Back to directory

Yao Agents

A self-hosted platform that keeps a user's AI agents and workspaces available across desktop, mobile, browser and API, tracking tasks on a shared board.

Yao Agents

Yao Agents keeps a user's agents and workspaces in one place, accessible from every device they own, tracking tasks on a board reachable from desktop, mobile, browser or API. Agents run on the user's own devices, and every machine added becomes another place for them to work, all managed from a single interface.

Each workspace is isolated, keeping work separate across machines while accumulating into documents that build a knowledge base; agents can read what they need from any connected node while working. Conversations become tasks on the board, and continuing a conversation improves and grows an agent purpose-built for that kind of work over time.

An open API, supporting both SSE and WebSocket, lets task and expert agents integrate into a user's own apps and workflows. It is self-hosted, with desktop and Android clients, and DeepSeek Harness is integrated directly into the desktop app, Android and browser versions.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.