Open Source Tools

Microsoft's zero-code-change RL trainer for AI agents

Agent Lightning is Microsoft Research's open-source framework that makes AI agents trainable through reinforcement learning with virtually zero code changes. Supports RL, Automatic Prompt Optimization, and Supervised Fine-tuning across any agent framework including LangChain, OpenAI Agents SDK, AutoGen, and CrewAI. 14K+ GitHub stars, ranked among Microsoft's top 50 most-starred projects.

Open standard for portable skills across AI agents

Agent Skills is the open SKILL.md folder specification for packaging reusable instructions, scripts, references, and assets that compatible AI agents load through progressive disclosure. Originally developed by Anthropic and released as an open standard, it defines the portable format itself—not an example library, marketplace, or hosted agent product.

Transparent AI agent framework with 100+ skills and real-time visibility

Agent Zero is an open-source general-purpose AI agent framework with 16,700+ GitHub stars that uses the computer itself as a tool. Unlike structured orchestration frameworks, it provides full transparency where every thought, action, and tool call is visible and editable in real time, supporting 100+ extensible skills.

Browser-based autonomous AI agent platform

AgentGPT is an open-source browser-based platform with 36K+ GitHub stars for creating and deploying autonomous AI agents without any setup or installation. Give an agent a name and goal in plain language, and it autonomously decomposes the objective into subtasks, executes them, and iterates toward completion. Built with Next.js and supports multiple LLM providers. Features include web search, code execution, and task chaining. No technical expertise required to create functional AI agents.

AI autopilot for existing test cases

AgentQ runs existing manual test cases on autopilot using AI to navigate applications and verify expected behavior without requiring test script rewriting. It bridges the gap between manual test plans and full automation by taking existing test documentation and executing it automatically, serving teams with large manual test backlogs who need immediate automation without migration effort.

Production-ready multi-agent platform by Alibaba

AgentScope is an open-source multi-agent platform with 22K+ GitHub stars developed by Alibaba. Designed for production-ready multi-agent applications with built-in distributed execution, fault tolerance, and agent-to-agent messaging. Features memory management with compression, a drag-and-drop workstation for visual agent building, multi-modal support, and flexible pipelines for sequential, parallel, and conditional agent orchestration. Supports all major LLM providers.

TypeScript AI agent standard library

Standard library of AI tools and integrations for TypeScript-based agents. Works with any AI SDK and includes ready-made integrations for search, web scraping, email, and other common tool patterns. Saves developers from rebuilding common agent capabilities from scratch, providing well-tested, type-safe building blocks for rapid AI agent development.

Security scanner for AI agentic workflows and MCP servers

Agentic Radar is an open-source CLI security scanner that maps attack surfaces in agentic AI workflows. It detects MCP servers, visualizes agent tool chains, and validates against OWASP LLM Top 10 vulnerabilities including prompt injection and excessive agency. Supports scanning CrewAI, LangGraph, AutoGen, and Semantic Kernel pipelines. Built by SPLX AI with active development and MCP-specific detection capabilities added for the growing MCP ecosystem.

LLM vulnerability scanner and red teaming kit

Agentic Security is an open-source vulnerability scanner for LLM agent workflows that tests AI systems against jailbreaks, fuzzing, and multimodal attacks. It probes weaknesses across text, image, and audio inputs through multi-step jailbreak simulations, randomized stress testing, and reinforcement learning-powered adaptive attacks. The toolkit connects directly to LLM APIs for high-volume real-world attack scenarios, helping developers identify and patch safety gaps before deployment.

AI-driven development workflow template

A template system that bootstraps AI-driven development workflows for your projects. Provides structured workflows, templates, and configurations for integrating AI agents into your development process. Reduces setup time by giving teams a proven starting point for organizing AI-assisted coding, task management, and quality assurance in new and existing repositories.

Non-agent approach to automated software engineering via localize-and-repair

Agentless takes a deliberate non-agent approach to LLM-powered software engineering. Instead of autonomous agents making tool calls, it uses a structured localize-then-repair pipeline: first narrowing down which files and functions are relevant, then generating targeted patches. Achieved competitive SWE-Bench results at $0.34 average cost per issue. Adopted by OpenAI for o3 evaluations. 3,000+ GitHub stars, MIT licensed. A counterpoint to the agent-heavy trend in AI coding tools.

Context retrieval layer for AI agents and RAG

Airweave is an open-source context retrieval platform that connects AI agents and RAG systems to 50+ apps and databases through a unified search interface. It continuously syncs data from sources like Notion, Slack, GitHub, and databases, making it searchable through LLM-friendly APIs. Airweave includes Python and TypeScript SDKs, MCP support, and a CLI for managing data connections.

A fast, cross-platform terminal

Self-described 'fastest terminal emulator in existence' — a GPU-accelerated, cross-platform terminal written in Rust focused on simplicity and performance. No tabs, splits, or built-in multiplexer — designed to pair with tmux or Zellij. Configured via YAML with a minimal feature set that prioritizes speed above all else. Supports true color, Vi mode, regex search, and clickable URLs. Available on macOS, Linux, Windows, and BSD. 57K+ GitHub stars.

Open-source toolkit for audio, music, and speech generation

Amphion is an open-source audio generation toolkit from OpenMMLab designed for reproducible research in speech synthesis, voice conversion, singing voice synthesis, and text-to-audio generation. It implements state-of-the-art models including MaskGCT, DualCodec, VITS, and VALL-E with built-in architecture visualizations for educational use. The project ships with the Emilia-Large dataset of 200,000 hours of speech data and includes multiple vocoders and evaluation metrics for benchmarking.

Craft image-scaling prompt-injection payloads to red-team multimodal AI systems

Open-source red-team toolkit from Trail of Bits that generates image-scaling attack payloads — images that look benign at full resolution but reveal a hidden prompt injection after a multimodal system downsamples them.

Simple agentless IT automation

Agentless IT automation tool from Red Hat for configuration management, application deployment, and infrastructure orchestration. Ansible uses simple YAML playbooks executed over SSH or WinRM — no agent installation required on managed nodes. Modules cover Linux, Windows, network gear, cloud APIs, and containers. Idempotent execution makes runs safe to repeat. Open-source core (GPL) with Ansible Automation Platform as the commercial Red Hat offering for enterprises.

Official SDK for building Claude-powered agentic applications

Anthropic's official SDK for building agents with Claude. Provides high-level abstractions for tool use, multi-turn conversations, computer use, and agent loops on top of the Claude API. Simplifies the development of production-grade agents by handling common patterns like retry logic, context management, and tool orchestration in a well-tested library.

Workflow orchestration platform for data pipelines

Apache Airflow is an open-source workflow orchestration platform with 39K+ GitHub stars for authoring, scheduling, and monitoring data pipelines as Python DAGs. Used by 80K+ organizations for ETL, ML training, and data transformation. Features dynamic pipeline generation, extensive operator library for AWS/GCP/Azure, task dependencies, retries, SLA monitoring, a rich web UI with Gantt charts, and pluggable executors from local to Kubernetes. The industry standard for pipeline orchestration.

Distributed event streaming platform

Apache Kafka is the industry standard open-source event streaming platform with 30K+ GitHub stars, used by 80% of Fortune 100 companies. Handles trillions of events per day with high throughput, low latency, and built-in fault tolerance. Features real-time stream processing via Kafka Streams, connectors for 100+ data sources, exactly-once semantics, and multi-datacenter replication. Foundation for event-driven architectures, real-time pipelines, and data integration at scale.

Native Linux containers on macOS via Apple Virtualization

Apple Containerization is Apple's official Swift package for running Linux containers natively on macOS using the Virtualization framework. It provides near-native performance without Docker Desktop's heavyweight VM, supporting OCI images, container networking, and a command-line interface. The library leverages Apple Silicon hardware acceleration for minimal overhead container execution on Mac development machines.

AI agent that builds other AI agents

Archon is an open-source AI meta-agent created by Cole Medin that autonomously builds, refines, and optimizes other AI agents. Now evolving into Archon OS, it serves as a knowledge and task management backbone for AI coding assistants. The system uses an agentic coding workflow with framework knowledge bases for Pydantic AI, LangGraph, and other agent frameworks, enabling developers to describe what they need and let Archon generate the agent code, test it, and iterate until it works.

Open-source data curation platform for LLM fine-tuning

Argilla is an open-source platform for curating and annotating data for LLM fine-tuning and RLHF workflows. It provides collaborative annotation interfaces for text classification, ranking, and preference labeling with integrated quality metrics. Part of the Hugging Face ecosystem, Argilla supports direct dataset publishing to the Hub and integrates with major training frameworks for seamless model improvement pipelines.

Visual regression testing for CI/CD pipelines

Argos CI is a visual regression testing platform that automatically catches unintended UI changes in CI/CD pipelines. It integrates with Playwright, Cypress, Storybook, and Puppeteer, featuring a stabilization engine that filters flaky pixel differences from genuine regressions. Used by teams at Meta and MUI for frontend quality gates.

Headless UI component library for React, Vue, Solid, and Svelte

Ark UI is a headless component library providing unstyled, accessible UI primitives for React, Vue, Solid, and Svelte. Built by the Chakra UI team using state machines for predictable behavior across frameworks. Includes complex components like date pickers, color pickers, comboboxes, and tree views that are notoriously difficult to build from scratch while maintaining accessibility.

Versatile microservice framework for any protocol

Armeria is an open-source microservice framework from the creator of Netty at LINE Corporation that supports gRPC, Thrift, REST, and GraphQL on a single server and port. It provides built-in decorators for metrics, distributed tracing, load balancing, authentication, rate limiting, circuit breakers, and automatic retries. The framework integrates seamlessly with Spring Boot, Dropwizard, and Reactive Streams while serving automated API documentation with interactive request testing.

Pipelineless AppSec for AI-driven development

Arnica is a pipelineless application security platform that scans every code push in real-time across SAST, SCA, IaC, secrets, and license risks without CI/CD pipeline integration. Its Arnie AI engine combines deterministic static analysis with multi-agent reasoning to detect logic flaws and vulnerabilities in both human-written and AI-generated code. It integrates directly with GitHub, GitLab, Bitbucket, and Azure DevOps for 100% repository coverage from day one.

Java diagnostic and troubleshooting tool

Arthas is Alibaba's open-source Java diagnostic tool that lets developers troubleshoot production issues without modifying code or restarting servers. It attaches to running JVM processes to inspect class loading, decompile classes, trace method invocations, monitor performance metrics, and view real-time stack traces. Supports JDK 6+ with both telnet and WebSocket interfaces for local and remote diagnostics across Linux, macOS, and Windows.

Agentic IM chatbot platform with multi-platform LLM integration

AstrBot is an open-source agentic chatbot infrastructure that connects multiple instant messaging platforms including Telegram, Discord, Slack, WeChat, QQ, Feishu, and DingTalk to AI language models. It supports multi-provider LLM integration, MCP protocol, knowledge bases, persona management, multimodal input, and a plugin ecosystem with over 1,000 community extensions. Features include a web management UI, sandbox code execution, and auto-context compression for efficient conversations.

Database schema management for modern teams

Database schema management and migration tool by Ariga with a declarative schema-as-code approach. Features automatic migration planning, CI/CD integration, and drift detection to keep database schemas in sync across environments. Supports PostgreSQL, MySQL, MariaDB, and SQLite, making database changes as reviewable and version-controlled as application code.

Official remote MCP server for Jira and Confluence

Atlassian's official remote MCP server connects Jira and Confluence to LLM clients, IDEs, and agent platforms over OAuth, so Claude, Cursor, and other MCP-aware tools can search issues, read pages, and post updates inside the same permission boundaries users already have. As a vendor-hosted reference implementation, it standardizes the Atlassian side of remote Model Context Protocol deployments.

Build AI agents like LEGO — modular and predictable

Atomic Agents is a lightweight Python framework by BrainBlend AI that applies Atomic Design principles to AI agent development. Each component — agents, tools, context providers — is a single-purpose, reusable building block with Pydantic-enforced input/output schemas for type safety. Built on Instructor for structured LLM outputs, it prioritizes predictability and developer control over the autonomous-but-unpredictable behavior of larger frameworks like LangChain or CrewAI.

Magical shell history

Shell history manager that replaces the default history with a SQLite-backed, encrypted, and synchronized command history across all your machines. Features full-text search with fuzzy matching, directory-based context filtering, session tracking, and statistics about command usage. Syncs via an encrypted server (self-hostable or hosted). Supports bash, zsh, and fish shells. 22K+ GitHub stars. Transforms shell history from a simple list into a searchable, cross-machine knowledge base.

Open-source autonomous AI agent platform

AutoGPT is an open-source autonomous AI agent platform with 183K+ GitHub stars that breaks goals into subtasks and executes them independently. Features a visual Agent Builder for creating workflows without coding, persistent cloud-based agents running on triggers, a marketplace of pre-built agents, and a plugin system. Agents can browse the web, write code, manage files, and call tools autonomously while maintaining memory across sessions.

Autonomous LLM-powered terminal coding agent

Autohand is an AI platform for adaptive continuous engineering and autonomous code evolution, giving teams infrastructure to coordinate multiple AI agents inside sandboxed execution environments. Its open-source Commander tool builds command interfaces that orchestrate multi-agent workflows, while the broader platform lets agents iteratively write, test, and evolve code safely. Aimed at engineering teams pushing beyond simple code generation toward continuous AI-driven software improvement.

AI agents running automated research

Autonomous research framework by Andrej Karpathy that lets AI agents plan and execute machine learning experiments end-to-end. Agents design experiments, run training loops, analyze results, and iterate on hypotheses with minimal human oversight. Runs efficiently on single-GPU setups and applies agentic patterns beyond software development — bringing autonomous agent workflows to the research process itself.

Curated collection of agent skills and capabilities

An opinionated project scaffolding tool that generates AI-ready codebases with pre-configured CLAUDE.md files, git hooks, and CI/CD templates. Ensures new projects follow best practices for AI-assisted development from day one, including structured prompts, context files, and workflow configurations that help AI coding agents understand and navigate the codebase effectively.

Curated directory of terminal-native AI coding agents and orchestration tools

Living directory of 80+ CLI coding agents, orchestration harnesses, and comparison benchmarks. Includes agent managers, parallel runners, and infrastructure tools. Community-maintained reference for the agentic coding ecosystem that helps developers evaluate and choose the right terminal-based AI coding tools from an increasingly crowded and fast-moving landscape.

Curated Claude Code resources

Official Anthropic-curated list of Claude Code tips, CLAUDE.md templates, hooks, MCP servers, and community tools. Essential reference for Claude Code users looking to optimize their workflow. Covers everything from initial setup and configuration best practices to advanced patterns like custom hooks and multi-agent orchestration with the Claude Code CLI.

Type-safe LLM function builder

BAML is a domain-specific language by BoundaryML for building reliable AI workflows and agents through schema engineering. It turns prompt engineering into a structured, type-safe discipline by letting developers declaratively define function schemas, validate LLM responses, and version prompts without fragile JSON parsing or boilerplate. BAML reframes prompt engineering as schema definition, making AI workflows testable and maintainable across models.

Markdown-based project management for AI agents

A tool for managing project collaboration between humans and AI agents in a git ecosystem. Uses markdown files as the source of truth for backlogs, tasks, and progress tracking. Keeps everything version-controlled and transparent, making it easy to assign work to AI agents and review their contributions alongside human commits.

Spotify's open-source developer portal framework

Backstage is Spotify's open-source framework for building internal developer portals, now a CNCF incubating project with 27,000+ GitHub stars. It provides a unified software catalog, service documentation, CI/CD pipeline views, and a plugin architecture with 200+ community plugins. Teams use it to create a single pane of glass for service ownership, API documentation, infrastructure management, and developer self-service workflows.

Python and TypeScript framework for production multi-agent systems

BeeAI Framework is an Apache-2.0 toolkit for building production-ready AI agents and multi-agent systems in Python and TypeScript. Its docs cover agents, tools, RAG, memory, workflows, backend providers, serving, and A2A/MCP integration surfaces, making it a vendor-neutral option for teams comparing LangGraph, CrewAI, Mastra, and related agent runtimes.

Open-source SQL editor and DB manager

Beekeeper Studio is a modern, open-source SQL editor and cross-platform database GUI for MySQL, PostgreSQL, SQLite, SQL Server, MariaDB, CockroachDB, Amazon Redshift, Oracle, and LibSQL. Focuses on a clean interface, fast multi-tab editor, saved queries, data export, and schema browsing — a lightweight alternative to DBeaver or DataGrip for everyday database work on Windows, macOS, and Linux.

ML model serving and deployment framework

BentoML is an open-source framework with 7K+ GitHub stars for packaging, deploying, and serving ML models as production-ready APIs. Bundles models, preprocessing, and serving logic into portable Bento archives with auto-generated REST/gRPC endpoints. Features adaptive batching for throughput optimization, GPU scheduling, multi-model inference pipelines, and containerization. Supports all major ML frameworks including PyTorch, TensorFlow, scikit-learn, and Hugging Face Transformers.

TypeScript-native open-source auth library

Better Auth is an open-source TypeScript-native auth library with 10K+ GitHub stars providing a comprehensive, framework-agnostic solution. Features email/password, social OAuth, magic links, passkeys, 2FA, session management, and organization support. Works with Next.js, Nuxt, SvelteKit, Astro, and any Node.js framework. Database adapters for PostgreSQL, MySQL, SQLite, MongoDB, Drizzle, and Prisma. Zero vendor lock-in alternative to Clerk and Auth0.

50x faster LLM gateway with MCP support, built in Go

Bifrost is a high-performance open-source AI gateway built from scratch in Go. Unifies access to 15+ providers and 1,000+ models through a single OpenAI-compatible API with only 11 microsecond overhead per request at 5K RPS — 50x faster than LiteLLM. Features automatic failover, load balancing, semantic caching, and functions as both MCP client and MCP server. Apache 2.0 licensed.

Fast Rust-based formatter and linter for web projects

Biome is a Rust-based toolchain for JavaScript, TypeScript, JSX, JSON, and CSS that combines formatting and linting in a single tool running 20-50x faster than ESLint + Prettier. Provides 300+ lint rules with automatic fixes, opinionated formatting compatible with Prettier output, and import sorting. Zero configuration needed to start with sensible defaults. Designed as a drop-in replacement for ESLint and Prettier with first-class IDE support via VS Code and JetBrains extensions.

Microsoft's framework for running 1-bit large language models on consumer CPUs

BitNet is Microsoft's official inference framework for 1-bit quantized large language models that enables running models with up to 100 billion parameters on standard consumer CPUs without requiring a GPU. By leveraging extreme quantization where weights use only 1.58 bits on average, BitNet achieves dramatic reductions in memory footprint and computational cost while maintaining competitive output quality for many practical use cases.