# Open Source

Unified Python/.NET framework for multi-agent AI

Microsoft Agent Framework is Microsoft's official unified SDK for building multi-agent AI workflows in Python and .NET. It consolidates Semantic Kernel and AutoGen into a single framework with MCP tool integration, graph-based workflows, human-in-the-loop patterns, and multi-agent orchestration. The framework reached Release Candidate status in February 2026 and is Microsoft's recommended path for production agent development.

High-performance S3-compatible object storage

MinIO is a high-performance, S3-compatible object storage server designed for AI, machine learning, and data-intensive workloads. Written in Go, it delivers industry-leading throughput for both read and write operations while maintaining full compatibility with the Amazon S3 API. MinIO includes an embedded web console for bucket management, a command-line client, and supports erasure coding, bitrot protection, and encryption at rest for enterprise-grade data durability.

MCP server for MiniMax speech, video, and image APIs

Official MiniMax Model Context Protocol server enabling AI applications and code editors to access text-to-speech, voice cloning, image generation, video generation, and music creation APIs. Designed for Claude Desktop, Cursor, and Windsurf integration with stdio and SSE transport support, regional API endpoints for global and China regions, and flexible resource handling for seamless generative AI workflows.

Free MIT-licensed drop-in replacement for LocalStack

MiniStack is a free, MIT-licensed drop-in replacement for LocalStack that emulates 33 AWS services using real infrastructure — actual Postgres for RDS, real Redis for ElastiCache, real Docker for ECS — rather than faking API responses. Born from LocalStack's surprise paywall in March 2026, it starts in 2 seconds, idles at 30MB RAM versus LocalStack's ~500MB, and runs real services for accurate local AWS development.

Multi-provider AI code completion as-you-type for Neovim

Neovim plugin that streams inline code completions from your choice of LLM (OpenAI, Claude, Gemini, Codestral, Ollama, Llama.cpp, and more), with no proprietary background binary.

Terminal-native coding agent by Mistral AI

Mistral Vibe is a native CLI coding agent from Mistral AI, powered by their Devstral coding model, that runs directly in the terminal with deep project awareness including automatic file structure scanning and Git status integration. Released December 2025 alongside Devstral 2, it features smart @-file references, shell command execution, and conversational workflows. Mistral's entry into the agentic CLI coding market alongside Claude Code and OpenCode.

Write components once and compile them into native code for multiple frameworks

Mitosis is Builder.io-backed open-source infrastructure for writing a component once and compiling it into native framework components for React, Vue, Angular, Svelte, Qwik, Solid, React Native, and other targets. It supports cross-framework design systems and Figma-to-code synchronization, but is distinct from the Builder.io visual builder product.

Project documentation with Markdown

Python-based static site generator purpose-built for project documentation. Simple YAML configuration, fast build times, and a rich plugin ecosystem. The Material for MkDocs theme adds a polished look with search, dark mode, and advanced navigation features. The go-to documentation tool for open-source projects and internal engineering docs that need to look professional with minimal effort.

MCP server for mobile device automation and testing

Mobile MCP is an open-source MCP server that enables AI agents to automate Android and iOS devices — navigating apps, tapping elements, extracting screen content, and running tests on simulators, emulators, and physical devices. It brings agentic mobile engineering to any MCP-compatible AI assistant.

Flexible JavaScript test framework

Feature-rich JavaScript test framework for Node.js with BDD/TDD interfaces, flexible assertion library choice, and extensive plugin support. The veteran test runner trusted by thousands of projects, offering async test support, configurable reporters, and a mature ecosystem that makes it reliable for both unit and integration testing in Node.js applications.

Disaggregated KV cache storage and transfer for LLM serving

Open-source infrastructure for disaggregated LLM serving that pools KV caches across prefill and decode workers, with high-performance transfer, distributed storage and integrations for vLLM and SGLang.

YC-backed multimodal RAG platform for documents, images, and video

Morphik is a YC-backed multimodal RAG platform that ingests and retrieves information from documents, images, tables, and video content. It processes complex document layouts including charts, diagrams, and multi-column formats that traditional text-only RAG systems handle poorly. Provides API-first integration for building knowledge bases that understand visual as well as textual information.

Production-ready React animation library, evolved from Framer Motion

Motion (formerly Framer Motion) is the most popular React animation library, providing a declarative API for complex animations, gestures, layout transitions, and scroll-triggered effects. Supports spring physics, keyframes, shared layout animations, and exit animations. Powers animations across thousands of production React applications with an API designed for developer ergonomics.

Open-source platform for managing AI coding agents as teammates

Multica is an open-source managed agents platform that lets you assign coding tasks to AI agents like Claude Code and Codex as if they were team members. It provides a unified dashboard for task assignment, execution monitoring, and skill reuse across local and cloud compute environments. With multi-workspace support, team-level isolation, and reusable skill compounding, Multica turns autonomous coding agents into organized, trackable development resources.

High-performance mobile neural network inference

NCNN is Tencent's high-performance neural network inference framework optimized for mobile and embedded platforms. It features pure C++ with zero dependencies, ARM NEON assembly optimization, Vulkan GPU acceleration, and sophisticated memory management for minimal footprint. Supports importing models from PyTorch, ONNX, Caffe, TensorFlow, and Keras with 8-bit quantization and half-precision storage for efficient on-device deployment across Android, iOS, and Linux.

Distributed inference orchestration above vLLM, SGLang and TensorRT-LLM

Open-source, datacenter-scale orchestration layer that coordinates vLLM, SGLang and TensorRT-LLM across nodes with disaggregated serving, KV-aware routing, multi-tier cache management and automatic scaling.

Secure sandboxed runtime for AI agent execution

NVIDIA OpenShell provides kernel-level isolation for AI agent workloads with Landlock, seccomp, and network namespace sandboxing. Announced at GTC 2026 with 17 enterprise partners including Adobe, Atlassian, SAP, and Salesforce, it offers declarative YAML policy enforcement, L7 HTTP inspection, and GPU passthrough — purpose-built to contain the blast radius when autonomous coding agents interact with filesystems and networks.

Framework for converting MCP servers into autonomous AI agents with UI

Nanobot transforms MCP servers into full autonomous agents by adding a planning layer, conversation memory, and web-based UI on top of MCP tool capabilities. It enables building agents that combine multiple MCP servers with LLM reasoning to complete multi-step tasks. Features MCP-UI for browser-based interaction and supports any MCP-compatible tools as agent capabilities.

Community-built, local-first terminal coding agent — bring your own model

An open-source terminal coding agent from the non-profit Nano Collective. Runs agentic coding on the model of your choice — local via Ollama or any OpenAI-compatible API — with no paid tiers and nothing gated behind a vendor.

Hyperextensible Vim-based text editor

Modern fork of Vim with Lua-based plugin architecture and built-in LSP support. Lightweight yet endlessly extensible, it serves as the foundation for AI-enhanced development workflows through plugins like Avante, Codecompanion, and Copilot.lua. With 85k+ GitHub stars, it's the terminal editor of choice for developers who value speed, customization, and keyboard-driven efficiency.

Open-source zero-trust networking with WireGuard

NetBird is an open-source zero-trust networking platform that creates encrypted WireGuard overlay networks between devices without opening ports or configuring firewalls. It provides peer-to-peer connectivity with NAT traversal, access control policies, DNS management, and a web dashboard for team management. NetBird replaces traditional VPNs with a simpler, more secure mesh networking approach for self-hosted infrastructure and remote teams.

Observability data accessible to AI agents via MCP

Netdata's MCP integration exposes infrastructure monitoring, discovery, and root-cause analysis capabilities to AI agents. Built into the 78K+ star Netdata monitoring platform, it lets agents query real-time metrics, explore system health, investigate incidents, and generate observability reports through the Model Context Protocol.

Unified LLM API gateway and proxy hub

New API is an open-source multi-tenant AI gateway that aggregates and distributes LLM API requests across providers like OpenAI, Claude, and Gemini through a unified proxy interface. It cross-converts requests into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats, with built-in channel management, quota control, token-based authentication, and billing capabilities. Deploy via Docker with SQLite or MySQL for centralized model management.

Cross-platform on-device AI model runtime

Nexa SDK enables running frontier LLMs and multimodal models locally across PC, mobile, IoT, and wearables with automatic hardware acceleration for GPU, NPU, and CPU. It supports Qwen, Gemma, Llama, DeepSeek models with Python/C++ desktop SDKs, Android/iOS mobile SDKs, and Docker for edge deployment. Includes an OpenAI-compatible API server with chat and function calling support.

Next.js documentation framework

Nextra is a Next.js-based static site generator designed for documentation websites and blogs with minimal configuration. Leverages the full Next.js ecosystem with pre-built themes (Docs and Blog), MDX support, automatic file-system routing, full-text search, dark mode, and i18n. Developers get fast, SEO-friendly docs sites while keeping access to Next.js features like React Server Components.

Low-code visual programming for event-driven apps

Node-RED is a flow-based, low-code development tool originally created by IBM in 2013 for wiring together hardware devices, APIs, and online services. Now an OpenJS Foundation project with nearly 23,000 GitHub stars, it provides a browser-based visual editor where flows are built by dragging and connecting nodes, then deployed to the Node.js runtime in a single click. Over 5,000 community-contributed nodes cover protocols like MQTT, Modbus, and OPC-UA alongside cloud APIs and databases.

Official Notion MCP server for AI-agent workspace access

Notion MCP Server is Notion's official MIT-licensed MCP server for connecting AI assistants to Notion workspaces. It supports the vendor-backed remote OAuth path and tools designed for page, workspace, and Markdown-style operations, making it a safer default than unofficial Notion bridges for teams already using Notion for docs, projects, or internal knowledge bases.

Browser automation framework turning websites into action APIs

Notte is a browser automation framework for AI agents that converts any website into a structured action API. Instead of scraping pages for text, Notte lets agents interact with sites — clicking buttons, filling forms, and navigating flows. Built with hybrid AI-plus-deterministic scripting, it includes digital personas, CAPTCHA solving, and proxy management for reliable automation at scale.

Animated number transition component for React and frameworks

NumberFlow is a lightweight component that animates number transitions with smooth morphing effects. Numbers roll, slide, and transform between values rather than snapping instantly, adding polish to dashboards, pricing displays, counters, and financial interfaces. Available for React, Vue, Svelte, and vanilla JS with over 6,300 GitHub stars and minimal bundle impact.

A new type of shell

Nushell is a modern cross-platform shell written in Rust that treats all data as structured tables instead of plain text streams. Pipes carry typed rows through commands like ls, where, and get, so you can query JSON, CSV, SQLite, TOML, and YAML with a single uniform syntax. Powerful enough to replace bash or PowerShell for interactive use and scripting, with plugin support for custom data sources.

Smart monorepo build system and dev tools

Nx is an open-source build system with 24K+ GitHub stars optimized for monorepo development. Features intelligent task scheduling that only rebuilds what changed, distributed caching for sharing build artifacts across teams, and remote execution for parallelizing CI across machines. Supports JavaScript, TypeScript, React, Angular, Node.js, Go, Rust, and more. Provides code generators, dependency graph visualization, and project boundaries enforcement. A Turborepo alternative with broader scope.

Cross-platform high-performance ML inference engine

ONNX Runtime is Microsoft's open-source inference engine for machine learning models in ONNX format. It delivers cross-platform acceleration via execution providers for NVIDIA CUDA, TensorRT, DirectML, CoreML, OpenVINO, and more. Supports training acceleration, quantization, and GenAI workloads. Used in production across Windows, Azure, Office 365, and thousands of applications with pip-installable Python and native C++/C#/Java APIs.

Multi-agent orchestration layer for OpenAI Codex CLI

Oh My Codex (OMX) transforms OpenAI Codex CLI into a coordinated multi-agent system. It layers workflow orchestration, persistent memory, team-based parallel execution via tmux worktrees, and a live HUD dashboard on top of standard Codex. OMX provides 30+ role-specialized agents and 40+ workflow skills covering planning, execution, verification, TDD, security review, and autonomous research loops.

AI coding agent with hash-anchored edits, LSP, subagents, and browser tools

AI-powered code migration tool that automates framework upgrades, language migrations, and API version transitions. Analyzes your codebase to generate migration plans, then applies changes systematically across affected files. Reduces the risk and effort of major upgrades by handling the tedious, error-prone aspects of codebase-wide transformations that would take developers weeks to complete manually.

A prompt theme engine for any shell

A cross-platform prompt theme engine that works with any shell including PowerShell, Bash, Zsh, and Fish. Customize your terminal prompt with rich themes, dynamic segments, and real-time information from Git repos, Kubernetes clusters, cloud providers, battery status, and execution time. The most versatile prompt customization tool available, with hundreds of community themes and a visual config editor.

Framework for managing Zsh config

Community-driven framework for managing Zsh configuration with 300+ plugins, 150+ themes, and an auto-update mechanism. Provides aliases, functions, and completions for Git, Docker, Node.js, Python, Kubernetes, and most developer tools out of the box. Popular themes like Powerlevel10k and agnoster for informative prompts. Simple plugin activation via .zshrc. 176K+ GitHub stars — the most starred developer tool on GitHub. Essential for Zsh users who want productivity without manual configuration.

Microsoft's screen parsing model for GUI agent interaction

OmniParser is Microsoft's open-source screen parsing toolkit that converts GUI screenshots into structured, actionable data for AI agents. It detects interactive UI elements like buttons, input fields, and icons, then generates grounded descriptions that enable language models to interact with any desktop or web application. Accumulated over 24,000 GitHub stars as a foundational layer for computer-use agents.

OpenAI API management gateway for 100+ LLM providers

One API is a self-hosted LLM API gateway that provides a unified OpenAI-compatible interface for managing multiple model providers including OpenAI, Azure, Anthropic, Google, and dozens of Chinese providers. It handles load balancing, quota management, rate limiting, token tracking, and channel-based routing through a web dashboard. Widely adopted in the Chinese developer ecosystem with over 18,000 GitHub stars.

Fork, customize, and ship AI agents on Vercel in minutes

Open Agents is a Vercel Labs open-source template for building and deploying cloud-hosted AI agents. It provides a production-ready Next.js starter with built-in tool use, streaming responses, multi-model support, and deployment on Vercel infrastructure. Developers can fork, customize agent behavior and tools, then ship agent-backed apps in minutes with automatic scaling and edge routing.

Private, self-hosted research notebooks with flexible AI models, source chat, and podcasts

Open Notebook is an MIT-licensed, self-hosted alternative to NotebookLM for collecting sources, chatting over research, generating reusable transformations, and producing multi-speaker podcasts. Its Docker stack keeps notebook data under the user's control while supporting 18-plus model providers, including local Ollama and LM Studio workflows.

Open-source async coding agent you can run in your own sandbox

Open-source framework from LangChain AI for building your organization's internal coding agent — the same pattern Stripe's Minions, Ramp's Inspect, and Coinbase's Cloudbot follow. Built on LangGraph and Deep Agents, Open SWE runs each task in an isolated cloud sandbox (Modal, Daytona, Runloop, or LangSmith), invokes from Slack, Linear, or GitHub, orchestrates subagents, and opens pull requests autonomously — customizable end-to-end for your codebase and conventions.

OpenAI's official GitHub Action that runs Codex in CI

OpenAI's official GitHub Action for running Codex CLI in GitHub Actions workflows with filesystem/network permission profiles and runner-level privilege controls. This is the CI/CD Action, not the terminal Codex agent; current Codex exec enables analytics by default, so telemetry policy needs review.

Lightweight multi-agent handoff framework by OpenAI

OpenAI Swarm is an experimental lightweight framework for building multi-agent systems with handoff patterns. Agents are defined as simple Python functions with instructions and tool lists, and can hand off conversations to other specialized agents. Designed to be minimal and educational rather than production-ready — demonstrates patterns for agent coordination without heavy abstractions. Runs on OpenAI's Chat Completions API with function calling for tool use and agent transitions.

Open-source financial data platform for quants, analysts, and AI agents

OpenBB is an open-source financial data platform that normalizes data from 100+ providers into a unified Python SDK, REST API, and Excel Add-in. It serves as the open-source alternative to Bloomberg Terminal for developers building fintech applications, quantitative research pipelines, and AI-powered financial analysis tools. With over 65,000 GitHub stars and SOC 2 Type II certification, it is one of the most popular open-source developer tools for financial data.

AI-generated git commit messages in 1 second

OpenCommit is a CLI tool that generates meaningful git commit messages using LLMs in about one second. It analyzes staged changes and produces conventional commit-style messages following your team's conventions. Supports OpenAI, Anthropic Claude, Ollama local models, and other providers. 7,200+ GitHub stars, MIT licensed, winner of GitHub 2023 Hackathon. Works as a CLI command, git hook, or GitHub Action for automated commit message generation.

Open-source Kubernetes cost monitoring (CNCF)

OpenCost is a CNCF-certified open-source tool for real-time Kubernetes cost monitoring that maps cloud spend directly to namespaces, deployments, pods, and labels. It provides granular cost allocation across teams and projects without vendor lock-in, supporting AWS, GCP, Azure, and on-premises clusters as the industry standard for open-source FinOps visibility in cloud-native environments.

AI-ready PDF parser with benchmark-leading accuracy

OpenDataLoader PDF is a high-performance parser that extracts structured, AI-ready data from PDFs with industry-leading 0.907 benchmark accuracy. Combines deterministic local processing with optional AI hybrid mode for complex layouts, OCR support across 80+ languages, formula extraction in LaTeX, chart descriptions, and built-in prompt injection filtering. Available as Python, Node.js, and Java SDKs for seamless RAG pipeline and data preparation integration.

Lightweight eval library for LLM applications

OpenEvals is a lightweight evaluation library from the LangChain team for testing LLM application quality using LLM-as-judge patterns. It provides pre-built prompt sets and evaluation functions that score model outputs against criteria like accuracy, relevance, coherence, and safety without requiring complex infrastructure. Available as both Python and JavaScript packages, OpenEvals complements OpenAI Evals with a simpler, framework-agnostic approach to quality measurement in agentic workflows.