Agent Framework

Build modular and scalable LLM Applications in Rust. Provides agent orchestration, tool-use, RAG pipelines, and other core capabilities for high-performance AI agent systems.

Open-source AI agent platform for financial analysis using LLMs, featuring intelligent research, market forecasting, and automated financial report generation.

A framework for building, running, and scaling AI agents as APIs and microservices, with built-in observability, auditability, and identity-aware access control from day one.

A GenAI application development framework that simplifies agent interaction with structured data and chained-calls syntax, using event-driven flow for complex logic.

Hundreds of models and providers. One command to find what runs on your hardware. Provides local LLM runtime for AI agents.

Atomic Agents is a modular AI agent building framework with an atomic design philosophy, providing composable components including tools, pipelines, and memory management for constructing agent systems.

BaseAI is a serverless AI agent framework for web developers, enabling local-first agentic pipes, tools, and memory with one-command serverless deployment for rapid AI agent application delivery.

Leading AI Agent Context Platform that provides unified context delivery for AI agents with knowledge management, resource scheduling, and skill integration.

The GEP-Powered Self-Evolution Engine for AI Agents — enables agents to autonomously optimize and evolve using Genome Evolution Protocol for continuous capability improvement.

AutoChain is a lightweight, extensible, and testable LLM Agent framework by Forethought, providing clean abstractions for agent building with automatic tool selection, conversation history management, and automated testing workflows.

The Multi-Agent Framework for building the first AI Software Company, enabling natural language programming with multi-role collaboration for automated requirement analysis, design, coding, and testing.

Fully-automated and zero-code LLM agent framework that enables users to build and deploy custom AI agents through natural language without writing code.

nanobot is an ultra-lightweight personal AI agent that supports multiple LLM backends for quickly deploying a private intelligent assistant.

Adala is an autonomous data labeling agent framework that uses AI agents to automate data annotation, classification, and quality checks, significantly improving data processing efficiency.

Agent SDK Go is a powerful Go framework for building production-ready AI agents, providing core features including tool use, conversation management, and multi-model support.

Open Multi-Agent is a lightweight TypeScript multi-agent framework that auto-decomposes tasks and executes them in parallel with a single runTeam() call. Only 3 dependencies, deploys anywhere Node.js runs.

A JVM framework by JetBrains for building predictable, fault-tolerant, enterprise-ready AI agents across all platforms — from backend services to Android, iOS, and in-browser environments, with built-in MCP and multi-provider LLM support.

Shannon is a production-oriented multi-agent orchestration framework built in Go, focusing on efficient and reliable agent coordination and task scheduling for enterprise-grade multi-agent systems.

LazyLLM is a lightweight multi-agent LLM application framework offering the easiest way to build multi-agent LLM apps, with built-in RAG, knowledge graph, fine-tuning, and integration with LangChain and LlamaIndex ecosystems.

An agent framework for llama.cpp that supports structured function calls and JSON output, enabling easy interaction with local LLMs without fine-tuning.

GenAI Agents is a comprehensive collection of 50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

An end-to-end infrastructure for training and evaluating various LLM agents — provides a complete toolchain from data construction to model training and evaluation.

ART (Agent Reinforcement Trainer) trains multi-step agents for real-world tasks using GRPO reinforcement learning, enabling on-the-job training for models like Qwen, Llama, and more.

Ouroboros is a spec-driven multi-agent framework that shifts from traditional prompting to specification-driven development, supporting multi-agent collaboration, MCP tool integration, and automated workflow orchestration for building high-quality agent systems.

Agent framework built on Qwen LLM, featuring function calling, MCP tool integration, code interpreter, RAG, and browser extension support.

An AI multi-agent framework for .NET with multi-LLM backend integration, providing agent management, tool calling, and conversation state management for enterprise agent development.

DeepResearchAgent is a hierarchical multi-agent system designed for deep research tasks and general-purpose problem solving, using a top-level planning agent to coordinate specialized sub-agents for automated task decomposition and efficient cross-domain execution.

LLM Compiler for Parallel Function Calling (ICML 2024), significantly improving agent tool calling efficiency and speed through parallel execution.

TEN Framework is an open-source framework for building conversational voice AI agents with real-time multi-modal interaction support.

Youtu Agent is a lightweight agent framework by Tencent that delivers out-of-the-box support for open-source LLMs, simplifying agent development and deployment.

PocketFlow is a minimalist 100-line LLM framework that lets Agents build Agents, enabling complex AI agent workflows through a clean abstraction layer.

SuperAGI is a dev-first open-source autonomous AI agent framework for building, managing, and running useful autonomous agents quickly and reliably.

Yao is a single-binary runtime to build and run autonomous agents — no Python, no Node.js, just define the role. Provides lightweight, high-performance agent development framework.

Teams-first multi-agent orchestration for Claude Code. Designed for team collaboration with support for multi-agent coordination, task distribution, and result integration to enhance team AI development efficiency.

Hive is a production-ready multi-agent execution harness providing state management, failure recovery, observability, and human-in-the-loop control with auto-generated multi-agent topologies for complex business workflows.

AG2 (formerly AutoGen) is an open-source AgentOS providing a multi-agent conversation framework with flexible agent orchestration, tool integration, and distributed collaboration for building complex multi-agent systems.

An autonomous agent framework for Elixir built for distributed, autonomous behavior and dynamic workflows, leveraging BEAM VM concurrency and fault tolerance for production-grade agent systems with high availability.

Agent-oriented programming framework for building LLM applications in Java. Provides agent abstractions, tool calling, multi-agent collaboration, and other core capabilities for enterprise Java ecosystem integration.

Open-source multi-agent framework from Alibaba, enabling the construction of observable and interpretable agents with rich distributed capabilities.

An AI Agent workforce platform that assigns every team member an AI agent squad for multi-agent collaboration, task orchestration, and compound skill building to scale team capacity beyond headcount.

AgentStation is an open-source platform focused on agent runtime orchestration, tool execution, and developer workflows for unifying multiple automation capabilities.

Agentuity is a production-oriented agent platform focused on runtime, tool execution, and orchestration for teams building deployable agent services.

AIOS: AI Agent Operating System - a foundational runtime for large-scale deployment and management of LLM agents with scheduling, memory management, and tool registration.

Agno is a high-performance agent framework for building multimodal AI agents with memory, knowledge, and tool-use capabilities, supporting multiple LLM providers.

A functional, composable, TypeScript-first AI Agent framework for real-world applications with declarative agent definition, tool composition, and streaming workflows.

A meta-learning agent framework that learns and evolves through conversation, enabling agents to autonomously acquire new skills and optimize strategies.

Spring AI Alibaba is an Agentic AI Framework for Java developers, built on the Spring ecosystem to provide multi-agent collaboration, workflow orchestration, and RAG capabilities.

OpenHands is an open-source AI software engineering agent platform that can automatically execute development tasks, modify code, and support collaborative iteration.

Build applications that make decisions (chatbots, agents, simulations, etc.). Monitor, trace, persist, and execute on your own infrastructure.

A curated collection of 500 AI agent use cases across industries including healthcare, finance, education, and retail. Showcases practical applications with open-source project links.

Real-time transport layer for Java AI agents supporting WebSocket, SSE, gRPC, and WebTransport/HTTP3, with native MCP, A2A, and AG-UI protocol support for building event-driven AI agent communication architectures.

One command brings a complete pre-wired LLM stack with hundreds of services to explore and build AI applications.

LangChain AWS is LangChain's AWS integration library, supporting building AI agents using AWS Bedrock, Lambda, and other services with seamless AWS cloud integration.

Pi Mono is a comprehensive AI agent toolkit including a coding agent CLI, unified LLM API, TUI and web UI libraries, Slack bot, and vLLM pod management for end-to-end agent development.

Block Open is infrastructure for the open agent ecosystem, focused on runtimes, tool connectivity, and task orchestration for teams that want standardized agent platforms.

An open-source chatbot and AI agent development platform with visual bot editor, NLP, and deep learning integration for multi-platform deployment.

ByteDance's open-source multimodal AI agent stack connecting cutting-edge AI models with agent infrastructure for GUI automation and computer control.

CAMEL is an open-source framework for multi-agent collaboration, supporting role-play, task decomposition, and coordinated execution.

Extensible AI agent microservice framework with plugin system, custom tools, and multi-model integration for conversational AI.

Cloudflare Agents is Cloudflare's platform for building agents on the edge runtime, combining Workers, durable state, and tool execution for low-latency production services.

Eino is an open-source Go framework from ByteDance for building LLM applications, offering type-safe orchestration, streaming, tool calling, and RAG pipelines for high-performance AI agent applications.

An open-source agent harness platform providing the best agent toolkit, supporting multiple AI coding agents.

CodeFuse-muAgent is an innovative agent framework driven by a knowledge graph engine, integrating EKG (Enterprise Knowledge Graph) technology for multi-agent collaboration, RAG-enhanced retrieval, and tool learning.

Ottomator Agents is a collection of runnable agent examples and automation patterns covering research, browser actions, tool use, and multi-step flows for practical learning.

CopilotKit is an open-source framework for building AI agent frontends, supporting Generative UI and the AG-UI Protocol to help developers quickly integrate agent capabilities into apps.

IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for complex task completion.

A multi-agent collaboration framework where AI agents form crews to accomplish complex tasks together. Role definition, task assignment, tool sharing, and process orchestration.

Fabric is an open-source framework for augmenting humans using AI, providing a modular system of crowdsourced AI prompts for solving specific problems anywhere.

Dapr Agents is a framework for building autonomous, resilient, and observable AI agents with built-in workflow orchestration, security, statefulness, and telemetry for production-grade agent deployments.

OpenAgentsControl is an AI agent framework for plan-first development workflows with approval-based execution. Supports TypeScript, Python, Go, and Rust with automatic testing, code review, and validation.

A cognitive architecture framework for enterprise AI agents, providing complete methodology for agent planning, execution, and learning.

Deepgram Agent API is a real-time interface layer for voice agents, combining speech recognition, TTS, and dialog control for phone, assistant, and voice workflow applications.

DIMOS is an agentic operating system for physical space, enabling natural language control of humanoids, quadrupeds, drones, and other hardware platforms, with multi-agent systems that seamlessly integrate cameras, lidar, and actuators.

An AI Agent builder and runtime by Docker Engineering, bringing container-native isolation, portability, and standardization to AI agent lifecycle management from development through production deployment.

A custom AI agent platform that lets teams build and deploy AI assistants by composing multiple agents, connecting them to internal knowledge bases and tools for trusted AI-powered collaboration in enterprise workflows.

A curated list of AI autonomous agents. A comprehensive collection of open-source agent projects for discovering and understanding the agent ecosystem.

Eidolon is the first AI Agent Server, providing a pluggable Agent SDK and enterprise-ready runtime supporting multi-agent orchestration, tool integration, and production deployment.

An autonomous agent framework for everyone, built in TypeScript with multi-platform deployment support and a rich plugin ecosystem for conversational AI agents and social bots.

An agent framework for the JVM built in Kotlin, providing a complete toolchain for developing, orchestrating, and deploying AI agents in the Java/Kotlin ecosystem.

The interaction control harness for customer-facing AI agents, optimized for building controlled, consistent and predictable customer interactions with LLMs.

A production-ready Reinforcement Learning AI Agent Library from Meta with comprehensive algorithm implementations.

A modular high-level library from Meta to train embodied AI agents across a variety of tasks and environments.

A next-generation Android RPA agent framework that enables intelligent device control through agent-driven automation, with smart UI element recognition and automated operations for mobile testing and intelligent assistants.

A framework for integrating AI into JSX components. Build AI applications the React way with streaming rendering, tool use, and agent composition.

Agent Zero is a general-purpose AI agent framework supporting autonomous task planning, tool use, and code execution for building self-directed AI assistants.

Blades is a Go-based multimodal AI agent framework from the Kratos team, supporting vision, voice, and text interactions with built-in agent orchestration, tool calling, and memory management.

An open-source, code-first Go toolkit by Google for building, evaluating, and deploying sophisticated AI agents with flexible tool integration, multi-turn conversation management, and streaming responses.

Google ADK Java is Google's Java toolkit for building, evaluating, and deploying sophisticated AI agents, filling the agent framework gap in the Java ecosystem.

Google Agent Development Kit (ADK) is Google's agent development framework for building complex AI agent systems with tool integration and multimodal processing capabilities.

Official Google Gemini fullstack quickstart using LangGraph. Complete React + Python implementation for building production AI agent applications.

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent with long-term memory and task tracking.

Griptape is a modular framework for building and deploying AI agents, supporting toolchains, memory, and multi-model integration.

A flexible multi-interface AI agent framework supporting reasoning, tool use, memory, deep research, blockchain interaction, and MCP protocol, capable of building agent applications ranging from simple conversations to complex research tasks.

The first full-stack open-source self-evolving general AI agent, offering a fully local alternative to agentic platforms like Manus and Genspark AI with autonomous thinking, task planning, tool usage, and knowledge accumulation.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs. Supports LoRA, QLoRA, RLHF and more for building custom agent models.

CLI-Anything aims to make all software agent-native by transforming applications into unified CLI interfaces, enabling AI agents to naturally interact with and operate any software through a centralized CLI Hub.

OpenHarness is an open agent harness platform with a built-in personal agent called Ohmo, providing an integrated solution for agent development, testing, and deployment.

OpenSpace is a platform that makes your agents smarter, lower-cost, and self-evolving, optimizing agent architectures and reasoning workflows for efficient autonomous evolution.

A research-agent service example from the DeepLearning.AI Agentic Workflow course, demonstrating core patterns for agentic workflows.

Hugging Face's official Agents Course covering fundamentals, frameworks (LangChain, LlamaIndex), and hands-on projects from beginner to advanced level.

smolagents is a lightweight agent framework from Hugging Face for quickly building tool-using LLM agents.

Build agents that monitor and act on your behalf. Create automated agents for Twitter, weather monitoring, web scraping, and many other scenarios.

Bee Agent Framework is a production-ready AI agent development framework supporting both Python and TypeScript, offering multi-modal agent building, tool integration, and observability capabilities for rapid production deployment.

An agentic framework for reflective PowerPoint generation that automates slide creation, content arrangement, and visual design.

Inkeep’s agent platform for creating AI assistants and multi-agent workflows through a no-code visual builder or TypeScript SDK.

A universal CLI Hub and AI-native runtime that transforms any website, Electron app, or local binary into a standardized command-line interface built for AI agents.

Open-source local realtime voice AI system supporting fully offline real-time voice conversations, suitable for building private voice assistants and voice interaction applications.

OxyGent is an open-source multi-agent collaboration framework from JD.com, supporting flexible agent role definition, task decomposition, and collaborative orchestration for enterprise AI agent applications.

Julep is a serverless AI workflow deployment platform for building and scaling AI agent applications, described as Firebase for AI agents.

KaibanJS is a JavaScript-native multi-agent framework with a Kanban-inspired approach for managing agent collaboration, supporting task assignment, role definition, and parallel execution for rapid multi-agent system development.

AI research automation agent by Andrej Karpathy that automatically runs nanochat training research experiments on a single GPU.

KubeAI is a Kubernetes-native AI inference operator that makes it easy to serve ML models in production, supporting LLMs, VLMs, embeddings, and speech-to-text with autoscaling.

Agent harness built with LangChain and LangGraph. Equipped with a planning tool, filesystem backend, and ability to spawn subagents for complex agentic tasks.

LangGraph is an agent workflow orchestration framework from the LangChain team, using graph structures to model agent state and transitions.

LangChain is a framework for building applications powered by language models. It provides core capabilities such as chaining, memory management, and agent orchestration, making it a go-to choice for AI agent development.

LangChain4j is a Java library that simplifies LLM integration through a unified API, supporting popular models and vector databases with built-in RAG, tool calling, MCP, and agent capabilities that integrate seamlessly with enterprise Java frameworks.

Langflow is a visual AI agent and workflow builder platform with drag-and-drop design, multi-LLM integration, and tool composition to simplify agent development.

Dify is an open-source LLM application development platform with a visual agent orchestration interface, supporting workflows, knowledge bases, and multiple models.

LangGraph for Java — a library for developing AI agentic architectures in the Java ecosystem, designed to work seamlessly with both LangChain4j and Spring AI, supporting stateful graph-based workflows and complex agent orchestration.

Langroid is a Python multi-agent programming framework that leverages an intuitive Agent-Task-Tool abstraction to help developers build LLM-powered multi-agent applications.

An AI agent framework built with Rust focusing on performance and security. Supports MCP protocol integration, composable toolchains, and distributed agent execution.

Letta (formerly MemGPT) is an open-source framework for building stateful AI agents with advanced reasoning and transparent long-term memory. It allows you to visually test, debug, and observe agents.

A multi-agent framework written in Rust for building, deploying, and coordinating multiple intelligent agents, designed for high performance and memory safety in latency-sensitive production systems.

LiveKit Agents is LiveKit's real-time voice and multimodal agent framework for phone, assistant, and interactive use cases that need low-latency experiences.

Official LiveKit Python voice agent starter template, demonstrating real-time voice AI agent construction with speech recognition, synthesis, and NLU.

Official LiveKit React voice agent starter template, demonstrating how to build real-time voice interactive AI agents with LiveKit Agents framework.

Open source real-time audio/video infrastructure for AI agents. WebRTC transport, agent framework, SIP telephony, and real-time transcription.

A hands-on Java and Spring AI project for building AI agents with RAG, tool calling, MCP, and ReAct-style autonomous planning.

llmware is a unified enterprise RAG framework for deploying small specialized models, featuring knowledge graphs, document parsing, vector indexing, and agent toolchains for building private, compliant AI applications.

A self-evolving agent framework that grows a skill tree from a 3.3K-line seed, achieving full system control with 6x less token consumption.

Mastra is a TypeScript-first agent platform that combines workflows, memory, RAG, evaluation, and deployment for scalable full-stack AI agent applications.

Self-hosted, always-on AI agent platform running in containers. Create multiple bots with long-term memory and connect them to Telegram, Discord, Feishu, Matrix, and more.

Microsoft's comprehensive multi-language framework for building, orchestrating, and deploying AI agents and multi-agent workflows with support for Python and .NET.

12 Lessons to Get Started Building AI Agents by Microsoft. Hands-on curriculum covering core agent concepts, tool use, and multi-agent collaboration.

Microsoft's R&D automation agent focused on data-driven and model-driven AI development processes, automating high-value R&D to enhance industrial productivity.

Microsoft Semantic Kernel is a lightweight SDK for combining large language models with conventional programming languages to build AI agent applications.

TaskWeaver is Microsoft's open-source code-interpreter-style agent framework, suitable for data analysis and complex task automation.

Mirascope is a lightweight LLM development library that takes a type-safe, Pythonic approach to building LLM applications, emphasizing simplicity over framework constraints.

Smart model routing for personal AI agents that cuts costs up to 70% by dynamically selecting the optimal LLM for each request.

A production-ready AI agent framework with tool calling, persistent memory, intelligent concurrency, and event-driven observability.

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, and MCP tools.

Motia is a TypeScript platform that models APIs, background jobs, agents, and workflows together for teams that want one structure for business logic and automation.

Powerful, self-hostable AI agent platform designed for maximum privacy and flexibility. A complete drop-in replacement for OpenAI Responses APIs running locally on consumer-grade hardware.

A simple general-purpose AI agent based on the OpenAI API, ideal for learning and rapid prototyping of autonomous agents.

The Application Engine for the AI Era. Multi-threaded, AI-native runtime with persistent Scene Graph for real-time agent introspection.

Neuron AI is a PHP agentic framework for building production-ready AI applications, enabling developers to connect LLMs, vector databases, and memory systems to create agents that interact with data.

An autonomous AI agent framework from NousResearch that supports multiple LLM backends and grows with user needs.

OctoTools is an agentic framework with extensible tools for complex reasoning, featuring a tool card system for flexible composition of diverse reasoning capabilities.

GitAgent is a framework-agnostic, git-native standard for defining AI agents where identity, rules, memory, tools, and skills are version-controlled files in a Git repository, enabling reproducible and collaborative agent development.

Open Lovable is an open-source experimental project for conversational app generation, combining agent-style interaction, generative UI, and rapid prototyping.

OpenAI Agents JS is the JavaScript version of the OpenAI Agents SDK, bringing tool calling, state orchestration, and runtime interfaces to JS/TS web stacks.

A lightweight, powerful framework from OpenAI for building multi-agent workflows with tool calling, agent handoffs, and guardrails.

OpenAI Agents SDK is OpenAI's official agent development toolkit, supporting the building of multi-step workflow AI agents with core features like tool calling and state management.

A demonstration of advanced agentic patterns built on top of OpenAI's Realtime API, showcasing real-time voice interaction and multi-agent collaboration.

An autonomous LLM agent framework for complex task solving with automatic task decomposition, tool usage, and multi-step reasoning from the OpenBMB team

An AI agent framework focused on agent collaboration, featuring a clean API design and documentation-driven development approach, supporting task decomposition, coordination, and result aggregation across multiple agents.

OpenRLHF is a high-performance agentic RL framework based on Ray and vLLM, offering PPO, DAPO, and REINFORCE++ algorithms for large-scale training of agents and vision-language models.

OpenRouter Agents is OpenRouter's platform capability for multi-model agent use cases, focused on routing, tool calling, and unified access layers.

Native macOS harness for AI agents with any model, persistent memory, autonomous execution, and cryptographic identity. Fully offline.

A comprehensive tutorial repository for learning AI agent development, covering OpenAI Agents SDK, LangGraph, MCP protocol, and more with hands-on projects.

Agentic AI framework for enterprise workflow automation. Uses LLM-powered pipelines for code reviews, DevOps, and other enterprise tasks.

Phidata is a framework for building AI agents with memory, knowledge, and tool integration to make agents more capable and useful.

PydanticAI builds agents on top of type systems, emphasizing verifiable data structures, tool calling, and production-grade reliability.

Rivet Actors are the primitive for stateful workloads. Built for AI agents, collaborative apps, and durable execution.

The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code/Codex integration.

ROMA (Recursive-Open-Meta-Agent) is a meta-agent framework for building high-performance multi-agent systems with recursive task decomposition and coordination.

AutoGPT is an autonomous AI agent that can complete user-defined tasks end-to-end. It plans and executes steps on its own and is considered a milestone in agent autonomy.

An application framework for AI engineering from the Spring team, providing unified LLM integration, vector storage, function calling, RAG, and agent development for Java and Spring ecosystems with support for OpenAI, Anthropic, Ollama, and more.

An open source autonomous agent built in Rust that lives on your machines 24/7 and keeps your apps running on autopilot.

Arrow is the first UI framework for the agentic era, tiny and performant with built-in WASM sandboxes for safe code execution, purpose-built for building AI agent interfaces.

DSPy is a declarative LLM programming framework focused on optimizable prompts and program structure, suitable for complex agent workflows.

Strands Agents SDK is an AWS open-source agent framework using a model-driven approach to build AI agents with built-in tool use, conversation memory, and multi-agent collaboration.

GPT Researcher is an autonomous research agent that can gather, organize, and analyze information to produce detailed research reports.

Tencent's open-source LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG.

AppAgent is an LLM-based multimodal agent framework designed to operate smartphone apps like a human, supporting touch interaction and autonomous exploration.

Next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent capabilities.

A reactive runtime for building durable AI agents, written in Rust for high reliability and persistence.

LangChainGo is the Go implementation of LangChain, providing the easiest way to write LLM-based programs in Go with chains, agents, and tool integrations.

trpc-agent-go is a powerful Go framework for building intelligent agent systems with LLM integration, tool calling, multi-step reasoning, and workflow orchestration, designed for enterprise-grade agent systems in microservice architectures.

Deep-dive research reports on AI Agent source code — systematic analysis of mainstream AI agent framework architectures, core principles, and implementation details.

The AI Toolkit for TypeScript by the Next.js creators. Build AI-powered applications and agents with streaming, tool use, multimodal, and agent orchestration.

An autonomous agent for deep financial research. Automatically analyzes financial reports, market data, company filings, generates investment recommendations and risk assessment reports.

VoltAgent is an agent platform for the modern TypeScript ecosystem, focused on workflows, tool orchestration, and application integrations for production web agents.

A Pydantic AI framework for Claude Code-style deep agents with tool calling, sandboxed execution, multi-agent teams, skills, checkpoints, and extended context.

Lightweight AI agent framework with built-in memory, tool calling, and tree-of-thought reasoning, supporting multi-agent collaboration and self-learning, compatible with OpenAI, DeepSeek, Qwen, and other major LLMs with MCP/SSE protocol integration.

Agentica is a TypeScript AI function calling framework enhanced by compiler skills, using type-safe schemas to auto-generate function calls and boost LLM tool-use capabilities for reliable AI agent backends.

Intelligent automation and multi-agent orchestration for Claude Code. Supports automated workflows, task coordination, and intelligent agent system building.

A general-purpose Java agent built with Spring Boot, Spring AI, RAG, tool calling, and MCP, supporting multi-turn dialogue and persistent memory.

Open-source AI Agent platform that brings Local Manus to your desktop — one-click model downloads, seamless LLM integration, offline RAG knowledge bases, and DeepResearch capabilities with 100% local data.

An agent framework connecting digital humans (2.5D/3D/mobile/web) with business systems, compatible with OpenAI and DeepSeek LLMs.

YoMo is a serverless AI Agent framework built on geo-distributed edge AI infrastructure, using low-latency stream processing for real-time agent orchestration and MCP tool integration, ideal for edge computing agent deployments.

Open-AutoGLM is an open phone agent model and framework enabling AI to autonomously operate smartphone interfaces, unlocking the AI Phone experience for everyone.

Fast, small, and fully autonomous AI personal assistant infrastructure built with Rust. Deploy anywhere, swap anything, on any OS and platform.

CowAgent (formerly chatgpt-on-wechat) is a powerful AI assistant framework built on LLMs with autonomous planning, tool use, long-term memory, multi-agent collaboration, and multi-channel integration for WeChat, Feishu, DingTalk, and more.