Rank #3 of 5 in Developer Docs Platforms
Showcase


Try itExperimental
See what an agent can do with GitBook before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); the live MCP handshake runs real requests from our edge, right now — including, where the server allows it, one real read-only tool call (bring your own key for auth-gated servers); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$curl -s -X POST 'https://gitbook.com/docs/~gitbook/mcp' -H 'Content-Type: application/json' -d '<jsonrpc initialize>' # the MCP server GitBook auto-generates for every published site, on its own docsrecorded session — replayed, not liveVerified integrations
Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.
By theme — the product's score on each story themeBy theme
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Ai docs — stories about ai docs in this arenaAi docsevidence →
Stories about ai docs in this arena
Analytics insights — stories about analytics insights in this arenaAnalytics insightsevidence →
Stories about analytics insights in this arena
Api reference — stories about api reference in this arenaApi referenceevidence →
Stories about api reference in this arena
Authoring editing — stories about authoring editing in this arenaAuthoring editingevidence →
Stories about authoring editing in this arena
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Collaboration review — stories about collaboration review in this arenaCollaboration reviewevidence →
Stories about collaboration review in this arena
Customization — bending the product to your needs — settings, theming, extension pointsCustomizationevidence →
Bending the product to your needs — settings, theming, extension points
Docs as code — stories about docs as code in this arenaDocs as codeevidence →
Stories about docs as code in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Publishing hosting — stories about publishing hosting in this arenaPublishing hostingevidence →
Stories about publishing hosting in this arena
Search discovery — stories about search discovery in this arenaSearch discoveryevidence →
Stories about search discovery in this arena
Versioning localization — stories about versioning localization in this arenaVersioning localizationevidence →
Stories about versioning localization in this arena
Story verdicts — every judged story with its evidenceStory verdicts
Follow the green: where the map greys out is where GitBook stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
✓8/10
unlocks → Webhooks · Official SDKs · Scoped API keys · Machine-readable spec · Versioning policy
Subscribe to events via webhooks
—0/10
Build against official SDKs
—0/10
Issue scoped/least-privilege API credentials for an agent
—0/10
Connect an agent via an official MCP server
✓8/10
Download a machine-readable API spec (OpenAPI or equivalent)
—0/10
Rely on versioned APIs with a documented deprecation policy
—0/10
Test against a sandbox environment without touching production data
n/an/a
Explore an interactive API reference with runnable examples
✓7/10
Docs for agents
Point an agent at llms.txt or agent-oriented docs
✓8/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
✓7/10
unlocks → MCP client
Operate the product with natural-language commands
✓8/10
Plug MCP servers into this product so it can use their tools
—0/10
Get AI-generated insights and suggestions from my data inside the product
✓7/10
Set up automations that run autonomously in the background
~5/10
Ai docs — stories about ai docs in this arenaAi docs
Stories about ai docs in this arena
My published docs site exposes its own MCP server that my users' agents can query for search and page content
✓7/10
Agent output
An embedded AI assistant on my docs site answers reader questions with citations into my content
✓8/10
A platform AI agent drafts, updates, and reviews my docs — from a prompt, a PR, or a schedule — and ships its work as change requests
✓7/10
Analytics insights — stories about analytics insights in this arenaAnalytics insights
Stories about analytics insights in this arena
Api reference — stories about api reference in this arenaApi reference
Stories about api reference in this arena
Authoring editing — stories about authoring editing in this arenaAuthoring editing
Stories about authoring editing in this arena
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Collaboration review — stories about collaboration review in this arenaCollaboration review
Stories about collaboration review in this arena
Customization — bending the product to your needs — settings, theming, extension pointsCustomization
Bending the product to your needs — settings, theming, extension points
Docs as code — stories about docs as code in this arenaDocs as code
Stories about docs as code in this arena
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Publishing hosting — stories about publishing hosting in this arenaPublishing hosting
Stories about publishing hosting in this arena
Search discovery — stories about search discovery in this arenaSearch discovery
Stories about search discovery in this arena
Versioning localization — stories about versioning localization in this arenaVersioning localization
Stories about versioning localization in this arena
Sorted by importance (agentic first) (high → low) · 53/53 stories · click a row’s chevron for the rationale and evidence
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 8/10 | Tprobed | |
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 8/10 | Tprobed | |
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 7/10 | Cclaimed | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ||
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 7/10 | Cclaimed | |
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 7/10 | Cclaimed | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 7/10 | Cclaimed | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Xcommunity | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Cclaimed | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | n/a | untested | none yet | |
My docs live in my own git repository — branches, pull requests, and merges drive what gets published C Git workflow | developer | Docs as code — stories about docs as code in this arenaDocs as code | 3 | full | 8/10 | Xcommunity | |
My published docs site automatically serves llms.txt (and a full-content variant) so agents can index it C Agent output | ai-native user | Ai docs — stories about ai docs in this arenaAi docs | 3 | full | 8/10 | Tprobed | |
Every published page serves clean markdown at its URL (e.g. appending .md) so agents skip the HTML C Agent output | ai-native user | Ai docs — stories about ai docs in this arenaAi docs | 3 | full | 7/10 | Tprobed | |
I author pages in Markdown/MDX with rich components — tabs, callouts, code groups, steps — without writing custom HTML C Authoring | technical writer | Authoring editing — stories about authoring editing in this arenaAuthoring editing | 3 | partial | 7/10 | Xcommunity | |
My published docs site exposes its own MCP server that my users' agents can query for search and page content C Agent access | ai-native user | Ai docs — stories about ai docs in this arenaAi docs | 3 | full | 7/10 | Tprobed | |
I publish versioned documentation per product or API version, and readers switch versions from the site C Versioning | developer | Versioning localization — stories about versioning localization in this arenaVersioning localization | 3 | partial | 6/10 | Cclaimed | |
My API reference pages are generated from an OpenAPI spec and stay in sync when the spec changes C Spec driven | developer | Api reference — stories about api reference in this arenaApi reference | 3 | partial | 6/10 | Cclaimed | |
Readers get fast, typo-tolerant, relevance-ranked search over the whole docs site out of the box C Search | developer | Search discovery — stories about search discovery in this arenaSearch discovery | 3 | partial | 6/10 | Xcommunity | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | partial | 5/10 | Xcommunity | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | 0/10 | ||
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | none | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | none | untested | none yet | |
An embedded AI assistant on my docs site answers reader questions with citations into my content C Assistant | ai-native user | Ai docs — stories about ai docs in this arenaAi docs | 2 | full | 8/10 | Cclaimed | |
I serve docs on my own custom domain or as a /docs subpath of my main site C Domains | devrel lead | Publishing hosting — stories about publishing hosting in this arenaPublishing hosting | 2 | full | 8/10 | Cclaimed | |
Non-technical teammates can edit docs in a visual web editor without touching git, and their changes flow into the same source of truth C Authoring | technical writer | Authoring editing — stories about authoring editing in this arenaAuthoring editing | 2 | full | 8/10 | Xcommunity | |
Teammates propose changes that go through review — comments, approvals, and a merge step — before they publish C Review | technical writer | Collaboration review — stories about collaboration review in this arenaCollaboration review | 2 | full | 8/10 | Cclaimed | |
A platform AI agent drafts, updates, and reviews my docs — from a prompt, a PR, or a schedule — and ships its work as change requests C Writer agent | ai-native user | Ai docs — stories about ai docs in this arenaAi docs | 2 | full | 7/10 | Cclaimed | |
Every docs pull request gets a shareable preview deployment before it merges C Git workflow | developer | Docs as code — stories about docs as code in this arenaDocs as code | 2 | full | 7/10 | Cclaimed | |
Readers can try real API calls from an interactive playground embedded in the reference docs C Playground | developer | Api reference — stories about api reference in this arenaApi reference | 2 | full | 7/10 | Cclaimed | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 6/10 | Tprobed | |
I see page views, search terms, and reader feedback so I know which docs work and which fail C Analytics | devrel lead | Analytics insights — stories about analytics insights in this arenaAnalytics insights | 2 | partial | 5/10 | Xcommunity | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 5/10 | Tprobed | |
I customize themes, fonts, and layout — down to custom CSS/JS or my own components — so the docs match my brand C Theming | devrel lead | Customization — bending the product to your needs — settings, theming, extension pointsCustomization | 2 | partial | 4/10 | Xcommunity | |
Export my entire docs site as a static bundle and host it anywhere, so my content is never locked in C Portability | developer | Publishing hosting — stories about publishing hosting in this arenaPublishing hosting | 2 | none | 0/10 | ||
My docs analytics distinguish AI-agent traffic from human traffic so I can see who — or what — is actually reading C Analytics | ai-native user | Analytics insights — stories about analytics insights in this arenaAnalytics insights | 2 | none | 0/10 | ||
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | 0/10 | ||
Automated checks lint my content against a style guide and flag issues before they publish C Quality | technical writer | Authoring editing — stories about authoring editing in this arenaAuthoring editing | 2 | none | untested | none yet | |
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
CI validation catches broken links and invalid configuration before the site publishes C Quality gates | developer | Docs as code — stories about docs as code in this arenaDocs as code | 2 | none | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | n/a | untested | none yet | |
Reusable snippets and variables keep repeated content in sync across pages C Content reuse | technical writer | Authoring editing — stories about authoring editing in this arenaAuthoring editing | 1 | full | 8/10 | Cclaimed | |
I gate some or all docs behind authentication — password, JWT, or SSO — for customers-only content G Access control | devrel lead | Publishing hosting — stories about publishing hosting in this arenaPublishing hosting | 1 | partial | 6/10 | Cclaimed | |
I publish my docs in multiple languages with translated navigation and content C Localization | technical writer | Versioning localization — stories about versioning localization in this arenaVersioning localization | 1 | partial | 6/10 | Xcommunity | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | partial | 5/10 | Cclaimed |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 31 stories with headroom
What would move GitBook’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
Evidence documents GitBook publishing its own MCP server so external AI agents (Claude Code, Cursor, etc.) can call GitBook's tools (gitbook-docs-14, gitbook-docs-15, gitbook-docs-33, gitbook-probe-4) — this is GitBook acting as an MCP server, not as an MCP client consuming external servers' tools.
Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events
nonemoves PA Scoreimpact 30
Missing: any documented rules/trigger builder, webhook or event-condition-action framework, or examples of users defining custom automation logic.
Openness — open source, data portability, and self-hosting storiesSelf-host the core product
nonemoves PA Scoreimpact 30
GitBook is documented and confirmed by community evidence as a SaaS-only platform; multiple users explicitly note GitBook 'moved everything to their SaaS with artificial barriers to just using the software' and abandoned its open-source spirit, with the CLI 'no longer under active development.' No vendor documentation anywhere offers a self-hosted deployment option for the core product.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
Missing: any privacy policy or settings documentation on opting out of AI training, contractual/DPA language about training data use, or third-party confirmation of such a control.
Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent
nonemoves agent-readyimpact 30
GitBook exposes a general REST API and an MCP server for AI agents, but no evidence describes scoped or least-privilege API credentials/tokens, granular permission scopes, or agent-specific access controls for its API keys — only generic 'authenticated access' for site audiences is mentioned, which is unrelated to credential scoping.
Agenticness — how well agents can access and operate the productBuild against official SDKs
nonemoves agent-readyimpact 30
Missing: any official SDK documentation, package registry listings, or language-specific client libraries.
Agenticness — how well agents can access and operate the productSubscribe to events via webhooks
nonemoves agent-readyimpact 30
No evidence of webhook subscription capability appears anywhere in the pack; GitBook's API reference mentions only REST methods (GET/POST/PATCH/DELETE) with no mention of webhooks or event subscriptions, and probes for OpenAPI specs failed.
Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)
nonemoves API qualityimpact 30
Probes explicitly show all candidate OpenAPI/spec endpoints (openapi.json, swagger.json, etc.) return 404, and there is no documentation link to download a machine-readable spec of GitBook's own API — the 'Add an OpenAPI specification' docs describe a feature for customers embedding specs in their own docs, not GitBook's own API spec.
Showing the top 8 of 31 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map8 surfaces · 34 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
docs34 stories
- Point an agent at llms.txt or agent-oriented docs
- Run the product headlessly / in CI for automation
- Connect an agent via an official MCP server
- Use an official CLI
- Drive the product through a documented public API
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Explore an interactive API reference with runnable examples
- My published docs site exposes its own MCP server that my users' agents can query for search and page content
- My published docs site automatically serves llms.txt (and a full-content variant) so agents can index it
- Every published page serves clean markdown at its URL (e.g. appending .md) so agents skip the HTML
- An embedded AI assistant on my docs site answers reader questions with citations into my content
- A platform AI agent drafts, updates, and reviews my docs — from a prompt, a PR, or a schedule — and ships its work as change requests
- I see page views, search terms, and reader feedback so I know which docs work and which fail
- Readers can try real API calls from an interactive playground embedded in the reference docs
- My API reference pages are generated from an OpenAPI spec and stay in sync when the spec changes
- I author pages in Markdown/MDX with rich components — tabs, callouts, code groups, steps — without writing custom HTML
- Non-technical teammates can edit docs in a visual web editor without touching git, and their changes flow into the same source of truth
- Reusable snippets and variables keep repeated content in sync across pages
- Perform bulk operations across many items at once
- Version, review, and roll back my automations
- Teammates propose changes that go through review — comments, approvals, and a merge step — before they publish
- I customize themes, fonts, and layout — down to custom CSS/JS or my own components — so the docs match my brand
- My docs live in my own git repository — branches, pull requests, and merges drive what gets published
- Every docs pull request gets a shareable preview deployment before it merges
- Do everything through the API that I can do in the UI
- Export all of my data in open formats and leave
- I gate some or all docs behind authentication — password, JWT, or SSO — for customers-only content
- I serve docs on my own custom domain or as a /docs subpath of my main site
- Readers get fast, typo-tolerant, relevance-ranked search over the whole docs site out of the box
- I publish my docs in multiple languages with translated navigation and content
- I publish versioned documentation per product or API version, and readers switch versions from the site
Pricing docs13 stories
- Explore an interactive API reference with runnable examples
- An embedded AI assistant on my docs site answers reader questions with citations into my content
- I see page views, search terms, and reader feedback so I know which docs work and which fail
- Readers can try real API calls from an interactive playground embedded in the reference docs
- My API reference pages are generated from an OpenAPI spec and stay in sync when the spec changes
- I author pages in Markdown/MDX with rich components — tabs, callouts, code groups, steps — without writing custom HTML
- Non-technical teammates can edit docs in a visual web editor without touching git, and their changes flow into the same source of truth
- Teammates propose changes that go through review — comments, approvals, and a merge step — before they publish
- I customize themes, fonts, and layout — down to custom CSS/JS or my own components — so the docs match my brand
- My docs live in my own git repository — branches, pull requests, and merges drive what gets published
- Every docs pull request gets a shareable preview deployment before it merges
- I serve docs on my own custom domain or as a /docs subpath of my main site
- Readers get fast, typo-tolerant, relevance-ranked search over the whole docs site out of the box
Features docs11 stories
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- An embedded AI assistant on my docs site answers reader questions with citations into my content
- A platform AI agent drafts, updates, and reviews my docs — from a prompt, a PR, or a schedule — and ships its work as change requests
- I author pages in Markdown/MDX with rich components — tabs, callouts, code groups, steps — without writing custom HTML
- Non-technical teammates can edit docs in a visual web editor without touching git, and their changes flow into the same source of truth
- Version, review, and roll back my automations
- Teammates propose changes that go through review — comments, approvals, and a merge step — before they publish
- My docs live in my own git repository — branches, pull requests, and merges drive what gets published
- Export all of my data in open formats and leave
Hacker News9 stories
- Run the product headlessly / in CI for automation
- I see page views, search terms, and reader feedback so I know which docs work and which fail
- I author pages in Markdown/MDX with rich components — tabs, callouts, code groups, steps — without writing custom HTML
- Non-technical teammates can edit docs in a visual web editor without touching git, and their changes flow into the same source of truth
- I customize themes, fonts, and layout — down to custom CSS/JS or my own components — so the docs match my brand
- My docs live in my own git repository — branches, pull requests, and merges drive what gets published
- Export all of my data in open formats and leave
- Readers get fast, typo-tolerant, relevance-ranked search over the whole docs site out of the box
- I publish my docs in multiple languages with translated navigation and content
llms.txt3 stories
gitbook.com3 stories
OpenAPI spec2 stories
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$curl -s -X POST 'https://gitbook.com/docs/~gitbook/mcp' -H 'Content-Type: application/json' -d '<jsonrpc initialize>' # the MCP server GitBook auto-generates for every published site, on its own docsreproduced$ curl -s -X POST 'https://gitbook.com/docs/~gitbook/mcp' -H 'Content-Type: application/json' -d '<jsonrpc initialize>' # the MCP server GitBook auto-generates for every published site, on its own docs
event: message
data: {"result":{"protocolVersion":"2025-06-18","capabilities":{"tools":{"listChanged":true}},"serverInfo":{"name":"mcp-typescript server on vercel","version":"0.1.0"}},"jsonrpc":"2.0","id":1}
$curl -si -X POST https://mcp.gitbook.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced$ curl -si -X POST https://mcp.gitbook.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'
HTTP/2 401
date: Tue, 08 Sep 2026 19:45:04 GMT
content-type: application/json
content-length: 71
www-authenticate: Bearer resource_metadata="https://mcp.gitbook.com/.well-known/oauth-protected-resource"
vary: accept-encoding
server: cloudflare
cf-ray: a38073911bd9787f-SJC
alt-svc: h3=":443"; ma=86400
{"error":"unauthorized","error_description":"Authentication required."}
$curl -sL https://gitbook.com/docs/llms.txt | head -6reproduced$ curl -sL https://gitbook.com/docs/llms.txt | head -6 # GitBook Documentation ## Documentation - [GitBook documentation](https://gitbook.com/docs/readme.md): Create and publish AI-native documentation your users will love. GitBook gives you intelligent tools to build product guides, API references, and documentation that improves over time. - [Quickstart](https://gitbook.com/docs/getting-started/quickstart.md): Get up and running in GitBook and publish your first docs site in minutes
$curl -sL https://gitbook.com/docs/getting-started/quickstart.md | head -5reproduced$ curl -sL https://gitbook.com/docs/getting-started/quickstart.md | head -5 > For the complete documentation index, see [llms.txt](https://gitbook.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://gitbook.com/docs/getting-started/quickstart.md). # Quickstart Get up and running in GitBook and publish your first docs site in minutes
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
10 of 24 testable claims verified · 0 contradicted → integrity 42/100
28 distinct capability claims found in GitBook’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
10
Verified
14
Unverified
0
Contradicted
10
Undersold
Verified (12)
“Keeps documentation accurate for both human readers and AI consumers”
My published docs site automatically serves llms.txt (and a full-content variant) so agents can index itfullproof ↗
“Block-based visual editor with support for custom content blocks”
Non-technical teammates can edit docs in a visual web editor without touching git, and their changes flow into the same source of truthfullproof ↗
“Block-based visual editor with support for custom content blocks”
I author pages in Markdown/MDX with rich components — tabs, callouts, code groups, steps — without writing custom HTMLpartialproof ↗
“Syncs docs content with a GitHub or GitLab repository”
My docs live in my own git repository — branches, pull requests, and merges drive what gets publishedfullproof ↗
“Applies optimizations to make content more usable by LLMs”
My published docs site automatically serves llms.txt (and a full-content variant) so agents can index itfullproof ↗
“Provides AI-powered search across the docs site”
Readers get fast, typo-tolerant, relevance-ranked search over the whole docs site out of the boxpartialproof ↗
“Offers advanced branding and site customization options”
I customize themes, fonts, and layout — down to custom CSS/JS or my own components — so the docs match my brandpartialproof ↗
“Provides analytics and collects user feedback on docs pages”
I see page views, search terms, and reader feedback so I know which docs work and which failpartialproof ↗
“Ships an official MCP server so AI agents can connect to GitBook”
“Published docs sites can expose their own MCP servers for reader agents”
My published docs site exposes its own MCP server that my users' agents can query for search and page contentfullproof ↗
“Produces LLM-ready docs output such as llms.txt or markdown mirrors”
My published docs site automatically serves llms.txt (and a full-content variant) so agents can index itfullproof ↗
“Produces LLM-ready docs output such as llms.txt or markdown mirrors”
Every published page serves clean markdown at its URL (e.g. appending .md) so agents skip the HTMLfullproof ↗
Unverified (17)
“Detects outdated docs content and can automatically fix it”
A platform AI agent drafts, updates, and reviews my docs — from a prompt, a PR, or a schedule — and ships its work as change requestsfullproof ↗
“Embeds interactive API playgrounds directly in docs pages”
Readers can try real API calls from an interactive playground embedded in the reference docsfullproof ↗
“Embeds interactive API playgrounds directly in docs pages”
Explore an interactive API reference with runnable examplesfullproof ↗
“Generates shareable preview deployments for docs changes”
Every docs pull request gets a shareable preview deployment before it mergesfullproof ↗
“Supports serving docs on a custom domain”
I serve docs on my own custom domain or as a /docs subpath of my main sitefullproof ↗
“Built-in AI Assistant answers questions about the docs content”
An embedded AI assistant on my docs site answers reader questions with citations into my contentfullproof ↗
“Built-in AI Assistant answers questions about the docs content”
Delegate tasks to a built-in AI assistant inside the productfullproof ↗
“Defines 'agent skills' that configure what the platform AI agent can do”
A platform AI agent drafts, updates, and reviews my docs — from a prompt, a PR, or a schedule — and ships its work as change requestsfullproof ↗
“GitBook's AI agent can review change requests before they publish”
A platform AI agent drafts, updates, and reviews my docs — from a prompt, a PR, or a schedule — and ships its work as change requestsfullproof ↗
“GitBook's AI agent can review change requests before they publish”
Teammates propose changes that go through review — comments, approvals, and a merge step — before they publishfullproof ↗
“Supports gating docs behind authenticated access”
I gate some or all docs behind authentication — password, JWT, or SSO — for customers-only contentpartialproof ↗
“Surfaces AI-generated insights within the docs platform”
Get AI-generated insights and suggestions from my data inside the productfullproof ↗
“Generates API reference pages from an OpenAPI specification”
My API reference pages are generated from an OpenAPI spec and stay in sync when the spec changespartialproof ↗
“Tracks version control history for docs content”
I publish versioned documentation per product or API version, and readers switch versions from the sitepartialproof ↗
“Reusable content snippets keep repeated text in sync across pages”
Reusable snippets and variables keep repeated content in sync across pagesfullproof ↗
“Provides an official GitBook CLI”
“Change requests provide a review workflow before docs publish”
Teammates propose changes that go through review — comments, approvals, and a merge step — before they publishfullproof ↗
Undersold (10)
Point an agent at llms.txt or agent-oriented docsfullproof ↗
Run the product headlessly / in CI for automationpartialproof ↗
Drive the product through a documented public APIfullproof ↗
Set up automations that run autonomously in the backgroundpartialproof ↗
Operate the product with natural-language commandsfullproof ↗
Perform bulk operations across many items at oncepartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
Export all of my data in open formats and leavepartialproof ↗
I publish my docs in multiple languages with translated navigation and contentpartialproof ↗
Claims outside our story set (4)
Real capability claims found in GitBook’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Lets teams invite members to collaborate on docs”
source ↗“Supports configuring site redirects”
source ↗“Supports content variants for different audiences or contexts”
source ↗“Supports searching across internal content sources”
source ↗
Business model
Free plan for individuals; Premium at $65/site/month and Ultimate at $249/site/month (billed annually) plus $12/user/month for additional members; Enterprise is custom.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
Agent surface uptime MCP up · llms.txt up (tracking since Sep 10 '26)
