Easily deploy Haystack pipelines and agents as REST APIs and MCP Tools. Officially maintained by deepset, featuring OpenAI-compatible endpoints, Chainlit UI integration, streaming responses, and file upload support.

SDKAI AgentsRAG

VIEW DETAILS →

Human-like memory layer for AI agents featuring semantic, episodic, and procedural memory with failure-driven workflow evolution. Offers Python/JS SDKs, REST API, and LangChain/CrewAI integrations.

Docs, Tutorials & ResourcesRAGModel Context Protocol

VIEW DETAILS →

A Python-based MCP protocol implementation framework providing client-server architecture for LLM tool orchestration, integrated with LangChain and ChromaDB for RAG development.

Model & Inference FrameworkRAGAI Agents

VIEW DETAILS →

Project NOVA is a multi-agent AI architecture based on n8n and MCP protocol, connecting 25+ specialized agents for intelligent routing and automation across knowledge management, DAW music production, smart home, and development tools. Includes complete Docker containers, n8n workflows, and system prompts for out-of-the-box deployment.

AI AgentsModel Context ProtocolMulti-Agent System

VIEW DETAILS →

Java AI application development framework supporting LLM-tool/skill, RAG, MCP, Agent-ReAct, Team-Agent, compatible with Java 8-25, embeddable in SpringBoot, jFinal, Vert.x, Quarkus.

Model & Inference FrameworkSDKMulti-Agent System

VIEW DETAILS →

An open-source Go-based application engine integrating autonomous agent framework, GraphRAG knowledge retrieval, and full-stack runtime in a single binary for building web apps, REST APIs, and edge intelligence services.

Model Context ProtocolRAGAI Agents

VIEW DETAILS →

An elegant Java-based LLM application framework similar to LangChain, offering LLM access, chat interceptors, prompt management, tool calling, memory systems, embedding, vector storage, and observability capabilities.

Agent & ToolingJavaSpring Boot

VIEW DETAILS →

MiniAGI is a simple general-purpose AI agent compatible with GPT-3.5-Turbo and GPT-4. It combines a robust prompt with a minimal set of tools, chain-of-thoughts, and short-term memory with summarization. It is also capable of inner monologue and self-criticism.

Agent & ToolingPythonAI Agents

VIEW DETAILS →

A powerful coding agent toolkit providing semantic retrieval and editing capabilities through an MCP server and other integrations, transforming LLMs into fully-featured agents that work directly on your codebase.

Agent & ToolingPythonAI Agents

VIEW DETAILS →

A universal AI agent application using Amazon Bedrock, capable of customizing to create/edit files, execute commands, search the web, use knowledge base, employ multi-agents, generate images, and more.

Agent & ToolingTypeScriptNode.js

VIEW DETAILS →