#13 in Chat AssistantsUpdated 2026-08

Jan

by Jan · Open-source ChatGPT alternative that runs models locally

49 — BenchRank score out of 100

Homepage

Visit website See full Chat Assistants ranking

Overview

Jan is an open-source desktop app for chatting with AI models, presented as an alternative to ChatGPT. It runs open models such as Llama, Mistral, Qwen, DeepSeek and Gemma on your own machine, or connects to hosted models from OpenAI, Anthropic and Google. It is downloaded from the site and released on GitHub, currently at v0.8.4.

Best for: Individuals who want to run open-source AI models locally or connect to cloud models.
Pricing: No prices are shown; the site describes Jan as free and open source.
Runs on: macOSWindowsLinux

Strengths and trade-offs

Strengths

Free and open source, with 43.8K stars on GitHub
Runs open models locally or connects to GPT, Claude and Gemini
Community of 1.8K on Discord and 123 models on HuggingFace

Trade-offs

Homepage only offers a Mac download; other platforms are not shown
Memory feature is marked Coming Soon, so not available yet
Pre-1.0 release (v0.8.4); expect changes between versions

How this score is made up

Each dimension is scored out of 100 and combined into the headline score using fixed weights.

MCP support: 60 out of 100
API quality: 10 out of 100
Documentation: 80 out of 100
Agent friendliness: 52 out of 100
Pricing transparency: 35 out of 100
Changelog: 100 out of 100
Marketing site structure: 50 out of 100
Operational trust: 0 out of 100

Measured, but not part of the score

Useful to know, but not a mark for or against the product — so these do not affect the ranking.

Openness: 30 out of 100
Maintenance: 100 out of 100

This doesn’t look right — report a problem with Jan’s score

Alternatives in Chat Assistants

Ranked 1
77.1 — BenchRank score out of 100
Browser Use
Browser Use · Open-source browser automation with hosted stealth browsers and agents
Best for: Teams building web automation that need hosted stealth browsers and agent APIs, plus an open-source library
Ranked 2
76.6 — BenchRank score out of 100
LobeHub
LobeHub · Hosted multi-agent platform with a skills and MCP marketplace
Best for: Individuals and small teams wanting to run several AI agents on a hosted, credit-metered platform
Ranked 3
68.8 — BenchRank score out of 100
Open WebUI
Open WebUI · Self-hosted interface for running local and cloud AI models
Best for: Teams that want to self-host one interface over local and cloud models on their own infrastructure.