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.
1–24 of 3,005 tools for “llm-framework”
Clear allCan an AI coding agent build the same framework-neutral spec on different stacks? External-oracle-graded benchmark. First: Spring Boot vs Tiko DI.
SkillMITFew starsNo key
ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
SkillApache-2.0★ 4.9kNo key
Multi-Agent LLM Framework for Commodity Futures Research with Social Media Sentiment Fusion
PythonApache-2.0★ 1Few starsNo key
Rust multi-agent LLM framework — OpenClaw alternative. WhatsApp + Telegram + Gmail + browser agents on a single binary. NATS broker, MCP client+server, Claude/Anthropic OAuth, MiniMax, durable TaskFlo
SkillApache-2.0★ 8No key
Framework para construir software con agentes de IA sin repetir los mismos errores: skills, patrones, plantillas y scripts (PowerShell + Bash). Compatible con Claude, Gemini, Cursor, Copilot, Windsurf
SkillMITFew starsNo key
Agent Communication Protocol (ACP): zero-server, P2P agent-to-agent communication for AI agents.
SkillApache-2.0★ 7No key
Claude Code skill for optimizing content for LLM answer engines and AI agents
SkillMITFew starsNo key
Agentinc SDK — The open-source Python SDK for the Agentinc agent marketplace. Build agents with any LLM framework (OpenAI, Anthropic, LangChain, CrewAI), wrap them in a universal protocol, and serve t
SkillApache-2.0★ 4Few starsNo key
Agent skills for integrating and instrumenting Opik: LLM observability for Claude Code and other coding agents.
SkillApache-2.0★ 8No key
An event-driven, multi-agent workflow framework built on FastMCP for structured and robust tool orchestration.
PythonApache-2.0★ 5No key
Design pattern + Claude Code skill for AI engineers. LLM judgment and deterministic code in mutually-generative cycles, not pipelines. Library of named graph-shapes (RAG, ReAct, codegen-with-verificat
SkillMIT★ 5No key
SkillApache-2.0★ 7No key
Production-ready LLM toolkit with unified interface for multiple providers (OpenAI, Anthropic, Google, Ollama)
PythonMIT★ 2Few starsNo key
Multi-agent AI framework for gene regulatory network analysis via Model Context Protocol
PythonMIT★ 1Few starsNo key
FullSense — umbrella brand & spec for llmesh / llive / llove (Apache-2.0)
SkillApache-2.0★ 1Few starsNo key
A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)
PythonMIT★ 2Few starsNo key
SkillMIT★ 4Few starsNo key
🚀 Unified, type-safe Tool Calling & Model Context Protocol (MCP) framework for OpenAI, Claude Sonnet 5, and Gemini 3.7 Flash with real-world agent optimizers.
PythonMITFew starsNo key
ReAct Agent Project — an LLM framework that alternates reasoning with tool use: think, act, observe, adapt. Better reliability for multi-step tasks compared to one-shot generation.
SkillMIT★ 2Few starsNo key
Local-first AI agent framework with approval gates, audit trails, and resumable multi-surface workflows.
PythonMIT★ 3Few starsNo key
Who stands behind it