OSS Tanbou

Leon — evolving into a personal AI assistant with tools, memory, and computer use

About these scores

OSS scale score is an unbounded metric that log-compresses and weights Stars, Watchers, Forks, and Contributors. Discovery score is the current OSS scale score minus the score at discovery. Update pace is commits in the last 30 days, growth momentum is the OSS scale score difference within the recent observation window, and OSS health is a 0–100 rating based on available recency, Community Health, and release data.

Stars
17,532
Primary language
TypeScript
License
MIT
Repository last updated
Sep 20, 2026

Overview

Leon is an open-source personal AI assistant built around tools, context, memory, and skills, with smart/controlled/agent execution modes, local and remote models, computer use, and voice/audio capabilities.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Switch between controlled and agentic execution depending on the task

Deterministic native skills and step-by-step agent execution coexist, while smart mode chooses a path based on the task.

Sources: [2][3]

Unify memory, skills, computer use, and voice in one assistant

Layered memory, skills, desktop/browser operations, and voice/audio tooling are combined toward a long-lived personal assistant.

Sources: [2][3]

For experimenting with personal agents grounded in local machine context and tools

It fits developers who need more than a chat UI and want model reasoning connected to real environment context and actions.

Sources: [2]

Do not confuse the 2.0 Developer Preview with the legacy branch

The repository says the develop branch and in-repo architecture documents are the current source of truth while public documentation catches up.

Sources: [2][3]

Official sources

  1. [1]leon-ai/leon repository(2026-09-21)
  2. [2]Leon README(2026-09-21)
  3. [3]Leon 2.0 architecture context(2026-09-21)
  4. [4]Leon MIT license(2026-09-21)
Supplemental curator note

Leon is undergoing a major transition from its earlier intent-classification assistant into an agentic 2.0 architecture. The README dated March 29, 2026 says `develop` is the 2.0 Developer Preview, `master` is the more stable legacy version, and public docs still largely reflect the older architecture. Branch choice matters for evaluation.

Try it in 3 steps

  1. 1

    Get the source

    git clone --depth 1 https://github.com/leon-ai/leon.git
  2. 2

    Enter the repository

    cd leon
  3. 3

    Check the official steps

    Continue with the commands in the README Installation, Quick Start, or Getting Started section.

    find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Check the official README

Growth

Growth trends · Last 30 days

17,532 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
139
Open PRs
17

Development activity is still being collected.

Built with

Categories and tags

GitHub data

GitHub dataView detailed GitHub data

GitHub Topics

  • leon
  • personal-assistant
  • nodejs
  • python
  • ai
  • artificial-intelligence
  • speech-to-text
  • text-to-speech
  • speech-recognition
  • speech-synthesis
  • assistant
  • virtual-assistant
Stars
17,532
Forks
1,469
Watchers
276
Open issues
94
Contributors
23
Primary language
TypeScript
License
MIT
Repository last updated
Sep 20, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.