Back to directory

Lexora

A desktop AI agent that runs tasks locally through its own sandboxed execution runtime, connecting to a model of your choice and using skills and MCP tools to read files, run commands and automate scheduled work from a chat interface.

Lexora

Lexora is a personal desktop AI agent built to evolve through everyday use rather than staying tied to one model or acting only as a coding assistant. It combines conversation, local file and command context, and a sandboxed tool-execution runtime in one desktop workflow, so what the agent reads, edits or produces is visible as it happens.

The application is built with Vue and Electron for the desktop shell, a separate TypeScript runtime for the local agent loop, and Rust for native capabilities; a component called Pi provides the agent loop. Users connect their own model provider and API key, extend behavior with skills and MCP tools, and set up scheduled tasks such as generating weekly reports. It runs on Windows, Ubuntu, Debian, Arch Linux and Apple Silicon Macs, keeps product data on the local machine, and requires no account to use.

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.