AI Agent Open-Source Projects

Showing 40 indexable projects from the current snapshot.

• koala73/worldmonitor

  A situational awareness application that consolidates over 65 external data providers and 500 news feeds into AI-synthesized briefs and multi-layered geospatial maps. It provides a native desktop interface, API access via an MCP server, an…

• usestrix/strix

  Strix provides autonomous AI penetration testing agents that dynamically execute code and validate vulnerabilities with working proofs-of-concept. Teams must have Docker running and provide an LLM API key from a supported provider to opera…

• ollama/ollama

  Ollama simplifies downloading and running open large language models locally on macOS, Windows, or Linux without requiring paid services. Users can interact with models via a CLI, a REST API, or client libraries.

• stablyai/orca

  Orca is a desktop and mobile development environment that orchestrates CLI coding agents across parallel isolated git worktrees. Developers can run multiple agents concurrently, compare their diffs, and monitor progress remotely.

• openai/codex-plugin-cc

  A Claude Code plugin that delegates read-only code reviews, adversarial design challenges, and background tasks to Codex without leaving the current workflow. It is intended for developers who use both Claude Code and Codex and want to red…

• HKUDS/Vibe-Trading

  An open-source research workspace that translates natural-language prompts into market-data loading, strategy drafting, backtesting, and report generation. It targets developers and data teams building research and analysis workflows acros…

• alibaba/page-agent

  An in-page JavaScript GUI agent that enables natural language control of web interfaces via a single script, operating directly on the DOM without requiring browser extensions, Python, or headless browsers.

• langgenius/dify

  Dify is an open-source platform for teams building, testing, and deploying agentic AI workflows and LLM applications through a visual interface, RAG features, agent tools, model management, and observability. It can be self-hosted or used…

• langchain-ai/langchain

  LangChain is a Python framework that simplifies building LLM applications by connecting models, embeddings, and vector stores through interoperable components. Developers can chain these integrations together using flexible abstractions ra…

• bradautomates/claude-video

  This project adds video comprehension to AI coding assistants and chat agents by downloading content, extracting frames, and transcribing audio. It operates as a portable skill unit across over 50 agent hosts without modification, giving m…

• infiniflow/ragflow

  RAGFlow provides a retrieval-augmented generation workflow focused on deep document understanding, processing complex unstructured formats to extract knowledge with traceable citations. It requires external LLM and embedding services to op…

• openclaw/openclaw

  A local-first, single-user AI assistant that connects to messaging platforms like WhatsApp, Telegram, Slack, and Discord from your own devices. It is suited for individuals seeking a unified inbox with voice and visual canvas support, but…

• obra/superpowers

  A skills framework and software development methodology that applies test-driven development and subagent-driven workflows for AI coding agents. It activates before code is written to refine designs, dispatches fresh subagents per task, an…

• affaan-m/ECC

  A system of over 260 reusable skills, rules, and hooks designed to standardize AI-assisted software development across multiple agent harnesses. It provides cross-harness automations, a security scanner for agent configurations, and an exp…

• NousResearch/hermes-agent

  A self-improving AI agent application that creates and refines skills from experience while maintaining context across sessions. It runs from a $5 VPS to a GPU cluster and connects to multiple messaging platforms.

• n8n-io/n8n

  n8n is a source-available platform for building and deploying AI agents and workflow automation using a visual canvas combined with custom code. It offers 1500+ integrations and can be self-hosted or deployed via a managed service.

• anomalyco/opencode

  anomalyco/opencode is an open source AI coding agent providing both a full-access Build Agent for development work and a read-only Plan Agent for codebase analysis. It runs as a binary, desktop application, or Node package on macOS, Window…

• Significant-Gravitas/AutoGPT

  A platform for building, deploying, and managing continuous AI agents via a low-code interface. Self-hosting requires Docker and multiple dependencies, and the managed cloud version is in Closed Beta.

• anthropics/skills

  A collection of reusable Agent Skills, templates, and specifications for completing specialized tasks with Claude. Requires a compatible Claude platform to execute skills and is intended for demonstration and educational use.

• firecrawl/firecrawl

  Firecrawl is a hosted web scraping, crawling, and search API built for AI applications. It converts web pages into Markdown, structured JSON, screenshots, and HTML while handling rotating proxies and rate limits.

• langflow-ai/langflow

  Langflow is a visual authoring environment for designing, testing, and deploying AI agents and workflows. It supports turning visual flows into APIs, JSON exports, and MCP servers, with component-level customization available through Pytho…

• anthropics/claude-code

  Claude Code is a terminal-native agentic coding tool that uses natural language commands to execute routine tasks, explain code, and manage git workflows. It is designed for developers seeking to accelerate coding through an AI agent that…

• msitarzewski/agency-agents

  A collection of specialized, personality-driven AI agents organized into divisions such as engineering, design, and security, packaged with scripts for installation into multiple agentic coding tools.

• Shubhamsaboo/awesome-llm-apps

  A repository of over 100 open-source AI agent and RAG application templates, organized across multiple domains such as voice, generative UI, and coding tools. It serves as a reference for developers and general users seeking tested startin…

• farion1231/cc-switch

  A cross-platform desktop GUI that centralizes provider configuration, MCP server setup, and skills management across seven AI coding tools. It is built for developers who regularly switch between multiple AI tools and need a visual interfa…

• continuedev/continue

  An open-source AI coding agent available as a CLI tool, a VS Code extension, and a JetBrains plugin. The repository is currently read-only with no active maintenance, and the JetBrains plugin is deprecated.

• run-llama/llama_index

  A data framework for augmenting LLMs with private data and building agentic applications, offering data connectors, indexing, and retrieval/query interfaces. It is designed for development teams that need to ingest existing documents, APIs…

• unclecode/crawl4ai

  Crawl4ai converts web pages into clean, LLM-ready Markdown and structured JSON for retrieval pipelines and AI agents. It provides controllable browser-based crawling and data extraction without mandatory API keys, operating as a self-hoste…

• modelcontextprotocol/servers

  A collection of official reference implementations for the Model Context Protocol, managed by the MCP steering group. Developers can use these servers to learn MCP features, evaluate official SDKs, and build their own custom servers.

• browser-use/browser-use

  browser-use/browser-use is a Python library and CLI that lets an AI agent operate a web browser to perform tasks described in natural language. Developers can use it for code-level browser automation and structured data extraction without…

• google-gemini/gemini-cli

  google-gemini/gemini-cli is a terminal-first AI agent that brings Gemini models into the command line for code understanding, generation, and workflow automation. It provides file operations, shell commands, web fetching, and extensibility…

• Mintplex-Labs/anything-llm

  This application lets users chat with their documents and run AI agents in a private, locally hosted environment by default. It supports multi-user permissioning, dynamic model routing, and custom agent construction without requiring codin…

• openai/codex

  OpenAI Codex is a terminal-based coding agent that runs locally on the user's computer and integrates with ChatGPT or the OpenAI API. It requires an OpenAI account or API key to function.

• crewAIInc/crewAI

  CrewAI is a Python framework for orchestrating role-playing, autonomous AI agents in production workflows. It provides high-level abstractions and low-level APIs to combine autonomous agent teams with event-driven control flows.

• TauricResearch/TradingAgents

  A multi-agent LLM framework that mirrors a real-world trading firm by deploying specialized agents to collaboratively evaluate market conditions and inform trading decisions. It deploys specialized agents for fundamentals, sentiment, news,…

• FlowiseAI/Flowise

  Flowise provides a visual, drag-and-drop canvas for assembling and deploying AI agents and multi-agent workflows without writing code. It runs locally on Node.js or on multiple cloud hosting platforms and is intended for users who need to…

• karpathy/autoresearch

  This project provides an autonomous research loop where an AI agent modifies training code, runs short experiments, evaluates results, and iterates automatically to improve a small LLM. It requires a single NVIDIA GPU and uses a fixed 5-mi…

• DietrichGebert/ponytail

  Ponytail is a Node-based, locally runnable skill for AI coding assistants that applies a reuse-first decision ladder before new code is written. On skill-capable hosts, it also supports diff review and repository audits that produce a dele…

• thedotmack/claude-mem

  claude-mem preserves context for Claude Code across sessions by automatically capturing tool usage, generating semantic summaries, and injecting relevant context into future sessions. It addresses the loss of knowledge continuity when AI a…

• microsoft/autogen

  AutoGen is a multi-agent AI orchestration framework currently in maintenance mode. It provides layered APIs for prototyping autonomous agent workflows, but new production projects should use Microsoft Agent Framework instead.