# Vellum

> Vellum is a personal AI assistant that remembers, learns, and takes real action across every platform you use. For a complete per-page index of the documentation, see [Vellum docs index](https://www.vellum.ai/docs/llms.txt).

Vellum is not a chatbot: it has persistent memory across days and months, its own identity (its own email, GitHub account, and Slack handle), and real tools — it browses the web, reads and writes files, runs code, sends email, manages calendars, and controls a Mac. The runtime is open source (MIT) and runs in encrypted Vellum Cloud or locally on your own machine; your data stays plain-text, exportable, and deletable. Install on macOS/Linux with `curl -fsSL https://www.vellum.ai/install.sh | bash && . ~/.config/vellum/env`. Append `.md` to any docs, blog, comparison, or leaderboard URL — or request it with `Accept: text/markdown` — to receive a clean Markdown version that starts at the title, with the canonical URL in the `Link` response header.

## Product

- [Product](https://www.vellum.ai/product): Your own personal intelligence: an assistant with its own identity, memory, and skills, entirely yours to raise.
- [Platform](https://www.vellum.ai/platform): The Vellum platform: skills, channels, and enterprise-grade security for building AI agents through conversation.

## Get started

- [Documentation home](https://www.vellum.ai/docs): Human-readable documentation for users and developers.
- [Vellum docs index](https://www.vellum.ai/docs/llms.txt): Generated index of every docs page with a one-line description and its Markdown mirror.
- [Downloads](https://www.vellum.ai/downloads): Desktop app for macOS and the iOS app.
- [Source code](https://github.com/vellum-ai/vellum-assistant): Open-source (MIT) monorepo with the assistant runtime, CLI, clients, gateway, and skill catalog.
- [Pricing](https://www.vellum.ai/pricing): Plans, what each includes, and how billing works.
- [Bring your existing agent](https://www.vellum.ai/import): Migrate an agent from ChatGPT, Claude, OpenClaw, or Hermes: upload an export and your new assistant rebuilds your skills in its own workspace.
- [Getting Started](https://www.vellum.ai/md/docs/getting-started): Get started with Vellum — installation, key concepts, quick start guide, and your first skill tutorial.
- [Installation](https://www.vellum.ai/md/docs/getting-started/installation): Get started with Vellum: sign up for Vellum Cloud, install the desktop app on macOS, or self-host. System requirements, setup, and permissions.
- [Quick Start](https://www.vellum.ai/md/docs/getting-started/quick-start): Your first 2 minutes with Vellum — setup, meeting your assistant, and getting started.
- [What is Vellum?](https://www.vellum.ai/md/docs/getting-started/what-is-vellum): What is Vellum? A personal AI assistant with tools, memory, identity, and a private cloud workspace, different from ChatGPT or Claude.
- [Your First Skill](https://www.vellum.ai/md/docs/getting-started/your-first-skill): Use and create your first Vellum skill — discover built-in skills, install new ones, and build custom skills.
- [Pricing](https://www.vellum.ai/md/docs/pricing): How Vellum pricing works today: prepaid credits, pending usage, and how to add credits to your account.

## Key concepts

- [Key Concepts](https://www.vellum.ai/md/docs/key-concepts): Core Vellum concepts — workspace, skills and tools, memory and context, channels, assistant identity, and glossary.
- [Channels](https://www.vellum.ai/md/docs/key-concepts/channels): Vellum communication channels — desktop app, CLI, Telegram, Slack, email, and phone. Same assistant everywhere, adapted to each channel.
- [Memory & Context](https://www.vellum.ai/md/docs/key-concepts/memory-and-context): How Vellum remembers: workspace files, long-term memory, procedural memory as skills, the injection gate, context assembly, and privacy considerations.
- [Model Profiles](https://www.vellum.ai/md/docs/key-concepts/model-profiles): Control which LLM model and settings your assistant uses for each job — conversations, memory, background tasks — and optimize token costs with profiles and call-site overrides.
- [OAuth Integrations](https://www.vellum.ai/md/docs/key-concepts/oauth-integrations): How Vellum connects to third-party services via OAuth2: supported services, how the credential vault works, security model, and troubleshooting.
- [Scheduling](https://www.vellum.ai/md/docs/key-concepts/scheduling): How scheduling and automation work in Vellum — one-shot and recurring schedules, heartbeats, watchers, playbooks, and proactive background work.
- [Tools & Skills](https://www.vellum.ai/md/docs/key-concepts/skills-and-tools): Skills vs. tools in Vellum — atomic actions, capability bundles, built-in skills, and creating custom skills.
- [The Workspace](https://www.vellum.ai/md/docs/key-concepts/the-workspace): The Vellum workspace — folder structure, IDENTITY.md, SOUL.md, USER.md, LOOKS.md, config.json, and skills directory.
- [Web Search](https://www.vellum.ai/md/docs/key-concepts/web-search): How web search works in Vellum: managed vs bring your own, the four built-in providers (Provider Native, Perplexity, Brave, Tavily), the fallback chain, and how it's billed.
- [Brave Search](https://www.vellum.ai/md/docs/key-concepts/web-search/brave): How to connect Brave Search as your web search provider in Vellum: API key setup, provider configuration, and usage.
- [Firecrawl](https://www.vellum.ai/md/docs/key-concepts/web-search/firecrawl): How to connect Firecrawl as your web search and web fetch provider in Vellum: API key setup, provider configuration, and usage.
- [Perplexity](https://www.vellum.ai/md/docs/key-concepts/web-search/perplexity): How to connect Perplexity as your web search provider in Vellum: API key setup, provider configuration, and usage.
- [Tavily](https://www.vellum.ai/md/docs/key-concepts/web-search/tavily): How to connect Tavily as your web search provider in Vellum: API key setup, provider configuration, and usage.

## Developer guide

- [Developer Guide](https://www.vellum.ai/md/docs/developer-guide): Technical reference for contributors and developers working on the Vellum Assistant platform.
- [API & Communication](https://www.vellum.ai/md/docs/developer-guide/api): SSE event stream, event payloads, connection management, and remote access via SSH.
- [Architecture](https://www.vellum.ai/md/docs/developer-guide/architecture): Platform domains, repository structure, and how the runtime, clients, and gateway fit together.
- [Contributing](https://www.vellum.ai/md/docs/developer-guide/contributing): How to set up the Vellum Assistant repo locally, run tests, follow code conventions, and submit a pull request.
- [Development Workflow](https://www.vellum.ai/md/docs/developer-guide/development-workflow): Claude Code slash commands, parallel PR execution, automated review loops, and the release pipeline.
- [Features & Capabilities](https://www.vellum.ai/md/docs/developer-guide/features): Integrations, dynamic skill authoring, browser automation, attachments, and media embeds.
- [Get Started](https://www.vellum.ai/md/docs/developer-guide/get-started): Developer on-ramp for Vellum Assistant: repo layout, local dev setup, CLI, HTTP API, and SSE event stream.
- [Security & Permissions](https://www.vellum.ai/md/docs/developer-guide/security): Sandbox model, credential storage, trust rules, and permission modes for the Vellum Assistant platform.

## Extensibility

- [Skills catalog](https://www.vellum.ai/skills): Installable skills that extend what the assistant can do, browsable by category; per-skill pages are listed in the sitemap.
- [Plugins](https://www.vellum.ai/plugins): Plugin catalog for extending the assistant runtime.
- [Extensibility](https://www.vellum.ai/md/docs/extensibility): All of the ways your Assistant can build on themselves. Overview of the surfaces a plugin can bundle and how they compose.
- [Apps](https://www.vellum.ai/md/docs/extensibility/apps): Apps let a plugin ship persistent, interactive UI (dashboards, tools, games) served in the workspace panel, built as compiled React.
- [Distribution](https://www.vellum.ai/md/docs/extensibility/distribution): How plugins ship: a curated marketplace catalog, installing by name from the CLI, installing directly from a GitHub URL (untrusted), the marketplace.json manifest, and why entries pin an immutable commit.
- [Hooks](https://www.vellum.ai/md/docs/extensibility/hooks): Lifecycle hooks let a plugin run code at fixed points during the Assistant's lifecycle.
- [Plugins](https://www.vellum.ai/md/docs/extensibility/plugins): How a plugin is laid out on disk, what its package.json manifest declares, and the single @vellumai/plugin-api package every surface imports from.
- [Routes](https://www.vellum.ai/md/docs/extensibility/routes): Routes let a plugin serve HTTP endpoints (webhooks, integrations, callbacks) in its own /x/plugins/<name>/ namespace.
- [Skills](https://www.vellum.ai/md/docs/extensibility/skills): Skills let a plugin bundle instructions, assets, and scripts the Assistant loads on demand when a conversation matches what the skill is for.
- [Tools](https://www.vellum.ai/md/docs/extensibility/tools): Tools let a plugin add new actions the model can call, landing in the same catalog as the Assistant's built-in tools.

## Skills reference

- [Skills Reference](https://www.vellum.ai/md/docs/skills-reference): Vellum skills reference — documentation for all available skills, capabilities, and configuration options.
- [ACP](https://www.vellum.ai/md/docs/skills-reference/acp): ACP skill for Vellum — delegates development tasks through the Agent Client Protocol.
- [Amazon](https://www.vellum.ai/md/docs/skills-reference/amazon): Amazon skill for Vellum — shop, track orders, and manage your Amazon account through your assistant.
- [App Builder](https://www.vellum.ai/md/docs/skills-reference/app-builder): App Builder skill for Vellum — create interactive web apps with HTML, CSS, and JavaScript through conversation.
- [Browser](https://www.vellum.ai/md/docs/skills-reference/browser): Browser skill for Vellum — navigate web pages, interact with content, and extract information.
- [ChatGPT Import](https://www.vellum.ai/md/docs/skills-reference/chatgpt-import): ChatGPT Import skill for Vellum — imports your conversation history from ChatGPT into Vellum.
- [Computer Use](https://www.vellum.ai/md/docs/skills-reference/computer-use): Computer Use skill for Vellum — control your Mac directly with screen observation, clicking, typing, and AppleScript.
- [Contacts](https://www.vellum.ai/md/docs/skills-reference/contacts): Contacts skill for Vellum — manage contacts, communication channels, access control, and invite links.
- [Document](https://www.vellum.ai/md/docs/skills-reference/document): Document skill for Vellum — create and edit long-form text in a dedicated rich-text editor with Markdown support.
- [DoorDash](https://www.vellum.ai/md/docs/skills-reference/doordash): DoorDash skill for Vellum — order food, groceries, and convenience items through your assistant.
- [Email (AgentMail)](https://www.vellum.ai/md/docs/skills-reference/email-agentmail): Email skill for Vellum — send, read, search, and manage email from your assistant's own address.
- [Followups](https://www.vellum.ai/md/docs/skills-reference/followups): Followups skill for Vellum — tracks messages awaiting responses across all communication channels.
- [Gmail](https://www.vellum.ai/md/docs/skills-reference/gmail): Gmail skill for Vellum — full inbox management including archive, label, draft, send, and filter capabilities.
- [Google Calendar](https://www.vellum.ai/md/docs/skills-reference/google-calendar): Google Calendar skill for Vellum — view events, create meetings, and check availability.
- [Image Studio](https://www.vellum.ai/md/docs/skills-reference/image-studio): Image Studio skill for Vellum — generate and edit images using AI through your assistant.
- [Media Processing](https://www.vellum.ai/md/docs/skills-reference/media-processing): Media Processing skill for Vellum — processes video, audio, and image files through a multi-phase AI pipeline.
- [Messaging](https://www.vellum.ai/md/docs/skills-reference/messaging): Messaging skill for Vellum — send and receive messages across Slack, Gmail, and Telegram.
- [Notifications](https://www.vellum.ai/md/docs/skills-reference/notifications): Notifications skill for Vellum — sends notifications through a unified routing system across connected channels.
- [Phone Calls](https://www.vellum.ai/md/docs/skills-reference/phone-calls): Phone Calls skill for Vellum — make and receive calls via Twilio with real-time voice conversation and transcription.
- [Playbooks](https://www.vellum.ai/md/docs/skills-reference/playbooks): Playbooks skill for Vellum — trigger-action automation rules for handling incoming messages.
- [Schedule](https://www.vellum.ai/md/docs/skills-reference/schedule): Schedule skill for Vellum — recurring and one-shot scheduled actions using cron syntax, RRULE patterns, or simple timestamps.
- [Screen Watch](https://www.vellum.ai/md/docs/skills-reference/screen-watch): Screen Watch skill for Vellum — observe your screen at regular intervals with OCR for context-aware assistance.
- [Skill Management](https://www.vellum.ai/md/docs/skills-reference/skill-management): Skill Management skill for Vellum — creates and deletes custom managed skills to extend your assistant.
- [Slack](https://www.vellum.ai/md/docs/skills-reference/slack): Slack skill for Vellum — scan channels, summarize threads, manage reactions, and configure privacy-aware integration.
- [Start the Day](https://www.vellum.ai/md/docs/skills-reference/start-the-day): Start the Day skill for Vellum — get a personalized daily briefing with weather, news, and tasks.
- [Subagent](https://www.vellum.ai/md/docs/skills-reference/subagent): Subagent skill for Vellum — spawns autonomous background agents that work independently on tasks.
- [Tasks](https://www.vellum.ai/md/docs/skills-reference/tasks): Tasks skill for Vellum — a two-layer task system with reusable templates and a prioritized work queue.
- [Transcribe](https://www.vellum.ai/md/docs/skills-reference/transcribe): Transcribe skill for Vellum — transcribes audio and video files using OpenAI Whisper or whisper.cpp.
- [Watcher](https://www.vellum.ai/md/docs/skills-reference/watcher): Watcher skill for Vellum — polls external services for changes and notifies you when something happens.
- [Weather](https://www.vellum.ai/md/docs/skills-reference/weather): Weather skill for Vellum — get current conditions and forecasts for any location.

## Trust and security

- [Trust & Security](https://www.vellum.ai/md/docs/trust-security): Vellum trust and security — privacy, data handling, permissions, and deployment best practices.
- [Privacy & Data](https://www.vellum.ai/md/docs/trust-security/privacy-and-data): Vellum privacy and data — what stays local, what leaves your device, and what Vellum never does.
- [Security Best Practices](https://www.vellum.ai/md/docs/trust-security/security-best-practices): Security best practices for Vellum — sharing information, reviewing files, permissions, and credentials.
- [The Permissions Model](https://www.vellum.ai/md/docs/trust-security/the-permissions-model): Vellum's permissions model — risk tolerance tiers, sandbox boundary, trust rules, and the Allow/Deny permission prompt.
- [Privacy Notice](https://www.vellum.ai/md/docs/privacy-policy): Vellum's privacy notice explaining how we collect, use, disclose and otherwise process your information.
- [Vellum Terms of Service](https://www.vellum.ai/md/docs/vellum-terms-of-use): Vellum's terms of service — the agreement governing your use of the Vellum AI agent platform and services.
- [Vellum Prohibited Use Policy](https://www.vellum.ai/md/docs/prohibited-use): Vellum's prohibited use policy — ensuring the Services are used safely, ethically, and in accordance with all applicable laws and regulations.

## Hosting

- [Hosting options](https://www.vellum.ai/md/docs/hosting-options): Choose where your assistant runs: Vellum Cloud (recommended), local on your Mac, or self-hosted on your own infrastructure.
- [Advanced options](https://www.vellum.ai/md/docs/hosting-options/advanced-options): Advanced hosting options for Vellum assistants: Local Apple Container, GCP, and AWS.
- [Cloud hosting](https://www.vellum.ai/md/docs/hosting-options/cloud-hosting): Run your assistant on Vellum Cloud: always-on, sandboxed per account, reachable from web, desktop, voice, and chat channels.
- [Local hosting](https://www.vellum.ai/md/docs/hosting-options/local-hosting): Run your assistant locally on your Mac with setup guidance, tradeoffs, and best practices.
- [Environments](https://www.vellum.ai/md/docs/environments): Choose a deployment environment for Vellum: Vellum Cloud (recommended), local, or user-hosted (GCP/AWS/custom), with trade-offs for each.

## LLM leaderboards

- [LLM Leaderboard](https://www.vellum.ai/llm-leaderboard): Benchmark rankings for frontier models across reasoning, coding, and math, with throughput, latency, cost, and context-window specs.
- [LLM Leaderboard data](https://www.vellum.ai/md/llm-leaderboard): The same rankings and model specs as Markdown tables.
- [Open LLM Leaderboard](https://www.vellum.ai/open-llm-leaderboard): The same benchmark rankings restricted to open-source and open-weight models.
- [Open LLM Leaderboard data](https://www.vellum.ai/md/open-llm-leaderboard): Open-model rankings and specs as Markdown tables.
- [Best LLM for coding](https://www.vellum.ai/best-llm-for-coding): Coding-specific rankings — SWE-Bench, LiveCodeBench, Aider Polyglot, and BFCL tool use.
- [Best LLM for coding data](https://www.vellum.ai/md/best-llm-for-coding): Coding benchmark rankings as Markdown tables.
- [AI assistants leaderboard](https://www.vellum.ai/llm-leaderboard/ai-assistants): Personal AI assistant platforms ranked across channels, memory, security, hosting, and integrations.
- [AI assistants leaderboard data](https://www.vellum.ai/md/llm-leaderboard/ai-assistants): The assistant comparison as Markdown tables.

## Compare assistants

- [Compare AI assistants](https://www.vellum.ai/compare-assistants): Side-by-side comparisons of personal AI assistant platforms; each comparison page has a Markdown mirror.

## Blog and roadmap

- [Blog](https://www.vellum.ai/blog): Articles on AI agents, assistant memory, and LLMs; every post has a Markdown mirror.
- [Vellum blog index](https://www.vellum.ai/blog/llms.txt): Generated index of every blog post with a one-line description and its Markdown mirror.
- [Roadmap](https://www.vellum.ai/roadmap): What has shipped and what is planned.
- [Roadmap](https://www.vellum.ai/md/docs/roadmap): What's coming to Vellum — shipping soon, up next, on the horizon, and what we're exploring.

## Company

- [About us](https://www.vellum.ai/about-us): The team behind Vellum and the mission: AI assistants anyone can create through natural conversation.
- [Team](https://www.vellum.ai/team): The people building Vellum and the assistants that work alongside them.
- [Community](https://www.vellum.ai/community): Where Vellum users connect, share ideas, and show what their assistants can do.
- [Showcase](https://www.vellum.ai/showcase): Real stories of what people and their assistants do together.
- [Branding guide](https://www.vellum.ai/branding-guide): Vellum brand colors, typography, and visual reference.

## Site metadata

- [Sitemap](https://www.vellum.ai/sitemap.xml): Full URL inventory — docs, blog posts, skills, and leaderboards.
- [Robots](https://www.vellum.ai/robots.txt): Crawl policy.

## Optional

- [Webinars](https://www.vellum.ai/webinars): Recorded webinars and live sessions on using Vellum.
- [LLM parameters guide](https://www.vellum.ai/llm-parameters-guide): Overview of every LLM request parameter, grouped by what it controls.
- [Temperature](https://www.vellum.ai/llm-parameters/temperature): LLM sampling parameter — behavior, trade-offs, and provider support.
- [Top-p](https://www.vellum.ai/llm-parameters/top-p): LLM sampling parameter — behavior, trade-offs, and provider support.
- [Top-k](https://www.vellum.ai/llm-parameters/top-k): LLM sampling parameter — behavior, trade-offs, and provider support.
- [Max tokens](https://www.vellum.ai/llm-parameters/max-tokens): LLM output limits parameter — behavior, trade-offs, and provider support.
- [Stop sequence](https://www.vellum.ai/llm-parameters/stop-sequence): LLM output limits parameter — behavior, trade-offs, and provider support.
- [Frequency penalty](https://www.vellum.ai/llm-parameters/frequency-penalty): LLM repetition & bias parameter — behavior, trade-offs, and provider support.
- [Presence penalty](https://www.vellum.ai/llm-parameters/presence-penalty): LLM repetition & bias parameter — behavior, trade-offs, and provider support.
- [Logit bias](https://www.vellum.ai/llm-parameters/logit-bias): LLM repetition & bias parameter — behavior, trade-offs, and provider support.
- [JSON mode](https://www.vellum.ai/llm-parameters/json-mode): LLM structured output parameter — behavior, trade-offs, and provider support.
- [Structured outputs](https://www.vellum.ai/llm-parameters/structured-outputs): LLM structured output parameter — behavior, trade-offs, and provider support.
- [Function calling](https://www.vellum.ai/llm-parameters/function-calling): LLM structured output parameter — behavior, trade-offs, and provider support.
- [Seed](https://www.vellum.ai/llm-parameters/seed): LLM debugging parameter — behavior, trade-offs, and provider support.
- [Logprobs](https://www.vellum.ai/llm-parameters/logprobs): LLM debugging parameter — behavior, trade-offs, and provider support.
- [LLM streaming](https://www.vellum.ai/llm-parameters/llm-streaming): LLM performance parameter — behavior, trade-offs, and provider support.
- [Prompt caching](https://www.vellum.ai/llm-parameters/prompt-caching): LLM performance parameter — behavior, trade-offs, and provider support.
- [Reasoning effort](https://www.vellum.ai/llm-parameters/reasoning-effort): LLM reasoning parameter — behavior, trade-offs, and provider support.
- [Thinking tokens](https://www.vellum.ai/llm-parameters/thinking-tokens): LLM reasoning parameter — behavior, trade-offs, and provider support.
- [Help](https://www.vellum.ai/md/docs/help): Get help with Vellum — frequently asked questions, common issues, and support channels.
- [Common Issues](https://www.vellum.ai/md/docs/help/common-issues): Troubleshoot common Vellum issues — installation, permissions, skills, performance, and workspace problems.
- [FAQ](https://www.vellum.ai/md/docs/help/faq): Frequently asked questions about Vellum — product capabilities, privacy, data handling, and your assistant.
- [Getting Help](https://www.vellum.ai/md/docs/help/getting-help): How to get help with Vellum — community, GitHub issues, email support, and what information to include.
- [Glossary](https://www.vellum.ai/md/docs/glossary): Vellum glossary — shared definitions for assistant, guardian, personal intelligence, memory, skills, channels, gateway, and other key terms.
- [Vellum Constitution](https://www.vellum.ai/md/docs/constitution): The Vellum Constitution — our purpose, worldview, principles, and the commitments that guide every product, design, and engineering decision we make.
- [Releases](https://www.vellum.ai/md/docs/releases): Vellum release notes, versioning, update channels, and how to stay up to date with the latest features and fixes.