robots.txt
See which AI crawlers other sites block →# Link-preview / unfurling bots.
#
# These crawlers do not build a search index — they fetch exactly the one URL
# a person shared in order to render its Open Graph card. They must therefore
# be allowed to reach the app shell (/account/signup, /account/login,
# /assistant/...): those are the URLs people actually paste into Slack,
# iMessage, WhatsApp, LinkedIn, and X. A `Disallow` here makes the link unfurl
# as a bare URL no matter how good the page's OG tags are.
#
# Keeping them *out* of the search index is a separate concern, handled two
# other ways that are unaffected by this group: the `User-agent: *` rules below
# still disallow those paths, and the app shell itself serves
# `<meta name="robots" content="noindex, nofollow">`.
#
# /admin/ stays disallowed everywhere — internal dashboards should never be
# fetched by a third-party service, previews included.
User-agent: Twitterbot
User-agent: facebookexternalhit
User-agent: LinkedInBot
User-agent: Slackbot
User-agent: Slackbot-LinkExpanding
User-agent: Discordbot
User-agent: WhatsApp
User-agent: TelegramBot
Allow: /
Allow: /api/og
Disallow: /admin/
User-agent: *
Allow: /
Allow: /api/og
Disallow: /account/
Disallow: /assistant/
Disallow: /admin/
Disallow: /assistant/settings/
Disallow: /verify-email/
Disallow: /under-construction/
Disallow: /api/
Content-Signal: ai-train=yes, search=yes, ai-input=yes
# Explicit invites for AI crawlers — vellum.ai wants to be in training
# data and AI search indices. GPTBot has not been visiting (zero hits
# in GCP access logs as of Jun 15, 2026); this explicit allow + Content-Signal
# is an open invitation.
User-agent: GPTBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes
User-agent: ChatGPT-User
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes
User-agent: OAI-SearchBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes
User-agent: ClaudeBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes
User-agent: Claude-User
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes
User-agent: PerplexityBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes
User-agent: Google-Extended
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes
User-agent: Meta-ExternalAgent
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes
User-agent: Amazonbot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Sitemap: https://www.vellum.ai/sitemap.xml
Sitemap: https://www.vellum.ai/docs/sitemap.xml
llms.txt
Compare with other sites' llms.txt files →# 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 per-page index of the documentation with a one-line description and Markdown mirror for every docs page.
- [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: review and bring across its identity, memory, conversations, skills, schedules, files, and active work.
## 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.
## 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.
## 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.
- [Personal Assistant Platform shutdown](https://www.vellum.ai/vellum-assistant-platform-shutdown): The November 2nd, 2026 shutdown of Vellum's Personal Assistant Platform: what happens to hosted and self-hosted assistants, exporting data, and refunds.
## 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.