--- title: "guidance vs jan" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/guidance-ai-guidance-vs-janhq-jan" tools: ["guidance-ai-guidance", "janhq-jan"] --- # guidance vs jan *GraphCanon updated Jul 11, 2026* ## Verdict Pick guidance if guidance is a specialized tool written in Jupyter Notebooks that provides a unique language to control large language models (LLMs) across multiple backends such as Transformers, llama.cpp, and OpenAI. It's open-source,轻; pick jan if jan is a TypeScript-based, self-hosted chatbot application that acts as an offline alternative to services like ChatGPT. [guidance](https://github.com/guidance-ai/guidance) reports 22k GitHub stars, 1.2k forks, and 303 open issues, last pushed May 21, 2026. [jan](https://jan.ai/) has 43k stars, 2.9k forks, and 387 open issues, last pushed Jul 10, 2026. Figures are from public GitHub metadata via [guidance's repository](https://github.com/guidance-ai/guidance) and [jan's repository](https://github.com/janhq/jan). | | [guidance](/tools/guidance-ai-guidance.md) | [jan](/tools/janhq-jan.md) | | --- | --- | --- | | Tagline | A guidance language for controlling large language models. | open source alternative to ChatGPT that runs offline locally | | Stars | 21,656 | 43,499 | | Forks | 1,190 | 2,896 | | Open issues | 303 | 387 | | Language | Jupyter Notebook | TypeScript | | Adopt for | Guidance is a specialized tool written in Jupyter Notebooks that provides a unique language to control large language models (LLMs) across multiple backends such as Transformers, llama.cpp, and OpenAI. It's open-source,轻 | Jan is a TypeScript-based, self-hosted chatbot application that acts as an offline alternative to services like ChatGPT. | | Persona | - | - | | Runtime | - | - | | License | MIT | Other | | Categories | Inference & Serving, LLM Frameworks | Inference & Serving, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [guidance](/tools/guidance-ai-guidance.md) | [jan](/tools/janhq-jan.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Very active (96%) | | Days since push | 50d | 1d | | Open issues (now) | 303 | 387 | | Full report | [trust report](/tools/guidance-ai-guidance/trust.md) | [trust report](/tools/janhq-jan/trust.md) | ## Decision facts: guidance - **Adopt for:** Guidance is a specialized tool written in Jupyter Notebooks that provides a unique language to control large language models (LLMs) across multiple backends such as Transformers, llama.cpp, and OpenAI. It's open-source,轻 ## Decision facts: jan - **Adopt for:** Jan is a TypeScript-based, self-hosted chatbot application that acts as an offline alternative to services like ChatGPT. ## Choose when ### Choose guidance if… - guidance is primarily Jupyter Notebook; jan is TypeScript. - License: guidance is MIT, jan is Other. - Tags unique to guidance: backend support, control language, language-models, pip-installable. - When you need a specific language to finely control various LLM backends including Transformers, llama.cpp, and OpenAI ### Choose jan if… - jan is primarily TypeScript; guidance is Jupyter Notebook. - License: jan is Other, guidance is MIT. - Tags unique to jan: chatgpt, gpt, llamacpp, llm. - - If you require an offline-capable AI assistant for environments without internet access. ## When NOT to use guidance - When your project is strictly confined to using only one type of backend which you can manage without a specialized control language - If your development environment does not support or prefer Jupyter Notebooks, Guidance may not be the best choice ## When NOT to use jan - - If you require real-time updates to the AI model, since Jan uses static local models which may not get frequent updates. - - When a vast knowledge base or continuous learning capabilities are essential, as Jan's offline nature constrains its ability to stay current with new information. ## Common questions ### What is the difference between guidance and jan? guidance: A guidance language for controlling large language models.. jan: open source alternative to ChatGPT that runs offline locally. See the comparison table for live GitHub stats and shared categories. ### When should I choose guidance over jan? Choose guidance over jan when guidance is primarily Jupyter Notebook; jan is TypeScript; License: guidance is MIT, jan is Other; Tags unique to guidance: backend support, control language, language-models, pip-installable; When you need a specific language to finely control various LLM backends including Transformers, llama.cpp, and OpenAI. ### When should I choose jan over guidance? Choose jan over guidance when jan is primarily TypeScript; guidance is Jupyter Notebook; License: jan is Other, guidance is MIT; Tags unique to jan: chatgpt, gpt, llamacpp, llm; - If you require an offline-capable AI assistant for environments without internet access. ### When should I avoid guidance? When your project is strictly confined to using only one type of backend which you can manage without a specialized control language If your development environment does not support or prefer Jupyter Notebooks, Guidance may not be the best choice ### When should I avoid jan? - If you require real-time updates to the AI model, since Jan uses static local models which may not get frequent updates. - When a vast knowledge base or continuous learning capabilities are essential, as Jan's offline nature constrains its ability to stay current with new information. ### Is guidance or jan more popular on GitHub? jan has more GitHub stars (43,499 vs 21,656). Stars measure visibility, not whether either tool fits your constraints. ### Are guidance and jan open source? Yes - both are open-source projects on GitHub (guidance: MIT, jan: Other). ### Where can I find alternatives to guidance or jan? GraphCanon lists graph-backed alternatives at [guidance alternatives](/tools/guidance-ai-guidance/alternatives) and [jan alternatives](/tools/janhq-jan/alternatives) ([guidance markdown twin](/tools/guidance-ai-guidance/alternatives.md), [jan markdown twin](/tools/janhq-jan/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/guidance-ai-guidance-vs-janhq-jan.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, guidance or jan? guidance: Steady. jan: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for guidance and jan? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [guidance trust report](/tools/guidance-ai-guidance/trust); [jan trust report](/tools/janhq-jan/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=guidance-ai-guidance`](/api/graphcanon/graph?tool=guidance-ai-guidance) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_