP-NixOS - Model Context Protocol Server for NixOS resources
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
MCP desktop companion for AI agent status, usage tracking, and everyday tools. Anything Universe · 桌面伙伴与日常工具入口。
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.
Persistent decision memory for AI agents: rationale, rejected approaches, and entity history. Connect any compatible agent through local MCP or the CLI.
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.
Decentralized agent memory for the Lightning economy. Nostr identity, L402 payments, MCP server.