Open Source Agent Frameworks
Discover 21 open source Agent Framework repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. Agent Framework projects here are most often combined with AI Agents, Python and LLM. Last updated October 3, 2026.
21 repositories · updated October 3, 2026
Agentarium: Build and Orchestrate AI Agent Simulations
Agentarium is a Python framework for creating AI agents that interact, take context-based actions, and retain memories. Use it to prototype multi-agent scenarios, add custom actions, and save agent states for repeatable experiments.
AgentStack: Scaffold AI Agent Projects
AgentStack is a Python CLI that creates and develops AI agent projects with supported frameworks, providers, and tools preconfigured. It suits developers who want a practical starting point without committing to a low-code platform or fixed stack.
harness-sdk: Build and Run AI Agents in Python and TypeScript
Strands Agents provides Python and TypeScript tools for building AI agents, from a ready-made harness to a customizable agent SDK. It suits teams that want model flexibility and control over agent execution without a hosted control plane.
agent-service-toolkit: Build and Serve LangGraph Agents
A Python starter toolkit that connects LangGraph agents to a FastAPI service, reusable client, and Streamlit chat interface. It suits developers who want an end-to-end foundation for building, testing, and customizing agent applications.
deepagents: Build Agents with Planning and Tooling Built In
Deep Agents is a Python agent harness for building LLM agents with planning, delegation, file access, and context management built in. It suits developers who need a more capable starting point than a minimal agent loop, while retaining control over models and tools.
fast-agent: Build and Run LLM Agents and Workflows
fast-agent is a Python framework and CLI for building, running, and evaluating LLM agents. It connects agents to MCP servers and supports multi-agent workflows, multiple model providers, and interactive terminal use.
Agent-S: Automate Desktop Tasks Through a GUI Agent
Agent-S is a Python framework that uses screenshots, mouse clicks, and keyboard input to carry out natural-language tasks in desktop applications. It suits research and automation workflows that need an agent to interact with a real computer interface.
agent-zero: Give AI Agents a Linux Workbench
Agent Zero is a Python framework for agents that need a working environment, not just a chat interface. It combines a Dockerized Linux desktop, browser, document editing, projects, extensions, and optional access to host-machine files.
rig: Build LLM Applications in Rust
Rig is a Rust library for building modular LLM applications, with shared interfaces for model providers, vector stores, and agent workflows. It suits Rust developers who want to integrate multiple LLM services without building each integration from scratch.