# Jan vs Vellum

Jan records 291,894 monthly visits with -9.6% month-over-month growth and Free pricing. Vellum records 331,901 monthly visits with -20.8% growth and Freemium, Paid pricing.

| Metric | [Jan](https://openaitools.app/tool/jan) | [Vellum](https://openaitools.app/tool/vellum) |
| :--- | :--- | :--- |
| Website URL | https://jan.ai | https://www.vellum.ai |
| Categories | AI Chatbot, AI Assistant, Open Source AI Models, Large Language Models (LLMs) | AI Developer Tools, AI Workflow, Prompt Engineering |
| Pricing Model | Free | Freemium, Paid |
| Monthly Visits | 291,894 | 331,901 |
| MoM Growth Rate | -9.6% | -20.8% |
| Primary Market | United States | United States |
| Direct Visits | 105,615 | 70,205 |
| Review Score | 4.6 | 4.2 |
| Saved Count | 6 | 3 |
| Supported Platforms | Website | Website |

## Jan

Jan is a desktop application that positions itself as an open replacement for ChatGPT, with the key difference that inference happens on hardware you control. After installing the app you pick a model, and Jan downloads and runs it locally, so prompts, chat history, and files stay on your machine rather than on someone else's server. For heavier workloads you can connect an OpenAI, Anthropic, Gemini, or Mistral key and route requests to the cloud while keeping the same chat interface and local history.

The project is developed in the open by Menlo Research and has accumulated tens of thousands of GitHub stars along with millions of downloads. It exposes OpenAI-compatible local endpoints, which means existing tooling and SDKs can point at Jan instead of a hosted service, and it supports custom assistants with their own instructions and model choices. Recent releases have added an agent surface alongside the classic desktop chat, and a memory feature is announced as coming to carry context and preferences between sessions.

Because it is open source, Jan can be audited, self-built, and extended, and there is no paid tier gating the desktop client. The practical tradeoff is that local model quality and speed depend entirely on your own GPU or CPU, so lighter machines will favor smaller quantized models while cloud keys remain the escape hatch for harder tasks.

**Pricing & Plans:** Jan is free and open source, with no paid tier for the desktop app. Costs only appear if you optionally connect your own paid cloud API keys for providers such as OpenAI or Anthropic.

- **Local-first inference:** Download and run open models such as Llama, Mistral, Qwen, Gemma, and DeepSeek directly on your own machine, with chat data kept on device.
- **Bring your own cloud models:** Optionally connect API keys for OpenAI, Anthropic, Gemini, Mistral, and other providers to route requests to frontier models from the same interface.
- **OpenAI-compatible local API:** Jan exposes a local server endpoint that follows the OpenAI API shape, so existing SDKs and tools can talk to your local models without code changes.
- **Custom assistants:** Create assistants with their own system instructions, model selection, and parameters, then reuse them across conversations.
- **Open source and extensible:** The full desktop client and agent code are public on GitHub, so you can audit behavior, build your own version, and contribute improvements.

**Strengths:** Completely free and open source, with no account required to run local models; Conversation data stays on your device by default; Works across macOS, Windows, and Linux with an OpenAI-compatible local endpoint; Optional cloud key support lets you mix local and frontier models in one app

**Limitations:** Local model quality and speed are capped by your own hardware; Very large models may need substantial RAM or VRAM to be practical; Some cloud-connected and memory features are newer or still rolling out

[Profile (Markdown)](https://openaitools.app/tool/jan.md)

## Vellum

Vellum is a personal AI assistant rather than a chat box. The core idea is ownership: your assistant runs locally on your own machine by default, or in a dedicated cloud container if you prefer Vellum Cloud, and it is yours to shape. You configure how it talks, what it can touch and which models it uses, choosing between OpenAI, Anthropic, Gemini or open-weight models via Ollama. The codebase is open-source, so the privacy claims can be inspected rather than merely trusted.

What separates it from a general-purpose chatbot is memory and autonomy. Vellum's custom memory system tracks you, your people, your preferences and your ongoing work across conversations, so context does not evaporate when a session ends. With built-in skills for Google Workspace, Slack, Notion and your filesystem, plus community and custom plugins, the assistant can send emails, manage calendars, browse the web, generate slides, write code, run deep research, monitor sites and repeat background tasks on a schedule. Because it acts rather than only answers, Vellum ships a fine-grained permission system: actions with real consequences require approval until you mark them trusted.

Availability is broad by design. It is native on Mac and reachable through iOS, Android, a web app, voice, email, Telegram, Slack and the terminal, with the same memory, tasks and schedules on every surface. Vellum is free to download and run locally; cloud subscriptions start at $30/month (Mighty), $100/month (Super) and $200/month (Ultra) with dedicated compute, storage and bundled credits. Note that the company has announced the Personal Assistant Platform is shutting down by December 13, 2026, so verify current availability and export options before committing.

**Pricing & Plans:** Free to download and run locally. Vellum Cloud subscriptions start at $30/month (Mighty), $100/month (Super) and $200/month (Ultra), each with dedicated compute, storage and bundled credits. Credits are consumed by actions. The site also notes the Personal Assistant Platform is shutting down by December 13, 2026, with instructions to download your assistant.

- **Long-term personal memory:** A custom-built memory system that retains you, your people, preferences and work across every conversation, rather than resetting each session.
- **Skills and tool integrations:** Connect Google Workspace, Slack, Notion, your filesystem and community plugins so the assistant can send emails, manage calendars, browse, create slides and run research.
- **Fine-grained permissions:** Set permissions so sensitive actions like emailing new contacts or modifying key files require approval until you mark them trusted.
- **Model choice:** Switch between OpenAI, Anthropic, Gemini or open-weight models via Ollama at any time, keeping you free of a single vendor lock-in.
- **Local-first privacy:** Your assistant runs locally by default with open-source code you can inspect; Vellum Cloud offers an isolated container provisioned just for you.
- **Available everywhere:** Native on Mac and available on iOS, Android, web, voice, email, Telegram, Slack and terminal, all sharing the same identity, memory and schedules.

**Strengths:** Runs locally by default with open-source code you can audit; Genuine long-term memory that persists across every conversation; Model-agnostic: OpenAI, Anthropic, Gemini or local open weights via Ollama; Takes real actions across email, calendar, files and connected tools

**Limitations:** The homepage banner states the Personal Assistant Platform is shutting down by December 13, 2026; Proprietary cloud tiers at $30–$200 per month, and credit-based actions can add cost; High-stakes actions require approval prompts until you mark them trusted, adding friction early on; Mac-first native experience, so non-Apple users depend on web and chat surfaces

[Profile (Markdown)](https://openaitools.app/tool/vellum.md)

## Frequently Asked Questions

### How do Jan and Vellum compare in monthly traffic?

Jan has 291,894 monthly visits, while Vellum has 331,901. Traffic estimates describe audience size, not product quality.

### How do their growth rates compare?

Jan has a month-over-month growth rate of -9.6%; Vellum has -20.8%.

### How does pricing compare?

Jan: Free. Jan is free and open source, with no paid tier for the desktop app. Costs only appear if you optionally connect your own paid cloud API keys for providers such as OpenAI or Anthropic. Vellum: Freemium, Paid. Free to download and run locally. Vellum Cloud subscriptions start at $30/month (Mighty), $100/month (Super) and $200/month (Ultra), each with dedicated compute, storage and bundled credits. Credits are consumed by actions. The site also notes the Personal Assistant Platform is shutting down by December 13, 2026, with instructions to download your assistant.

## Alternatives

| # | Tool Name | Monthly Visits | MoM Growth Rate | Pricing Model | Summary | Profile (Markdown) |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| 1 | [Ollama](https://openaitools.app/tool/ollama) | 9,421,973 | +4.3% | Free, Freemium, Paid | Serves as a lightweight backend runtime for running local models, but requires a separate UI or client app. | [.md](https://openaitools.app/tool/ollama.md) |
| 2 | [n8n](https://openaitools.app/tool/n8n) | 4,522,449 | -7.4% | Freemium | Excels at node-based workflow automation and agent orchestration, but is less focused on conversational assistant interactions. | [.md](https://openaitools.app/tool/n8n.md) |
| 3 | [Hermes-Agent](https://openaitools.app/tool/hermes-agent-1) | 3,638,741 | -5.4% | Freemium | Offers autonomous personal agent capabilities with persistent memory, but requires more technical setup than Vellum. | [.md](https://openaitools.app/tool/hermes-agent-1.md) |
| 4 | [Clawdbot (OpenClaw)](https://openaitools.app/tool/clawdbot) | 1,903,068 | -25.4% | Paid, Free | Connects local models directly to messaging apps for task automation, but lacks Vellum's polished desktop assistant interface. | [.md](https://openaitools.app/tool/clawdbot.md) |
| 5 | [Dify](https://openaitools.app/tool/dify-ai) | 819,691 | -15% | Freemium | Provides visual workflow building and RAG pipelines, but is structured more as a developer platform than a personal assistant. | [.md](https://openaitools.app/tool/dify-ai.md) |
| 6 | [Open WebUI](https://openaitools.app/tool/open-webui) | 804,534 | -2.8% | Freemium | Provides a feature-rich self-hosted chat interface for local models, but lacks native background workflow automation. | [.md](https://openaitools.app/tool/open-webui.md) |
| 7 | [AnythingLLM](https://openaitools.app/tool/anythingllm) | 512,269 | +12.9% | Freemium | Focuses heavily on local document RAG and privacy-first chat, whereas Vellum emphasizes broader assistant workflows. | [.md](https://openaitools.app/tool/anythingllm.md) |
| 8 | [LibreChat](https://openaitools.app/tool/librechat) | 346,879 | -3.5% | Free | Unites multiple AI providers in a customizable open-source platform, but is typically deployed as a web server. | [.md](https://openaitools.app/tool/librechat.md) |
| 9 | [Activepieces](https://openaitools.app/tool/activepieces) | 258,553 | +1.5% | Freemium | Combines visual workflow builders with AI agent connectors, but lacks native local model management out of the box. | [.md](https://openaitools.app/tool/activepieces.md) |
| 10 | [Dyad](https://openaitools.app/tool/dyad) | 207,981 | +3.5% | Freemium | Free, open-source AI app builder that runs on your own machine | [.md](https://openaitools.app/tool/dyad.md) |

---
Source: https://openaitools.app/compare/jan-vs-vellum

More Markdown: [Categories](https://openaitools.app/categories.md) · [Traffic rankings](https://openaitools.app/rankings.md) · [llms.txt](https://openaitools.app/llms.txt)
