Leon
Leon is your open-source personal AI assistant built around tools, context, memory, and agentic execution. It can operate locally, use dedicated tools, and complete tasks deterministically or via agent-style planning.
Smart Download
Visit Project Homepage
No installer available yet — head to the source repository
A privacy-first open-source AI assistant that runs locally, uses tools, and remembers context.
Core Features
- Runs locally with privacy-first design, supports remote AI providers too
- Native skills (controlled execution) & agent skills (autonomous planning)
- Layered memory: durable preferences, day-to-day context, recent discussions
- Built-in search, productivity, system utilities, media, coding, voice/audio skills
- Modular architecture: skills, toolkits, bridges, binaries for easy extension
What It Can't Do
- •The 2.0 Developer Preview is work-in-progress with incomplete docs. Use the 'master' branch for a stable legacy version. Read core/context/LEON.md and ARCHITECTURE.md for current architecture.
Use Cases
- Personal assistant for daily tasks: search, reminders, file management, system operations
- Developers can use Leon as an AI foundation and customize workflows via skills and toolkits
- Privacy-sensitive scenarios where everything runs locally without third-party cloud services
Detailed Introduction
Leon is an open-source personal AI assistant designed to be practical, privacy-aware, and grounded in your real environment. It can operate locally, use dedicated tools instead of relying on pure model guessing, and complete tasks from start to finish through deterministic workflows or agent-style execution. Leon supports native skills for controlled actions, agent skills for step-by-step planning, layered memory (preferences, context, recent discussions), and both local & remote AI providers. The project is currently in a major transition to version 2.0, rebuilding its core around tools, context, memory, and agentic execution. It includes skills for search, productivity, system utilities, media, coding, memory, and voice/audio features.
Troubleshooting & FAQ (2)
TroubleshootingHow to fix audio or video errors in Leon AI when using Google Cloud TTS/STT?
Incorrect provider names in the .env file cause audio/video failures. Set them explicitly:
LEON_TTS_PROVIDER=google-cloud-tts
LEON_STT_PROVIDER=google-cloud-sttAlso confirm GOOGLE_APPLICATION_CREDENTIALS points to your service account key file.
TroubleshootingHow to fix 'TypeError: Invalid Version: 3.7.6rc1' when installing Leon AI on Windows 10?
This error occurs because the semver npm package cannot parse Python's release candidate version string (e.g., 3.7.6rc1). To resolve:
1. Install a stable Python release (e.g., 3.7.6 or 3.8.1) and ensure it's used by pipenv.
2. Alternatively, switch to the develop branch where the issue may be fixed:
git checkout develop
npm install
npm run check3. For a quick start without local setup, use Gitpod:
[https://gitpod.io/#https://github.com/leon-ai/leon](https://gitpod.io/#https://github.com/leon-ai/leon)
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Double-click the downloaded installer and follow the prompts
Clone repo: git clone https://github.com/leon-ai/leon.git
Enter directory: cd leon
Install pnpm: npm install --global pnpm@latest
- Clone repo: git clone https://github.com/leon-ai/leon.git
- Enter directory: cd leon
- Install pnpm: npm install --global pnpm@latest
Checksum not available
This project has not published a SHA-256 checksum on its GitHub Release page
SHA256 Checksum
No checksum available
Download directly from GitHub Releases and verify file integrity yourself
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Simply delete the project directory. Optionally uninstall global pnpm with: npm uninstall -g pnpm.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Having issues? Check the FAQ below
2 FAQs
Similar Projects
Chatbox
Chatbox Community Edition is an open-source desktop client for interacting with multiple large language models. It supports OpenAI (ChatGPT), Azure OpenAI, Claude, Google Gemini Pro, Ollama (local models like Llama 2, Mistral), and ChatGLM-6B. All your chat data is stored locally on your device, ensuring privacy and preventing data loss. The app features a clean, ergonomic UI with dark mode, keyboard shortcuts, streaming replies, and full Markdown/LaTeX rendering with code highlighting. It also includes a prompt library, message quoting, and team collaboration for sharing API resources. Available on Windows, macOS, Linux, Web, iOS, and Android. The community edition is fully functional but may lack some advanced features from the pro version.
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).