Back to directory

Xagent

A platform for building personal AI agents that scales into team and enterprise agent workforces, letting a user describe an outcome rather than write a workflow.

Xagent

Xagent helps an individual complete real tasks with a personal agent, lets a team publish reusable agents, and lets an enterprise run agent systems with its own tools, models, knowledge and infrastructure, all without hand-built workflows: a user describes the outcome they want rather than the steps to reach it.

As a personal agent it gives chat-style execution over tools, files, models and data with real-time progress, for one-off tasks, research and writing. As a team workforce it turns agents into reusable units with roles, tools, models, knowledge bases, templates and live preview that can be published and shared. As an enterprise platform it runs agent systems against an organization's own infrastructure.

It runs locally as a single Python package with a bundled web UI, needing no Docker or Node.js, or as a Docker Compose stack for teams and self-hosting, and can import agents, skills and schedules migrated from OpenClaw or Hermes.

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.