OpenAI Swarm
An experimental Python framework for learning multi-agent orchestration with tools, handoffs, and context variables.
Open-source and self-hosted AI tools you can run on your own machine or servers
379tools listed
Pricing mix
An experimental Python framework for learning multi-agent orchestration with tools, handoffs, and context variables.
ComfyUI nodes and workflows for steering video motion with batches of images.
Convert screenshots, Figma designs, mockups, and screen recordings into frontend code with AI.
Open-source transformer training examples and GPU-optimized building blocks for distributed model training.
Open-source text-to-text transformer library for training, fine-tuning, and evaluating NLP models.
Open-source ORM that uses OpenAI to turn plain-language requests into SQL and execute database queries.
Open-source multi-agent orchestration with visual workflows, a Python SDK, and local deployment.
MotionAgent generates scripts, movie stills, videos from images, and custom-style background music.
Generate lip-sync videos in Automatic1111 with speech audio, face restoration, and optional face swapping.
Open-source prompt generation, testing and ELO ranking in Google Colab or local Jupyter notebooks.
Open-source AI research agent for cited reports from web sources, local documents, and MCP-connected data.
Open-source browser for running MCP agents in parallel with existing Chrome logins and local session replay.
An open-source AI assistant that generates code and markdown cells in Jupyter notebooks.
Open-source CLI for generating code from natural-language instructions and improving existing projects.
Open-source deepfake software for face replacement, face de-aging and head replacement.
Open-source code and models for generating 3D objects from text prompts or images.
Open-source Python REST API for classifying text with custom JSON models and OpenAI.
Open-source text-to-audio model for multilingual speech, music, sound effects and nonverbal sounds.
AI chat and search summaries inside DuckDuckGo through a browser userscript.
AI chat and search summaries inside Brave Search through a browser userscript.
An open-source framework for managing Python functions and experimenting with self-building autonomous agents.
Open-source software for animating drawn human figures with motion data and exporting videos or transparent GIFs.
Open-source point cloud generation from images and text, with a model for converting point clouds to meshes.
Speech-to-text, text-to-speech, translation, and OSC text displays for VRChat and use outside VRChat.
Open-source Python agent that connects language models to CLI commands for programming and environment setup.
Open-source benchmark for evaluating language models with JSON and programmatic tasks
Swift APIs for durable AI agents on Apple platforms, with persistent conversations and crash recovery.
An open-source operating system that uses Hermes Agent to manage apps, files and routines through voice or text.
Local codebase intelligence, code health analysis, generated documentation and MCP tools for coding agents.
Open-source full-text search and persistent memory for agents working with large datasets.
Open-source video subject replacement with local review, Seedance generation, and original audio restoration.
Open-source browser AI agent for tab automation, sandboxed code execution, and peer-to-peer collaboration.
Open-source CLI agent that investigates failed CI runs and pushes fixes for review.
Local-first permission policies, one-time approvals, and redacted audit logs for MCP tool calls.
Replay Claude Code, Codex, and pi coding-agent sessions on a local 3D map of a repository.
An open-source React slide framework for coding agents, with browser editing, presenter tools, and deck exports.