Back to directory

xopc

An open-source, local-first personal AI that remembers a user's goals and context across sessions and channels, and takes action on connected tools with confirmation required before high-impact steps.

xopc

xopc keeps context, evidence and the next action together across sessions, so work does not disappear when a chat ends: a user can drop in unorganized text, voice, files or links, and xopc carries the thread forward across desktop, web, terminal, mobile, Telegram, WeChat and Feishu or Lark clients, with a choice of cloud or local models. It can use tools, run workflows and verify results, then continue that work later rather than only giving advice.

The project is local-first by design: sources are authorized separately, high-impact actions such as sending or deleting something require confirmation, and connecting to a companion cloud or privately deployed platform for centrally published services is opt-in and does not upload the local database or workspace. The easiest way to start is a desktop app for macOS, Windows or Linux that runs local model setup and a built-in chat console; a one-line installer also supports Linux, macOS, WSL2 and Termux.

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.