[opensourcedex]

Leon is a free, open source ai interaction & interfaces project written in TypeScript and released under MIT. It has 17,518 GitHub stars, 1,469 forks and 112 open issues, and was last pushed 10 hours ago. On this registry it ranks #32 of 76 tracked projects in AI Interaction & Interfaces, with 5 head-to-head comparisons available. It gained 12 stars over the last 6 tracked days.

Leon — Your open-source personal assistant for server automation

What is Leon?

What it is

Leon is open-source personal AI assistant. It lives in Node.js and TypeScript ecosystem, under AI Interaction & Interfaces category. Project builds around tools, context, memory, and agentic execution. It aims to stay practical, privacy-aware, and grounded in real environment. Leon can operate locally, use dedicated tools instead of relying on free-form guessing, and complete tasks from start to finish across deterministic workflows and agent-style execution.

Problem solved: generic chat assistants give text replies without real environment access, without repeatable tool use, without durable context, and often push data through third-party services. Leon gives self-hosted users local assistant that can choose mode, use skills, inspect machine context, remember preferences and recent discussion, and act through desktop or browser interfaces. It also keeps modular path through skills, toolkits, bridges, and binaries, so automation work can grow beyond plain chat.

Key capabilities

  • Supports three execution modes: smart mode chooses handling, controlled mode follows deterministic native skills and actions, agent mode plans step by step.
  • Provides native skills for controlled actions and agent skills backed by SKILL.md workflows.
  • Uses real tools to complete work instead of only replying with plain text.
  • Includes advanced, progressively loaded computer use that can operate desktop and browser interfaces, verify visual outcomes, and run locally or through Satellite without exposing full tool surface to unrelated turns.
  • Keeps layered memory for durable preferences, day-to-day context, and recent discussion context.
  • Supports local and remote AI providers, helping balance privacy, control, and capability.
  • Runs server with runtime, routing, memory, context management, HTTP API, and agent/controlled execution; web app and Aurora UI components sit alongside built-in skills.

Who uses it and how

  • Self-hosters run Leon locally on Linux, macOS, or Windows as personal assistant and automation bot.
  • Privacy-focused users pair it with local models and local context, reducing forced third-party service use.
  • Operators use controlled native skills for deterministic actions, then agent mode for goals that need step-by-step planning.
  • Users with desktop or browser tasks can let computer use interact with interfaces and verify visual outcomes.
  • Contributors can work against develop branch for new core, or master branch for legacy pre-agentic version.

Getting started

Install Node.js 24.0.0 or newer, clone https://github.com/leon-ai/leon.git, install pnpm, run pnpm install, then pnpm start. Default local app appears at http://localhost:5366; pnpm run check verifies setup.

When to use it — and when not to

Use Leon for open-source, local-first AI assistant with tools, memory, and agentic execution in Node.js. Avoid it when needing finished 2.0 documentation or stable new-core behavior, because current docs mostly reflect legacy architecture and develop branch is Developer Preview. Master branch offers legacy more stable pre-agentic version, but it is not same as new core.

project readme (upstream, from github) — read inline

Leon
Leon

Your open-source personal AI assistant.

I share Leon progress most regularly on X / @grenlouis

Follow progress on X / @grenlouis · Website · Newsletter · Roadmap · Story

⚠️ Important Notice (as of 2026-03-29)

[!IMPORTANT] Leon is currently focused on the 2.0 Developer Preview on the develop branch.

  • The new documentation is not ready yet.
  • The current docs site and older guides mostly reflect the legacy architecture.
  • If you want the legacy, more stable pre-agentic version of Leon, use the master branch.
  • If you want to explore or contribute to Leon's new core, develop is the right place.

The most accurate high-level references for Leon's current state are:

👋 Introduction

Leon is your open-source personal AI assistant built around tools, context, memory, and agentic execution.

Leon is designed to stay practical, privacy-aware, and grounded in your real environment. It can operate locally, use dedicated tools instead of relying on free-form guessing, and complete tasks from start to finish across deterministic workflows and agent-style execution.

🧠 What Leon Is Today

Leon is no longer just a classic intent-classification assistant like it was for its first release in 2019.

Today, Leon is being built as a more capable assistant that can understand a goal, choose how to handle it, use tools, remember useful information, and recover when something goes wrong.

  • Leon can run in different ways depending on the task: smart mode chooses for you, controlled mode follows deterministic native skills and actions, and agent mode can plan step by step.
  • Leon supports native skills for controlled actions and agent skills for SKILL.md-backed workflows.
  • Leon can use real tools to get work done instead of only replying with plain text.
  • Leon includes advanced, progressively loaded computer use that can operate desktop and browser interfaces, verify visual outcomes, and run locally or through Satellite without exposing its full tool surface to unrelated turns.
  • Leon can use context about your environment so answers stay grounded in what is actually happening on your machine and setup.
  • Leon keeps layered memory so it can remember durable preferences, day-to-day context, and recent discussion context.
  • Leon supports both local and remote AI providers, which helps balance privacy, control, and capability.
  • Under the hood, Leon-native skills follow Skills -> Actions -> Tools -> Functions (-> Binaries).

Leon also keeps a compact self-model and a bounded proactive pulse system so it can stay more consistent over time without flooding itself with unnecessary context.

Why?

  • Privacy matters: Leon can work with local models and local context instead of forcing everything through third-party services.
  • Grounded behavior matters: Leon prefers explicit tools, context, and memory over vague model-only responses.
  • Extensibility matters: skills, toolkits, bridges, and binaries make it possible to keep Leon modular.
  • Open source matters: anyone can inspect the architecture, build on top of it, and help shape where it goes next.

🚀 Getting Started

Prerequisites

  • Node.js >= 24.0.0
  • Supported OSes: Linux, macOS, and Windows

Recommended: manage Node.js with Volta.

Installation

# Clone the repository
git clone https://github.com/leon-ai/leon.git

# Go to the project root
cd leon

# Install pnpm
npm install --global pnpm@latest

# Install dependencies
pnpm install

Run Leon

# Run Leon
pnpm start

Check Your Setup

# Check the setup went well
pnpm run check

By default, Leon runs locally and the app is available on http://localhost:5366.

🏗️ Architecture Snapshot

At a high level, Leon currently consists of:

  • server/: the main runtime, routing, memory, context management, HTTP API, and agent/controlled execution
  • app/: the web application
  • aurora/: UI components and preview environment
  • skills/: built-in capabilities, split between native/ skills and agent/ skills
  • bridges/: Node.js and Python bridges plus toolkit definitions and tool runtimes
  • tcp_server/: Python services used by parts of the runtime stack
  • core/context/: generated identity and architecture context documents that describe Leon's current behavior

This repository already includes skills and toolkits for areas such as search, productivity, system utilities, media workflows, coding assistance, memory-backed interactions, and voice/audio features.

📚 Documentation Status

The new docs for Leon 2.0 are not ready yet.

For now:

  • treat this repository as the source of truth for the 2.0 Developer Preview
  • use core/context/LEON.md for Leon's current identity and behavior
  • use core/context/ARCHITECTURE.md for the current architecture overview
  • expect the public docs site to lag behind the new core until the updated documentation is published

❤️ Contributing

We are starting to progressively onboard contributors for the 2.0 Developer Preview.

If you want to follow the project or express interest in joining that onboarding:

Why is there a small amount of contributors?

Leon has been evolving for a long time, but the current 2.0 work is a major transition period.

For a long time, Leon was a smaller assistant project with a simpler architecture. Today, the core is being rebuilt into a much more capable system around tools, memory, context, and agent-style execution. That means a lot of things are still moving, and it makes contribution harder than it will be once the new docs and architecture settle down.

Another important reason is simply time: Leon is still developed largely during spare time. So progress can be uneven, and opening the project more broadly has to be balanced with keeping the direction coherent while the 2.0 Developer Preview is still taking shape.

📖 The Story Behind Leon

Leon started in 2017 and has been active since 2019. If you want the longer backstory, read the story behind Leon.

🔔 Stay Tuned

👨 Author

Louis Grenard (@grenlouis)

👍 Sponsors

You can also contribute by sponsoring Leon.

Thanks

OpenAI logo.OpenAI logo. JetBrains logo.JetBrains logo. MacStadium logo.MacStadium logo.
openai.com/form/codex-for-oss jb.gg/OpenSource macstadium.com/company/opensource

Frequently asked questions

Is Leon free to use?

Leon is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does Leon do?

Your open-source personal assistant for server automation

What is Leon written in?

Leon is primarily written in TypeScript. Its source is publicly available at https://github.com/leon-ai/leon, and it has 17,518 GitHub stars.