Deploy Now

SaaS Alternative

ChatGPT Claude Lindy Manus

Stars

17,695

Forks

1,484

Watchers

266

Leon

Leon is a personal AI assistant that lives on your own server, remembers what matters to you, and finishes real tasks with tools instead of just chatting. Ask for something in the browser web app and Leon plans the work, runs tools in isolated workers, checks the results, recovers from failures, and writes a short summary. Agent mode handles open-ended requests, controlled mode follows predictable native skills, and smart mode picks the better route for each task. Layered memory keeps durable facts and preferences, daily summaries, and recent discussion context, and Leon can search earlier conversations when exact details matter. Answers can arrive as interactive charts with region toggles, forms, and calculators instead of walls of text, and generated files become downloadable artifacts. Setup cards guide you through connecting services such as Spotify, owner-installed MCP servers add more tools, and a browser tool and computer use handle web pages and desktop applications. Pick models per profile, from a local llama.cpp model to OpenAI, Anthropic, DeepSeek, Groq, or OpenRouter. Profiles keep config, secrets, sessions, and memory separate, so one server can serve several people, with optional token authentication for remote clients. Workspaces group conversations under a shared brief, and Leon Satellite lets a remote Leon use enabled tools on your own device. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Leon
Leon
Leon
Leon
Leon

Benefits

  • Plans, acts, and verifies tasks
  • The agent loop breaks a request into a plan, calls declared tools in isolated workers, reads every result, retries after failures, and reports what was finished and what still remains.
  • Memory that stays private per profile
  • Persistent facts, daily summaries, and recent discussion memory live in profile-owned storage beside separate config and secrets, so one server can serve several people without mixing their data.
  • Bring your own model or provider
  • Run a local llama.cpp model or connect OpenAI, Anthropic, DeepSeek, Groq, OpenRouter, and other providers, with separate default, workflow, and agent models chosen in profile settings.
  • Answers you can interact with
  • Aurora widgets render charts with toggles, forms, and calculators inside the conversation, so a sales question returns an explorable view, and generated files arrive as downloadable artifacts.

Features

  • Continuous Agent Loop
  • Agent mode keeps one tool-calling transcript that plans, executes, observes, and recovers, with checkpoints, deadlines, and completion review; controlled and smart modes route to native skills.
  • Layered Memory System
  • Persistent facts, daily summaries, and discussion memory are searched through QMD, with a curated owner profile, exact session search, and compaction that prunes older short-term records.
  • Tools, Skills, and MCP
  • Native tools declare functions, settings, and binaries, agent skills use SKILL.md files, and owner-installed HTTP MCP servers add tools with encrypted OAuth and cancellable calls.
  • Aurora Visual Answers
  • Native widgets and sandboxed generated HTML, CSS, and JavaScript render charts, forms, and calculators in opaque-origin frames, and only confirmed values return to Leon as commands.
  • Leon Satellite and Computer Use
  • An optional Satellite process on your device exposes its enabled tools to a remote Leon server, while Browser Use CLI and Cua handle browser and desktop control.
  • Multi-Profile Server Runtime
  • One server runs many profiles at once, each with isolated config, secrets, sessions, and logs, and a profile:token credential can authenticate Socket.IO clients, HTTP integrations, and Satellite.

Apps Similar to Leon