
AG2 is an open-source Python framework for developers and researchers building systems where AI agents share work. The code uses the Apache 2.0 license.
Agents can call Python tools to work with external data, APIs and functions. Workflows can run autonomously or pause for a person to approve an action or supply missing information. A2A and MCP support provide connections to other agents and tools, while shared state carries context across a task's lifecycle.
Multi-agent coordination uses a Network with a central hub and channels for conversations, consultations, group discussions and conditional handoffs. The hub keeps an audit trail. This gives developers a choice between open-ended agent exchanges and workflows with defined transitions.
For longer-running work, agents can retain knowledge between runs and summarize conversation history as it grows. Structured outputs, telemetry, evaluation and testing support help developers check what their agents produce and how they behave.
AG2 is distinct from AG2 Classic, the maintained AutoGen-derived framework. Classic retains the older agent classes and group-chat patterns; the current framework uses a different agent model and isn't a drop-in replacement.
Claim this page with an email at ag2.ai. AG2 gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find AG2?Promote it
Something wrong or outdated on this page?
24.8KUpdated 1 day ago
Docker · Web#Code execution#Human approval#MCP
Activepieces brings AI agents and workflow automation into one workspace for teams that need to connect their apps and internal data. It runs on your own servers with Docker or Kubernetes, or as a managed cloud service. An isolated deployment can keep platform data on its own infrastructure; connected apps and model providers may still require external access. Its core and app integration pieces are MIT-licensed.
42.4KUpdated 1 day agoApache-2.0
Docker · Web#Guardrails#Human approval#LLM tracing
10.5KUpdated 7 months agoApache-2.0
macOS · Windows · Linux · Android · Web#Code execution#MCP#Multimodal input
41.2KUpdated 1 day agoAGPL-3.0
macOS · Docker · Web#Code execution#Hybrid search#LM Studio integration
61.2KUpdated 6 months agoCC-BY-4.0
Web#Code execution#MCP#Multi-agent workflows
3.1KUpdated 2 days agoApache-2.0
macOS · Windows · Linux · Web#Code execution#MCP#Multi-agent workflows
Agno is a Python framework and runtime for developers building customer-facing or internal AI agents. You can run its agent platform locally with Docker, on your own servers or in your cloud. The open-source framework uses the Apache 2.0 license, and the platform keeps sessions, memory, knowledge and traces in your database.
aichat brings Ollama and cloud AI services into the same terminal interface for developers and people who work at the command line. It runs locally on macOS, Linux and Windows, with Android support through Termux. Model processing happens through the backend you choose: Ollama supports local models, while providers such as OpenAI, Claude and Gemini process requests in the cloud.
AstrBot brings AI assistants into messaging apps such as Telegram, Discord, Slack, QQ and WeCom. It's an open source platform under AGPL-3.0 for people building personal companions, customer support bots or team automation. You can run it on your own computer or server, including through Docker, or use its desktop app for browser-style chat.
AutoGen is a framework for developers building AI agents that work together or alongside people. Its agent runtime can run locally or across distributed systems, while model integrations such as OpenAI and Azure OpenAI send requests to external services. It's community-managed and in maintenance mode, with no further features or enhancements planned.
BotSharp is a self-hosted framework for .NET developers building AI agents into business applications. Written in C#, it runs on Windows, Linux and macOS and is open source software under Apache 2.0. Its plugin design lets teams choose their model provider, storage and interface while keeping agent coordination in the same framework.