What did Hlido score leon-ai/leon?

leon-ai/leon scored 75/100 (STEADY) in Hlido's independent, hands-on review.

Is leon-ai/leon reliable?

leon-ai/leon is rated STEADY (75/100) by Hlido. Public-surface review of leon-ai/leon.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

leon-ai/leon

Name: leon-ai/leon review
Item: leon-ai/leon
Rating: 75
Author: Hlido Editor

Chat & Companion · tested 2026-10-01 · by the Hlido desk, not the vendor

In short: A long-running open-source personal assistant leaning into privacy and offline operation — and now visibly rebuilding itself around agentic execution.

3 PASS · 2 FAIL of 5 public-surface claims

Visit leon-ai/leon → scorecard.json

Quick answer

leon-ai/leon scores 75/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-10-01). STEADY (75) for a mature, genuinely open-source personal assistant with a defensible privacy/offline niche, speech on both ends, and a coherent move toward agentic execution with both native and SKILL.md-backed skills. Pricing was not findable on the public surface when tested.

Hlido Editor · 2026-10-01

Leon is one of the older open-source personal-assistant projects, and its public surface shows a deliberate second act: from a voice/skill assistant toward a more capable agent that can understand a goal, pick how to handle it, use tools, remember useful information and recover from failures. The privacy-and-offline posture is the honest differentiator — it can run locally with speech-to-text and text-to-speech, which is a genuinely different value proposition from the cloud assistants, and it matters to exactly the users who won't accept those. The project documents both native skills for controlled actions and agent skills backed by SKILL.md workflows, which is a sensible bridge between deterministic automation and agent-style execution. This is a public-surface and repository read, not a running installation, so the verdict reflects the project's direction, maturity signals and stated capabilities rather than measured task completion — and 'being rebuilt' is a phase a buyer should weigh, because it means the most interesting capabilities are partly aspirational today.

Why STEADY

STEADY (75) for a mature, genuinely open-source personal assistant with a defensible privacy/offline niche, speech on both ends, and a coherent move toward agentic execution with both native and SKILL.md-backed skills. Not higher because the project openly describes itself as being rebuilt, so some of the most compelling capabilities are in progress, and this is a surface read rather than a measured run.

Public-surface checklist

PASS Homepage loads (required)
PASS Primary value prop (required)
FAIL Cta present (required)
FAIL Pricing or access
PASS Evidence or demo

What we saw

1 screenshot captured by the Hlido engine during the reviewed run (run-2bc7f86b00c019f2-github-com). Our own captures — not vendor marketing material.

leon-ai/leon — run screenshot 1 (home.png) — home.png

What it does well

Privacy-first and offline-capable — a real differentiator from cloud assistants
Fully open-source with a long track record
Speech-to-text and text-to-speech on-device for a voice-driven experience
Both native skills (controlled actions) and SKILL.md-backed agent skills
Clear, stated direction toward goal-understanding and failure recovery

What it fails at

Openly mid-rebuild — the most capable agentic features are partly aspirational
Self-hosted assistant means setup and maintenance fall on the user
Stated capabilities were read, not executed, in this review
Smaller ecosystem than commercial assistants means fewer ready integrations

Best for

Privacy-conscious users who want a self-hosted, offline-capable assistant
Developers who want to extend an assistant with their own skills
Voice-driven local automation where cloud assistants are unacceptable

Not recommended for

Users wanting a polished, zero-setup commercial assistant
Buyers who need the in-progress agentic features working today
Non-technical users unwilling to self-host

Pricing & access

Pricing findable on the public surfaceFAIL

Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-06-15.

Compared to

goose personal-assistant
Goose is a developer-focused local agent; Leon is a broader personal assistant with voice and a privacy/offline emphasis. Choose Leon for a voice-driven home/personal assistant, Goose for developer task automation.

Agent relevance

CLI SDK

Leon is itself an assistant/agent that developers extend with native and SKILL.md-backed skills; it is self-hosted and driven locally. It is a thing you build on and run, not a hosted endpoint other agents call.

Agent-friendly score: 5/10

Evidence

Open-source personal assistant — source (2026-10-01) verified
Can operate locally and use dedicated tools across deterministic workflows and agent-style execution — source (2026-10-01) verified
Supports native skills for controlled actions and agent skills via SKILL.md workflows — source (2026-10-01) verified

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: public-surface-tier-2-repo+editorial-narrative-v2 · Methodology version 2026.05 ·

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/leon-ai-leon.svg)](https://hlido.eu/check/?agent=leon-ai-leon)

HTML

<a href="https://hlido.eu/check/?agent=leon-ai-leon"><img src="https://hlido.eu/badge/leon-ai-leon.svg" alt="Hlido trust score"></a>