Frameworks AI agent tools
133 frameworks tools in the AgentScout directory, each with a link-checked listing.
Updated
There are 133 frameworks tools: 127 open source, 1 source-available, 2 free or freemium, 1 paid, usage-based or enterprise, 2 pricing on the maker's site.
Quick comparison Top 10 of 133 listed below. Pricing as the maker states it; blank means we don't have it.
| Tool | Pricing | Best for | Open source |
|---|---|---|---|
 eve | Open source | Build an agent | Yes |
 Sage | Open source | Build multi-agent systems | Yes |
 Agentlas | Open source | Build an agent | Yes |
 thClaws | Open source | Build an agent | Yes |
 Raven | Open source | Write code | Yes |
 Dynamiq | Open source | Build an agent | Yes |
 AWorld | Open source | Build an agent | Yes |
 Golem | Free | Build an agent | |
 AstrBot | Open source | Build an agent | Yes |
 Go Micro | Open source | Build an agent | Yes |
Tasks in this category
Showing 133 of 133 tools
eve
Vercel's open-source agent framework, pitched as Next.js for agents: a file-system-based way to define an agent's tools, prompts and workflows and run it in production.
Added
Sage
Sage is an MIT-licensed framework for building configurable, self-improving AI agents from reusable agent packages, tools, Skills and MCP services. It supports multi-agent workflows and multi-round self-improvement, keeping a version history of agent packages so you choose which version to adopt.
Added
Agentlas
A local-first agent OS that keeps specialist agents in a hub and spins up a temporary orchestrator for each task, with reusable methods and your choice of model and host.
Added
thClaws
An open-source AI agent workspace in native Rust that runs locally as a GUI, CLI, headless service or web app from a single binary, with multiple model providers.
Added
Raven
Host agent that plans complex jobs as task graphs and coordinates built-in and third-party agents for research, coding, design and on-call work.
Added
Dynamiq
Python orchestration framework for building agentic and RAG applications from reusable nodes and workflows.
Added
AWorld
Agent harness from inclusionAI for building expert agents that search, reproduce and improve on ideas with their own tools and memory.
Added
Golem
Agent-native platform for building durable agents and distributed apps that keep state and never duplicate work after a failure.
Added
AstrBot
Open-source agent chatbot platform and framework that connects LLMs, plugins and tools to mainstream messaging apps for assistants, support bots and knowledge bases.
Added
Go Micro
Go framework for distributed systems where services double as tools for AI agents, with RPC, discovery, messaging and agent workflows.
Added
Agents CLI
Google's CLI and skills that teach coding assistants to build, evaluate and deploy agents on Google Cloud and the Gemini platform.
Added
Apache Maka
Incubating Apache agent harness and workspace that records everything it does and publishes benchmarked run results.
Added
FrontierAgent
Open-source agent runtime and terminal app for long-horizon research and file work, with single-agent ReAct and parallel agent-team modes.
Added
Atmosphere
Real-time AI agent runtime for the JVM that runs one agent class on Spring AI, LangChain4j and other backends with streaming, MCP, A2A and AG-UI.
Added
Antigravity SDK
Google's Python SDK for building stateful AI agents powered by Antigravity and Gemini, abstracting the agent loop and runtime.
Added
BeeAI Framework
Framework for building production-ready agents and multi-agent systems in Python or TypeScript.
Added
II-Agent
Open-source AI agent for real work from Intelligent Internet that you can run, fork and extend with your own API keys.
Added
EvoAgentX
Framework for building, evaluating and automatically evolving LLM agents and agentic workflows.
Added
Cheshire Cat
Open-source AI agent microservice designed to be easy to understand and extend, with plugins and memory.
Added
OpenGAP
Framework-agnostic, git-native standard and CLI for defining AI agents so a repository becomes a runnable agent.
Added
Workflow SDK
Vercel's TypeScript SDK for building durable, reliable and observable apps and AI agents.
Added
agentUniverse
Multi-agent framework with reusable collaboration patterns for building LLM agent applications.
Added
Neuron AI
PHP framework for creating and orchestrating AI agents with LLMs, tools, vector stores and memory.
Added
LangGraph4j
Java library for building stateful multi-agent applications as graphs, working with LangChain4j and Spring AI.
Added
Langchain.rb
Ruby library for building LLM-powered applications, RAG and assistants.
Added
PrivateGPT
Open-source API layer that turns local models into private AI applications, with RAG, tools, skills, MCP and text-to-SQL on any OpenAI-compatible server.
Added
DSPy
Stanford framework for programming rather than prompting language models, with optimizers that tune prompts and weights for RAG pipelines and agent loops.
Added
ChatDev
Zero-code multi-agent platform from OpenBMB, grown from a software-development agent company into a general multi-agent orchestration system.
Added
Guidance
Programming paradigm for steering language models that constrains output with regex and grammars and interleaves control flow with generation.
Added
RocketRide
AI pipeline engine with a C++ core and 50+ Python nodes for building, debugging and deploying LLM workflows and agents from VS Code or the CLI.
Added
Outlines
Library from .txt for structured generation that guarantees LLM output matches a JSON schema, regex or grammar.
Added
Instructor
Library for getting validated structured outputs from any LLM, built on Pydantic with retries and type safety.
Added
BAML
Typed programming language for agents and LLM functions, with runtime types, typed errors and structured outputs designed to reduce agent mistakes.
Added
TypeChat
Microsoft library for building natural-language interfaces by using types to constrain and validate LLM responses.
Added
Claude Agent SDK (Python)
Anthropic's Python SDK for building agents on Claude Code's agent loop, with the CLI bundled, custom tools and hooks.
Added
AIOS
Research AI agent operating system that handles scheduling, context switching, memory, storage and tool management for LLM-based agents.
Added
Agency Swarm
Multi-agent orchestration framework built on the OpenAI Agents SDK for creating collaborating agent "agencies" with defined roles.
Added
MS-Agent
ModelScope's modular agent framework for complex, long-running tasks that combines models, tools, skills and sub-agents in a customizable harness.
Added
Lagent
Lightweight PyTorch-inspired framework from InternLM for building LLM-based agents.
Added
tRPC-Agent-Go
Go framework for production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation and OpenTelemetry.
Added
KaibanJS
JavaScript-native framework for building and managing multi-agent systems with a Kanban-style board for agent tasks.
Added
Adala
HumanSignal's autonomous data-labeling agent framework, where agents learn labeling skills iteratively.
Added
assistant-ui
Open-source React components and runtimes for building AI chat and agent front ends with streaming, tools and persistence.
Added
Agent Zero
Open-source agentic framework and computer assistant whose agents use their own OS environment, create tools and self-correct.
Added
Restack
Platform for designing, testing and running reliable agents at enterprise scale on Kubernetes.
Added
OpenUI
Framework-agnostic generative UI framework with a compact streaming language and runtimes for React, Vue, Svelte and Angular.
Added
BaseAI
Web AI framework from Langbase for building AI agents with memory (RAG) and deploying them serverless.
Added
AMD GAIA
AMD's open-source toolkit for building AI agents that run locally on Ryzen AI PCs, keeping data on the device.
Added
Jido
Elixir framework for building supervised, fault-tolerant agents and multi-agent systems on the BEAM.
Added
Mirascope
Lightweight Python library for calling any LLM with typed outputs and tools through one interface, without a heavy framework.
Added
DeepSeek Harness
DeepSeek's open-source agent harness with a local web UI, built so that every tool, model and scheduled task is a swappable plugin; still a developer preview.
Added
Agent Lightning
Microsoft's lightweight trainer that improves existing agents with reinforcement learning through a model proxy, without rewriting the agent's tools or control flow.
Added
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.
Added
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).
Added
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.
Added
Hermes Agent (Nous Research)
Open-source agent harness; v0.21.7 stable shipped Oct 12, v0.22.0 RCs Oct 13-14.
Added
OpenAI Agents SDK (Python)
OpenAI's Python SDK for building multi-agent workflows; v0.23.0/0.23.1 released Oct 1-2.
Added
LangChain Deep Agents
Library for long-running agents with subagents and skills; 0.7.23 (Oct 7) adds pinned_skills.
Added
LangGraph
Framework for stateful, graph-based agent workflows.
Added
CrewAI
Framework for role-based multi-agent crews.
Added
AutoGen
Microsoft's framework for multi-agent conversations, now archived and no longer maintained; Microsoft points new users to Microsoft Agent Framework.
Added
Pydantic AI
Type-safe Python agent framework from the Pydantic team.
Added
Google ADK
Google's Agent Development Kit for building and deploying agents.
Added
Mastra
TypeScript framework for agents, workflows and RAG.
Added
smolagents
Hugging Face's minimal library for code-writing agents.
Added
LlamaIndex
Framework for agents over your data (RAG, document agents).
Added
Vercel AI SDK
TypeScript toolkit for building AI apps and agents.
Added
Letta
Framework for stateful agents with long-term memory (formerly MemGPT).
Added
AutoGPT
One of the first autonomous agent projects, now a platform for building, deploying and running continuous AI agents that automate workflows.
Added
BabyAGI
Yohei Nakajima's experimental self-building agent framework that creates, stores and runs its own functions.
Added
Lyzr
Enterprise agent studio and framework for building secure AI agents.
Added
MetaGPT
Multi-agent framework that assigns roles like product manager and engineer to LLM agents to build software.
Added
OpenPipe
Reinforcement learning tooling, including the ART library, to train better agents.
Added
Orkes
Orchestration platform built on Conductor for durable workflows and AI agents.
Added
Prime Intellect
Decentralized compute and open RL environment hub for training agentic models.
Added
Viam
Software platform for building and operating robots and smart machines.
Added
Agno
Python framework and runtime for building, running and managing multi-agent systems with memory, knowledge and tools.
Added
OpenHuman
Lightweight open-source agent harness designed to run many agents cheaply on small servers.
Added
CopilotKit
Frontend stack for putting agents and generative UI into React and other apps, from the makers of the AG-UI protocol.
Added
AgentScope
Framework for building and running transparent multi-agent applications with visual debugging.
Added
Haystack
Open-source orchestration framework for building production LLM apps, RAG and agents.
Added
A2A
Agent2Agent, an open protocol for agents built on different frameworks to communicate and work together.
Added
Parlant
Framework for building reliable customer-facing agents with explicit behavior guidelines.
Added
OpenFang
Open-source agent operating system for running autonomous agents.
Added
AG-UI
Agent-User Interaction protocol for streaming agent state and events into frontend apps.
Added
Trigger.dev
Platform for building and deploying durable background AI agents and workflows in TypeScript.
Added
Microsoft Agent Framework
Microsoft's framework for building and orchestrating agents and multi-agent workflows in Python and .NET.
Added
PocketFlow
Minimalist 100-line LLM framework for building agents and workflows.
Added
Tambo
Generative UI SDK for React that lets agents render components.
Added
Aden Hive
Multi-agent harness for production AI.
Added
Spring AI Alibaba
Agentic AI framework for Java developers built on Spring AI.
Added
Omnigent
Open-source agent framework and meta-harness that orchestrates Claude Code, Codex, Cursor and other agents together.
Added
VoltAgent
TypeScript agent framework plus an engineering platform for building, observing and deploying AI agents.
Added
PraisonAI
Multi-agent framework for building a self-improving AI workforce with little code.
Added
Strands Agents
Strands open-source SDK for building production agent harnesses in Python and TypeScript.
Added
Evolver
Self-evolving engine for AI agents with auditable genes, capsules and events.
Added
Upsonic
Python framework for building autonomous AI agents.
Added
Agent Squad
Framework for routing conversations across multiple specialized AI agents.
Added
Flyte
Type-safe orchestration for agents, ML pipelines and inference on Kubernetes.
Added
OpenEvolve
Open-source take on AlphaEvolve that uses LLM agents to evolve better code and algorithms.
Added
Swarms
Enterprise multi-agent orchestration framework.
Added
Open Multi-Agent
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records.
Added
Julep
Platform for durable AI agent workflows that can crash, resume and retry safely.
Added
Genkit
Google's open-source framework for building agentic apps in JavaScript, Go, Dart and Python.
Added
IntentKit
Self-hosted cloud cluster for running a team of collaborating AI agents.
Added
TrueForge
Open-source agent harness runtime that turns an LLM into a working agent.
Added
Marvin
Python library from Prefect for building AI agents and structured LLM workflows.
Added
AgentScope Java
Java version of AgentScope for building distributed, long-running agents.
Added
Open Agents
Vercel's open-source template for building cloud agents.
Added
Cloudflare Agents
Cloudflare's SDK for building and deploying stateful AI agents on Workers.
Added
AReaL
Reinforcement learning system for training LLM-based agents.
Added
ZenML
MLOps and agent platform for building pipelines and deploying agents.
Added
AG2
AG2, the community continuation of AutoGen, an open-source framework for multi-agent systems.
Added
Koog
JetBrains' Kotlin framework for building predictable, enterprise-ready AI agents on the JVM.
Added
Docker Agent
Docker's agent builder and runtime for defining and running agents.
Added
Agent Service Toolkit
Toolkit for running an agent service with LangGraph, FastAPI and Streamlit.
Added
Embabel
Agent framework for the JVM from the creator of Spring.
Added
RubyLLM
Ruby framework for working with LLMs, including chat, tools and agents, through one API.
Added
Dagu
Self-hostable workflow orchestrator with a simple definition format and web UI, usable for agent jobs.
Added
DocETL
System for agentic, LLM-powered document processing and ETL pipelines from UC Berkeley.
Added
Langroid
Python framework for multi-agent programming with LLMs.
Added
kagent
Cloud-native framework for running AI agents on Kubernetes.
Added
fast-agent
Framework to build, run and evaluate agents with strong MCP, ACP and A2A support.
Added
LazyLLM
Low-code framework for building multi-agent LLM applications.
Added
TanStack AI
Type-safe, provider-agnostic TypeScript SDK for chat, tool calling and agents.
Added
BotSharp
Multi-agent framework for .NET.
Added
Ax
DSPy-style framework for building LLM programs and agents in TypeScript.
Added
RAGEN
Reinforcement learning framework for multi-turn LLM agents.
Added
AgentField
Build, run and scale AI agents like APIs and microservices.
Added
Agentic Context Engine
Engine that lets agents learn from their own experience.
Added
IBM CUGA
IBM Research's configurable generalist agent (CUGA) for enterprise web and API tasks, with a live demo on Hugging Face Spaces.
Added
AgentFlow
Stanford's trainable agentic system where planner, executor, verifier and generator modules coordinate, with a Hugging Face demo.
Added
CAMEL
CAMEL, one of the first multi-agent frameworks, for building role-playing agents and large agent societies.
Added
Top frameworks repos on GitHub (130)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| Hermes Agent (Nous Research) ↗ | 253,590 | MIT | 2026-10-21 |
| DeepSeek Harness ↗ | 251,853 | MIT | 2026-10-17 |
| AutoGPT ↗ | 187,612 | MIT outside the autogpt_platform folder; the platform is under the Polyform Shield | 2026-10-19 |
| Ruflo ↗ | 74,609 | MIT | 2026-10-21 |
| MetaGPT ↗ | 70,885 | MIT | 2026-01-21 |
| AutoGen ↗ | 61,395 | MIT for code (LICENSE-CODE); CC-BY-4.0 for documentation | 2026-10-16 |
| CrewAI ↗ | 59,675 | MIT | 2026-10-21 |
| PrivateGPT ↗ | 57,594 | Apache License 2.0 | 2026-10-20 |
| LlamaIndex ↗ | 52,485 | MIT | 2026-10-14 |
| LangGraph ↗ | 43,237 | MIT | 2026-10-21 |
| Agno ↗ | 42,769 | Apache License 2.0 | 2026-10-21 |
| OpenHuman ↗ | 42,113 | GNU GPL v3.0 | 2026-10-21 |
| AstrBot ↗ | 42,095 | GNU Affero General Public License v3.0 | 2026-10-21 |
| DSPy ↗ | 38,676 | MIT | 2026-10-20 |
| CopilotKit ↗ | 38,064 | MIT | 2026-10-20 |
Top 15 of 130 by stars. Stars and licence come from each repo, checked when the listing was last verified.
All categories
Related searches
Who uses these
Best-of lists
Alternatives pages
Task guides
Free tools for this: Agent run cost estimator · Tool schema builder · System prompt linter
Facts come from our directory listings; pricing is as each maker states it. Check official sites before you choose.