An AI assistant platform from Tencent Cloud, MIT licensed, where conversations, workspaces and keys stay on your own machine and nine chat platforms route into the same set of experts.

Four layers split by depth — a no-code studio, a conversational layer, an event-driven core and an extension pack. The framework is in maintenance mode, so the honest question is whether to start on it or only keep running it.

An assistant that lives in the chat apps you already use and keeps every trace of its memory on your own disk. A non-profit foundation holds the project, there is no paid tier, and one gateway process routes 29 channels into a coding agent.

More than 300 verified programs for local AI, each packaged with its own installation script: one press brings down the models, sorts the dependencies, starts the service and opens the interface in a window, all inside its own sandbox.

A deliberately small agent library: about a thousand lines of core logic, and one opinion that shapes everything. Instead of emitting structured tool calls, the model writes a short piece of code, which the library runs and reports back. Fewer steps, fewer calls, and source short enough to actually read.

An agent that runs on your own machine and does the work rather than describing it: reading files, changing code, running commands and continuing from the output. Desktop application, command line and an interface for embedding, more than seventy extensions, and workflows you can save and reuse. Free and open source.

An open agent runtime in which models, tools, skills, sessions, sandboxes, storage and even the interface are plugins sitting at the same level, with no privileged core. Model independent, with an append-only log of every run and four ready-made modes from a full coding agent down to a minimal shell. Free and open source.