Lexora
View on GitHubA self-evolved, sovereign desktop AI agent built for real-world action — beyond model wrappers and coding copilots. / 真实实践中自我演化的独立桌面 AI Agent。
Lexora is a local-first desktop AI agent (Vue + Electron + a separate TypeScript runtime, Rust native layer) that runs an agent loop with sandboxed tool execution, MCP integrations, Skills and scheduled tasks. It is model-agnostic and requires explicit user authorization for file and tool access.
Use Cases
Run a desktop AI agent that reads files, runs commands and edits codeAutomate recurring chores like work logs and weekly reports via scheduled tasksConnect your own model providers instead of a single bundled modelExtend agent capabilities with MCP tool serversPackage reusable working methods as SkillsGenerate images and artifacts from chat tasksExecute tools inside a sandbox with per-action user authorizationKeep project context and artifacts local to your machineTrack task execution and deliverables in one desktop workflowInstall on Windows, Linux or macOS as a standalone app
Built With
- Language
- TypeScript
- Frameworks
- Vue · Electron · TypeScript · Rust · Pi · Prisma · Docker · Traefik · pnpm · ESLint
Tags
desktop-agent · autonomous-agents · agent-loop · mcp · skills · sandbox · local-ai · local-first · task-automation · file-automation · scheduled-tasks · desktop-pet · electron · rust · linux · multi-model