Back to directory

LobeHub

LobeHub positions itself as a "Chief Agent Operator" that organizes a user's AI agents into round-the-clock operation, hiring, scheduling and reporting on their work so a person can stay in charge without staying online.

LobeHub

LobeHub treats agents as the basic unit of work: it creates them, lets them collaborate in new kinds of networks, and frames ongoing use as a co-evolution between humans and agents rather than one-off task runs that forget context between sessions.

It self-hosts through Vercel, Zeabur, Sealos, Alibaba Cloud or Docker, with configurable environment variables and support for connecting an OpenAI API key or other providers. A plugin system extends what agents can do, and the project ships an ecosystem of related products alongside the core application.

The project describes its contributors as design-engineers building toward a more open, transparent product ecosystem, and says it remains under active development with feedback welcomed through its issue tracker. TypeScript.

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.