Frameworks AI agent tools
84 frameworks tools in the AgentScout directory, each with a link-checked listing.
AutoGPT
One of the first autonomous agent projects, now a platform for building, deploying and running continuous AI agents that automate workflows.
BabyAGI
Yohei Nakajima's experimental self-building agent framework that creates, stores and runs its own functions.
Lyzr
Enterprise agent studio and framework for building secure AI agents.
MetaGPT
Multi-agent framework that assigns roles like product manager and engineer to LLM agents to build software.
OpenPipe
Reinforcement learning tooling, including the ART library, to train better agents.
Orkes
Orchestration platform built on Conductor for durable workflows and AI agents.
Prime Intellect
Decentralized compute and open RL environment hub for training agentic models.
Viam
Software platform for building and operating robots and smart machines.
RAGFlow
Open-source RAG engine with deep document parsing and agent features for building grounded question-answering over your files.
Agno
Python framework and runtime for building, running and managing multi-agent systems with memory, knowledge and tools.
OpenHuman
Lightweight open-source agent harness designed to run many agents cheaply on small servers.
PageIndex
Document index for reasoning-based, vectorless RAG that lets agents navigate long documents like a table of contents.
CopilotKit
Frontend stack for putting agents and generative UI into React and other apps, from the makers of the AG-UI protocol.
AgentScope
Framework for building and running transparent multi-agent applications with visual debugging.
Haystack
Open-source orchestration framework for building production LLM apps, RAG and agents.
A2A
Agent2Agent, an open protocol for agents built on different frameworks to communicate and work together.
Parlant
Framework for building reliable customer-facing agents with explicit behavior guidelines.
OpenFang
Open-source agent operating system for running autonomous agents.
AG-UI
Agent-User Interaction protocol for streaming agent state and events into frontend apps.
Trigger.dev
Platform for building and deploying durable background AI agents and workflows in TypeScript.
Microsoft Agent Framework
Microsoft's framework for building and orchestrating agents and multi-agent workflows in Python and .NET.
PocketFlow
Minimalist 100-line LLM framework for building agents and workflows.
Tambo
Generative UI SDK for React that lets agents render components.
Aden Hive
Multi-agent harness for production AI.
Spring AI Alibaba
Agentic AI framework for Java developers built on Spring AI.
Omnigent
Open-source agent framework and meta-harness that orchestrates Claude Code, Codex, Cursor and other agents together.
VoltAgent
TypeScript agent framework plus an engineering platform for building, observing and deploying AI agents.
PraisonAI
Multi-agent framework for building a self-improving AI workforce with little code.
Strands Agents
Strands open-source SDK for building production agent harnesses in Python and TypeScript.
Evolver
Self-evolving engine for AI agents with auditable genes, capsules and events.
Upsonic
Python framework for building autonomous AI agents.
Agent Squad
Framework for routing conversations across multiple specialized AI agents.
Flyte
Type-safe orchestration for agents, ML pipelines and inference on Kubernetes.
OpenEvolve
Open-source take on AlphaEvolve that uses LLM agents to evolve better code and algorithms.
Swarms
Enterprise multi-agent orchestration framework.
Open Multi-Agent
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records.
Julep
Platform for durable AI agent workflows that can crash, resume and retry safely.
Genkit
Google's open-source framework for building agentic apps in JavaScript, Go, Dart and Python.
IntentKit
Self-hosted cloud cluster for running a team of collaborating AI agents.
TrueForge
Open-source agent harness runtime that turns an LLM into a working agent.
Marvin
Python library from Prefect for building AI agents and structured LLM workflows.
AgentScope Java
Java version of AgentScope for building distributed, long-running agents.
Open Agents
Vercel's open-source template for building cloud agents.
Cloudflare Agents
Cloudflare's SDK for building and deploying stateful AI agents on Workers.
AReaL
Reinforcement learning system for training LLM-based agents.
ZenML
MLOps and agent platform for building pipelines and deploying agents.
AG2
AG2, the community continuation of AutoGen, an open-source framework for multi-agent systems.
Koog
JetBrains' Kotlin framework for building predictable, enterprise-ready AI agents on the JVM.
Docker Agent
Docker's agent builder and runtime for defining and running agents.
Agent Service Toolkit
Toolkit for running an agent service with LangGraph, FastAPI and Streamlit.
Embabel
Agent framework for the JVM from the creator of Spring.
RubyLLM
Ruby framework for working with LLMs, including chat, tools and agents, through one API.
Dagu
Self-hostable workflow orchestrator with a simple definition format and web UI, usable for agent jobs.
DocETL
System for agentic, LLM-powered document processing and ETL pipelines from UC Berkeley.
Langroid
Python framework for multi-agent programming with LLMs.
kagent
Cloud-native framework for running AI agents on Kubernetes.
fast-agent
Framework to build, run and evaluate agents with strong MCP, ACP and A2A support.
LazyLLM
Low-code framework for building multi-agent LLM applications.
TanStack AI
Type-safe, provider-agnostic TypeScript SDK for chat, tool calling and agents.
BotSharp
Multi-agent framework for .NET.
Ax
DSPy-style framework for building LLM programs and agents in TypeScript.
RAGEN
Reinforcement learning framework for multi-turn LLM agents.
AgentField
Build, run and scale AI agents like APIs and microservices.
Agentic Context Engine
Engine that lets agents learn from their own experience.
Agentset
Open-source RAG platform for building agents and apps that answer accurately from your documents.
IBM CUGA
IBM Research's configurable generalist agent (CUGA) for enterprise web and API tasks, with a live demo on Hugging Face Spaces.
AgentFlow
Stanford's trainable agentic system where planner, executor, verifier and generator modules coordinate, with a Hugging Face demo.
CAMEL
CAMEL, one of the first multi-agent frameworks, for building role-playing agents and large agent societies.
Agent-Native (Builder.io)
Open-source TypeScript framework for building agents that come with their own app UI; each action is shared by the UI, agent, API, CLI, MCP and A2A.
Orca Agent Engine
Open Apache-2.0 runtime to build, run, and govern managed agents with choice of harness (Claude Agent SDK, Codex, Pi) and model; open-sourced Oct 6, 2026 (Developer Preview).
Ruflo
Open-source multi-agent meta-harness for Claude Code, Codex, and MCP clients; Oct 13 release adds Mods (mission workflows) and a single control plane with human approval.
Hermes Agent (Nous Research)
Open-source agent harness; v0.21.7 stable shipped Oct 12, v0.22.0 RCs Oct 13-14.
OpenAI Agents SDK (Python)
OpenAI's Python SDK for building multi-agent workflows; v0.23.0/0.23.1 released Oct 1-2.
LangChain Deep Agents
Library for long-running agents with subagents and skills; 0.7.23 (Oct 7) adds pinned_skills.
LangGraph
Framework for stateful, graph-based agent workflows.
CrewAI
Framework for role-based multi-agent crews.
AutoGen
Microsoft's framework for multi-agent conversations.
Pydantic AI
Type-safe Python agent framework from the Pydantic team.
Google ADK
Google's Agent Development Kit for building and deploying agents.
Mastra
TypeScript framework for agents, workflows and RAG.
smolagents
Hugging Face's minimal library for code-writing agents.
LlamaIndex
Framework for agents over your data (RAG, document agents).
Vercel AI SDK
TypeScript toolkit for building AI apps and agents.
Letta
Framework for stateful agents with long-term memory (formerly MemGPT).
All categories
Facts come from our directory listings; pricing is as each maker states it. Check official sites before you choose.