Agents

New open-source framework to build and deploy intelligent agents with support for Claude, Gemini, and OpenAI models. Apache 2.0 licensed

Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows with actor-model concurrency. Apache 2.0 licensed

Stateful agent workflow platform with memory, tools, branching, and long-running task execution

JavaScript-native framework for building and managing multi-agent systems with a Kanban-inspired approach. Visual task board for AI agents with real-time collaboration features. MIT licensed

Open-source agentic coding assistant with IDE workflows, tool use, and support for local or OpenAI-compatible models

Enforce output format (JSON Schema, Regex, etc) of language models by filtering allowed tokens at each generation step. Compatible with Hugging Face, llama-cpp-python, and vLLM. MIT licensed

Foundational library for agents, chains, and memory

Pioneering framework for structured and meta-prompt design. Battle-tested by thousands of users worldwide with 10,000+ stars. The most popular prompt engineering paradigm for creating reusable, maintainable prompt templates. Apache 2.0 licensed

Stateful, controllable agent orchestration

Visual low-code platform for agentic workflows

Harness LLMs with multi-agent programming. Mature tool calling system based on Pydantic, supports hundreds of LLM providers including OpenAI and local servers. Built for robust agent behavior in real-world use cases. MIT licensed

Platform for building stateful agents with advanced memory that learn and self-improve over time

Memory-first coding harness designed for long-lived agents that learn from experience. Persistent agents with portable memory across models (Claude, GPT, Gemini, GLM, Kimi). CLI and desktop app for macOS, Windows, and Linux. Apache 2.0 licensed

Python framework for structured outputs and agentic AI workflows. Simplifies LLM interactions with type-safe interfaces, automatic schema generation, and built-in observability. From the creators of Prefect. Apache 2.0 licensed

TypeScript-first agent framework with built-in RAG, workflows, tool integrations, observability and observational memory

Universal memory layer for AI agents. Persistent, multi-session memory across models and environments

High-performance, benchmarked AI memory system for persistent recall and retrieval in long-horizon autonomous workflows

The Multi-Agent Framework: First AI Software Company. Assigns different roles to GPTs to form a collaborative software entity. Takes one-line requirements and outputs comprehensive software development artifacts including user stories, competitive analysis, requirements, data structures, APIs, and documents. ICLR 2024 oral presentation (top 1.2%). MIT licensed

Microsoft's official framework combining AutoGen's agent abstractions with Semantic Kernel's enterprise features. Supports Python and .NET with graph-based workflows

Minimal CLI coding agent by Mistral. Lightweight, fast, and designed for local development workflows

Powerful GUI agent family for autonomous mobile device control. Multimodal agent framework designed to operate smartphone apps through visual UI perception and reasoning. MIT licensed

Beautiful local-first coding agent running in your terminal. Built for privacy and control with support for multiple AI providers via OpenRouter

PHP Agentic Framework for building production-ready AI driven applications. Connect components (LLMs, vector DBs, memory) to agents that can interact with your data. MIT licensed

Advanced multi-agent collaboration system

Model-agnostic AI agent runtime written in Rust with specialist agents, MCP support, multiple provider integrations, and zero-config setup. Apache 2.0 licensed

TypeScript-native multi-agent orchestration with multi-model teams and parallel execution. Automatically converts goals to task DAGs. MIT licensed

Asynchronous coding agent from the LangChain ecosystem for background software engineering tasks

Production-ready lightweight framework for multi-agent workflows. The evolution of Swarm with enhanced orchestration capabilities and enterprise-grade features

AI Agent Networks for Open Collaboration. Platform for building collaborative multi-agent systems with shared knowledge and distributed task execution. Apache 2.0 licensed

Terminal-native autonomous coding agent

Full-featured open-source AI software engineer

Open-source framework for building general AI agents. Modular agent architecture with planning, tool use, and autonomous task execution. 56k+ stars. MIT licensed

Safe and private runtime for autonomous AI agents with policy-driven execution boundaries and CLI integration

Structured outputs for LLMs. Guarantees valid JSON, regex-compliant text, and Pydantic model outputs during generation. Trusted by NVIDIA, Cohere, Hugging Face, and vLLM. Apache 2.0 licensed

AI agent company and orchestration framework with 55K+ stars. MIT licensed

Conversational control layer for customer-facing AI agents. Enterprise-grade context engineering framework optimized for consistent, compliant, and on-brand B2C and sensitive B2B interactions. Apache 2.0 licensed

Terminal coding agent with hash-anchored edits, LSP integration, subagents, MCP support, and package ecosystem

100-line minimalist LLM framework for building agent workflows. Lightweight, extensible architecture for tool use and autonomous task execution

24/7 AI employee team for automating complex challenges. Low-code multi-agent framework with handoffs, guardrails, memory, RAG, and 100+ LLM providers

AI prompt optimization tool with multi-round iterative improvements, dual-mode optimization for system and user prompts, and multi-model support. Available as web app, desktop app, Chrome extension, and Docker deployment. AGPL-3.0 licensed

Open-source tools for prompt testing and experimentation with support for LLMs and vector databases. Test prompt variants across multiple providers (OpenAI, LLaMA) and vector stores (Chroma, Weaviate, LanceDB). Apache 2.0 licensed

Task-based NLP engine with Pydantic structured outputs, built-in evaluation, and LiteLLM as the universal LLM backend. Think "scikit-learn for LLM-powered NLP". Apache 2.0 licensed

Type-safe AI agent framework from the creators of Pydantic. Model-agnostic with 20+ providers, built-in observability via Logfire, MCP/A2A protocol support, and YAML/JSON agent definitions. MIT licensed

Agent framework built on Qwen models featuring function calling, MCP support, code interpreter, RAG, and Chrome extension. Powers Qwen Chat with advanced tool use and planning capabilities. Apache 2.0 licensed

SDK for building and orchestrating AI agents and workflows across multiple programming languages

Open-source AI workspace for building, deploying, and orchestrating AI agents. Visual canvas with 1000+ integrations, multi-framework support (Agno, OpenAI, LangChain, Google ADK), and self-hosted or cloud deployment. Apache 2.0 licensed

Open-source browser API for AI agents and apps. Batteries-included browser sandbox for web automation without infrastructure worries. Apache 2.0 licensed

Model-driven approach to building AI agents in just a few lines of code. Multi-agent systems, autonomous agents, and streaming support with built-in MCP. Apache 2.0 licensed