Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Portable Agent Skills for building, operating, evaluating, and governing LLM-Wiki knowledge systems.
SkillMIT★ 4Few starsNo key
The reference architecture for LLM-maintained knowledge vaults — schema, lifecycle loop, machine verification, self-installation
SkillMIT★ 13No key
Local-first task memory for AI coding agents: durable task bundles, checkpoints, worktrees, MCP tools, hooks, and optional Jira import.
Node.jsMIT★ 9No key
The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.
Node.jsMIT★ 2.2kNo key
MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge
Node.jsMIT★ 2Few starsNo key
Node.jsMIT★ 2Few starsNo key
Continuously-updated catalog + query API for LLM provider availability and pricing. MCP server + HTTP API. weiseer probe P-001.
MCPLink onlyFew stars
MCP server for token-efficient large document analysis via the use of REPL state
Node.jsApache-2.0★ 150No key
MCP server for delegating mechanical tasks to local LLMs via Ollama. Claude does the thinking, your local model does the grunt work.
Node.jsMIT★ 13No key
A Model Context Protocol (MCP) server that provides access to multiple Large Language Model (LLM) APIs including ChatGPT, Claude, Gemini, Mistral, Kimi K2, and DeepSeek.
Node.jsMIT★ 16No key
🧠 Knowledge Graph Memory for AI Coding Agents & Openclaw - Full offline mode with Docker. Integrates with Claude, Cline, Cursor, Windsurf, and more. Auto-extracts entities & relationships. No API key
Node.jsAGPL-3.0★ 4Few starsNo key
Intelligent MCP Research Router - Tool selection, search strategy planning, and parallel execution
Node.jsMIT★ 4Few starsNo key
A high-performance, token-efficient Model Context Protocol (MCP) gateway proxy. Avoids context bloat and eliminates multi-turn tool discovery latency by intercepting prompts and semantically injecting
Node.jsMIT★ 66No key
Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to th
Node.jsMIT★ 62No key
MCP server for LLMTest — benchmark AI models on real prompts, find cheaper alternatives across 340+ models. Works with Claude Code, Cursor, Windsurf.
Node.jsMITFew starsNeeds a key
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external
SkillMIT★ 67No key
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE,
SkillApache-2.0★ 48kNo key
MCP server for natural language queries against SAP CAP db-layer entities. Schema auto-discovered from cds.model.
Node.jsMITFew starsNo key
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Node.jsMIT★ 282kNo key
A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.
Node.jsMIT★ 136No key
Persistent memory for AI agents. Claude Code and Codex share one memory per project. Store, retrieve, summarize, and prune on SQLite, Postgres, Redis, MongoDB, vector databases, and more.
Node.jsMITFew starsNo key
A MCP server that gives LLMs direct access to the AT Protocol ecosystem, enabling seamless interaction with Bluesky and other AT Protocol-based social networks.
Node.jsMIT★ 10No key
MCP security scanner (CLI + MCP server): detects tool poisoning, prompt injection, and rug-pulls in MCP manifests. Also an OWASP LLM Top 10 prompt-injection/jailbreak CLI for LLM apps.
Node.jsMIT★ 1Few starsNo key
Who stands behind it