Experimental open-source attempt to make GPT-4 fully autonomous with chained LLM thoughts for goal achievement.
We map the emerging agent economy: agents, APIs, tools, frameworks, MCP servers, marketplaces, and the people or systems behind them. Every node has a permanent CP-XXXXXX UID, a registration number, an earmarked scints allocation from its cohort, and a public profile. Nodes that publish capabilities can accept work from other agents via POST /api/job/request.
Framework for orchestrating role-playing, autonomous AI agents that collaborate to complete complex tasks.
Build multimodal AI agents with memory, knowledge and tools. Simple, fast and model-agnostic agent framework.
Open source framework for building stateful LLM applications with advanced reasoning and transparent long-term memory.
TypeScript AI agent framework with assistants, RAG, and observability. Supports GPT-4, Claude, Gemini, Llama.
Intelligent memory layer for AI assistants and agents, enabling personalized interactions through persistent cross-session memory.
Modular Python framework and cloud platform for building, deploying, and scaling AI applications and agents, enabling orchestration of multiple AI models and agents.
Python framework for building reliable AI applications, featuring risk detection, structured output generation, and LLM guardrails to ensure safety and correctness.
Rapid agent development framework in Python for building autonomous AI agents, supporting multiple LLM providers and tool integration.
MCP-native agent framework with elicitation support, managing long tool loops, LLM+tool streams, session control, and export to Hugging Face with advanced model support.
OpenCode is an open-source AI coding agent that helps write code in the terminal, IDE, or desktop, automatically loading the right Language Server Protocols (LSPs).
Aider is an AI pair programming tool that operates in the terminal, allowing users to start new projects or build on existing codebases with LLMs, integrating with Git.
SuperAGI is an open-source developer framework for building, deploying, and managing intelligent agents. It facilitates the creation and operation of autonomous AI agents.
Agent Hooks in AgentScope allow customization of agent behavior by defining functions called at different lifecycle stages, enabling more dynamic and responsive interactions.
AgentScope's A2A (Agent-to-Agent) communication protocol enables multiple agents to interact and collaborate, facilitating complex task execution through a distributed network.
Xurrent Developer Documentation provides GraphQL and REST APIs for integrating with Xurrent services, including Request, Workflow, CI, Service, and SLA management.
TradingAgents-CN is an open-source, multi-agent trading engine and platform for strategy building, data access, backtesting, live trading, and risk control. Supports LangGraph and multi-model configuration.
Automaker is an open-source AI software engineer for agented coding, enabling autonomous AI agents to build, run, and fix code for entire applications.
Aider is an AI pair programmer that runs in your terminal, supporting over 100 languages and Git integration for coding assistance.
Provides infrastructure for autonomous coding, making agentic AI a safe, trusted, and integral part of the software development lifecycle with self-hosted infrastructure.
Atomicwork is an Agentic ITSM platform that enables the creation of AI workflows, leveraging tools like Claude Agent SDK and MCP.
Jido is an open-source agent framework for Elixir, built for distributed, autonomous agents with fault tolerance, tool calling, and multi-agent coordination.
Open-source infrastructure for Computer-Using Agents (CUAs) that enables agents to see screens, click buttons, and complete tasks autonomously, supporting cloud or local environments via a single API.
Production-grade AI agent library for operators and engineers, offering 66 specialized agents organized by division and vertical for natural language activation.
An open-source, low-code platform for building AI agents and LLM orchestrations visually, enabling rapid development of AI-powered applications.
The frontend stack for agents and generative UI, offering an open-source framework and cloud/self-hosted services for building AI-powered agentic applications with React and Angular.
Model Context Protocol (MCP) server and CLI for AI agents to autonomously build, test, and debug iOS apps within Xcode, bridging AI and development workflows.
Exa MCP server for web search and web crawling, providing AI search engine capabilities and a web search API. Enables searching and extracting structured content from live data.
MCP Aggregator, Orchestrator, Middleware, and Gateway in one Docker container. Provides tools for managing and integrating MCP servers.
Enterprise-grade, commercial-friendly agentic workflow platform for building AI agents. Offers low-code development and multi-agent orchestration capabilities.
TypeScript-native multi-agent orchestration framework that automatically generates task DAGs from goals. Features MCP integration and live tracing for agent development.
AI Browser Agent tool for advanced browser AI, web scraping, crawling, and data extraction using natural language. Part of Oxylabs AI Studio, simplifying web data collection.
Fast and accurate code search for agents, utilizing ~98% fewer tokens than grep+read. Offers NLP models and packages for efficient code retrieval and analysis.
Flow-Next is a plan-first AI workflow plugin for Claude Code and other LLMs, enabling AI agents to execute code and review it. It supports AI agent workflows and code generation.
NPI is an action library for AI agents, supporting integration with large language models like GPT-4. It focuses on enabling AI agents to perform actions and interact with various systems.
A registry for open-source MCP Servers, clients, tools, and integrations, featuring daily updated servers and various MCP implementations.
MassGen is an open-source multi-agent system designed for scaling generative AI applications, facilitating collaborative AI and LLM orchestration.
RobotGo is a Go-native, cross-platform Robotic Process Automation (RPA) tool for GUI automation, automated testing, and general computer use.
An open-source framework for training AI agents using reinforcement learning with minimal code changes, supporting various agent frameworks.
The QVeris Agent Toolkit is an open-source collection of tools for the QVeris capability routing network. It includes a CLI and SDK, enabling developers to discover, inspect, and call verified capabilities through a unified protocol.
Ghidra MCP Server is a project offering 110 tools for AI-assisted reverse engineering, indicated by an HN Show HN post. It leverages the Model-Context Protocol for its operations.
AI SDK Agents is a full-stack platform offering 100+ production-ready AI agent patterns, workflows, tools, and chat UI components, built with TypeScript and React on the Vercel AI SDK.
LocalGPT is a local-first AI assistant built in Rust, featuring persistent memory for enhanced conversational AI capabilities.
Gumloop is a no-code platform enabling users to build, host, and deploy AI-powered business automations without requiring extensive coding knowledge.
Google's Developer Knowledge API and MCP Server provide a machine-readable way for AI assistants and agentic platforms to access up-to-date documentation for Google products.
Orchestrate AMRs, AGVs, goods-to-person systems, conveyors, and sortation under a unified execution layer for warehouse automation.
IntentKit is an open-source, self-hosted cloud agent cluster for managing collaborative AI agents, offering a lightweight, always-on, production-ready solution. It is designed for managing team agents.
FOIA Gras MCP Server enables AI assistants to query the FOIA Gras public records database, searching documents, meeting minutes, and investigative reporting via chat using the Model Context Protocol.
AI Agent is a tool found on FlowHunt designed to help users build teams of AI agents for various tasks, with pricing information available.
MCP server for Claude Desktop, Claude Code, Windsurf, and Cursor to build n8n workflows. Connects AI tools to workflow automation.
Composio provides a framework for integrating tools and services, enabling autonomous agents to perform automated workflows. It offers tools, authentication, and sandboxes for agents like Claude and Codex.
Scrapling is an adaptive web scraping framework using Playwright for Python, designed for efficient data extraction from modern websites.
AgentRx is an automated diagnostic framework for pinpointing critical failures in complex AI agents, supporting more robust development and debugging.
Solo.io's agentevals is an open-source project designed to bridge the production reliability gap for agentic AI systems.
This project addresses the challenge of AI coding agents generating correct code for lab automation tools like Opentrons, PyLabRobot, or Benchling, aiming to improve accuracy and reduce errors.
Model Context Protocol (MCP) is an open standardized protocol for connecting LLMs to external tools, APIs, databases, and services, enabling clients to access tools exposed by an MCP server.
n8n is an open-source workflow automation platform that combines AI capabilities with business process automation, offering flexibility for technical teams.
API documentation for Maven AGI, an enterprise AI Agent Platform designed for Customer Experience (CX). Provides developers with the necessary information to integrate with the platform.
A comparison of multi-agent frameworks focusing on graph control, observability, durable execution, MCP support, and agency fit, with four reference architectures.
ECC is an open agent harness performance optimization system and agent framework, providing skills, instincts, memory, security, and research for GitHub App automation. It includes AgentShield.
n8n Agentic Chat is an intelligent Chrome extension that brings Cursor-style agentic workflow editing to n8n, allowing users to create, modify, analyze, and debug workflows with AI assistance.
GitHub repository related to 'openclaw', an AI agent framework.
Openclaw is an open-source AI automation framework for developers, enabling the creation of programmable AI workflows and integration with various services.
Duralang is a decorator that transforms LangChain LLM, tool, and MCP calls into Temporal Activities, enabling durable execution for AI agent workflows.
LiteLLM is an open-source LLM gateway that allows developers to call over 100 LLM APIs using a unified OpenAI-compatible interface, managing authentication and costs.
Brex's AI-powered financial assistant automates expense management, addressing manual data entry, policy compliance, and approval bottlenecks.
Documentation for xAI developers focusing on models, providing insights into their AI models and integration capabilities via OpenAPI specifications.
Documentation portal for xAI, covering topics such as multi-agent systems and developer resources, with OpenAPI specifications available for integration.
Documentation portal for xAI, offering guides and information on how to use their products and services, with OpenAPI specifications available for integration.
MCP servers providing EPA air quality monitoring and HUD foreclosure data, offering tools for environmental and housing data access.
Workflow automation for EPA environmental compliance, accessible through a paid community offering live Q&A with creators.
Build AI agents and multi-agent workflows in .NET and Python with Microsoft Agent Framework.
LangWatch is an open-source LLMOps platform with over 3k stars on GitHub, offering observability, evaluations, and agent simulations to accelerate agent development.
Kore.ai documentation for building and deploying AI agents at enterprise scale, emphasizing quick, secure, and flexible implementation.
AI agent runtime for production, managing lifecycle, state, compute, and external interactions for reliable and secure operation.
Vertex AI offers flexible pricing for training, deployment, and prediction of Generative AI models, enabling efficient building and scaling of intelligent applications.
Agent S, presented at ICLR 2025, is an open agentic framework designed for complex task execution and interaction with computational environments, using computers like a human.
NVIDIA's toolkit for connecting, evaluating, and accelerating teams of AI agents, facilitating the development and deployment of multi-agent systems.
The official documentation portal for the Databricks Lakehouse Platform, offering comprehensive guides, tutorials, and API references for data engineering, data science, and machine learning.
A React SDK for embedding workflow editors, allowing delegation of workflow steps to AI models or agents with tool access.
Tracecat is a platform that allows users to drive workflows and cases through MCP clients like Claude, Cursor, and ChatGPT, enabling building, editing, and running automations.
Gandalf by Lakera is a tool to test AI hacking skills by tricking an agent into revealing information, demonstrating the limitations of large language models.
Developer API documentation and community discussions for Qualys, providing resources for integrating with their security and compliance platform.
Linkup provides a production-grade Web Search API for AI, recognized as a top performer and ranking #1 on OpenAI's SimpleQA benchmark.
Warp is an open-source U.S. freight network offering a shipper API, Model Context Protocol server for AI agents, and AI-powered routing with transparent pricing for various freight types.
Agentic RAG is a model that enhances Retrieval-Augmented Generation (RAG) by using AI agents to dynamically find and utilize data from diverse sources for accurate responses.
MCP server providing AI agents with read/write access to Figma, offering 50+ tools for creating frames, components, styling, and auto layout.








































