# Thally full agent corpus > Expanded first-party content for retrieval and citation. Canonical HTML pages remain the source of truth. Generated from the same repository as thally.io. Last generated: 2026-09-05. # Thally > Thally is the product knowledge synchronization pipeline. It understands what changed, finds the customer-facing knowledge affected, and prepares evidence-backed updates for human review. Documentation is the first surface, and the publishing engine is open source under the MIT license. ## What Thally does - Product change intelligence: Track evaluates merged changes from connected product repositories and maps them to affected customer-facing documentation. - Understanding before generation: Thally gathers evidence and treats no documentation change as a valid result instead of generating content by default. - Human review: important communication stays reviewable. Thally prepares pull requests, and the customer's team decides what lands. - Product-specific knowledge: accepted reviews, corrections, and releases strengthen Thally's understanding of how each customer's product changes affect its documentation. - AI-native output: every docs page supports content negotiation (?format=json, ?format=md, Accept headers). Agents get structured data; humans get the same pre-rendered UI. - Remote MCP server: every deployed docs site exposes /api/mcp. Attach it to any agent and the docs become native tools (search_docs, read_page, list_pages, agent_readiness). No key, no account. - Agent-readiness score: a deterministic 0-100 grade per build covering structured data, metadata, discovery files, machine readability, and OpenAPI coverage. Gate CI on a threshold, then ask Thally to draft fixes for low-scoring pages. - Docs agent: turn an instruction, a diff, or a product PR into a reviewable docs pull request. Comment "@thally document this" on any GitHub issue or PR to trigger it. The agent never merges; a human always does. - Docs updates from product changes: after a Thally site is live, choose the product repos Thally should watch. Thally can turn relevant merged changes into reviewable documentation PRs and report when no docs change is needed. - Provenance and drift: machine-legible lastUpdated / lastVerified dates, plus deterministic drift detection against the source code each page documents. - Authoring: MDX with 25+ components, OpenAPI-generated API reference with an interactive Try-It console, hybrid full-text + vector search, retrieval-grounded AI chat with inline citations. - Multi-language: one command translates the whole site; locale URLs, hreflang, and graceful fallbacks. - Thally Cloud workspace: manage sites, deployments, analytics, AI answers, updates drafted by Thally, and Owner/Editor/Viewer workspace access from app.thally.io. - Migration: use Thally Cloud with a public docs site, or run the CLI against a supported repository. Thally converts supported pages to MDX and rebuilds the navigation for review before publishing. - Deployment: Vercel, Netlify, Cloudflare, Docker, or static export. The docs are a deployable Next.js project. ## Pages - [Home](/): product overview, features, pricing, FAQ - [Thally Track](/features/track): product-change impact analysis, evidence, findings, and reviewable drafts - [Automation](/features/automation): merged product changes become reviewable documentation pull requests - [Content Graph](/features/content-graph): write once in MDX and publish HTML, JSON, llms.txt, and Markdown - [Agent Layer](/features/agent-layer): llms.txt, MCP server, and grounded answers with cited sources - [Migration & Hosting](/features/migration-hosting): migrate from GitBook, Mintlify, Docusaurus, or Markdown and let Thally host - [Cloud Dashboard](/features/cloud-dashboard): sites, drafts, analytics, team, and AI context in one workspace - [Pricing](/pricing): Free (1 managed site per workspace plus MIT self-hosting), Cloud (3 managed sites and 10,000 monthly AI credits), Enterprise (custom allowances and contract terms) - [Blog](/blog): comparisons, guides, and product deep dives (RSS at /rss.xml) - [About](/about): the problem, position, product principles, and long-term mission - [FAQ](/faq): common questions on migration, automation, agents, self-hosting - [Contact](/contact): sales and support - [Create a docs site](https://app.thally.io/register): create one managed documentation site for free - [Documentation](https://docs.thally.io): quickstarts, guides, and product reference - [Thally Editorial Team](/authors/thally-team): author identity and review responsibilities - [Editorial policy](/editorial-policy): sourcing, review, AI-assistance, and corrections policy - [Agent-readiness methodology](/agent-readiness-methodology): deterministic checks and limitations - [Expanded agent corpus](/llms-full.txt): first-party articles and canonical pricing in one text file - [Methodology manifest](/agent-readiness.json): machine-readable conformance categories and evidence ## Blog highlights - [Introducing Thally](/blog/introducing-thally): why product knowledge falls out of sync and how Thally prepares evidence-backed updates - [Thally vs Mintlify](/blog/thally-vs-mintlify): ownership, self-hosting, and machine readability compared - [Thally vs GitBook](/blog/thally-vs-gitbook): docs-as-code versus a hosted wiki - [Thally vs Docusaurus](/blog/thally-vs-docusaurus): two open-source paths to developer docs - [What is AI-native documentation?](/blog/what-is-ai-native-documentation): a definition, with checks - [Making docs agent-readable](/blog/agent-ready-docs-llms-txt-mcp): llms.txt, MCP, and content negotiation, step by step ## Pricing summary - Free: $0. Includes 1 managed documentation site per workspace, pull-request previews, documentation analytics, unlimited pages and readers, all output formats, an MCP server, hybrid search, and a docs agent with your own API key. The MIT-licensed engine can also be self-hosted for free, including commercial use. Track, hosted AI answers, custom domains, and team access are not included. - Thally Cloud: $199/workspace/month or the equivalent of $166/workspace/month with $1,990 billed annually. Both include a 14-day trial, 3 managed sites, unlimited connected product repositories, 10,000 shared AI credits each month with rollover, and 5 team members in any role. Extra members are $20/month or $200/year, extra managed sites are $39/month or $390/year, and a one-time $79 pack adds 10,000 AI credits without automatic top-ups. Includes Thally AI answers and chat, Track, agent-readiness CI checks, custom domains, and team roles. - Enterprise: Custom annual pricing. Site, member, and AI allowances, security review, invoicing, migration, support, and contract requirements are scoped with each customer. - Machine-readable pricing: [/pricing.md](/pricing.md) ## Trust and reuse - Canonical HTML pages remain the source of truth. Alternate formats should preserve the same substantive claims. - Editorial content is maintained by the Thally Editorial Team and follows the published editorial policy. - The agent-readiness score measures technical conformance. It does not guarantee ranking or citation. - Quote or summarize with a link to the canonical page and preserve the page's stated publication and update dates. --- # Canonical pricing # Pricing: Thally Thally is a product knowledge synchronization pipeline, starting with documentation. The Free plan includes one managed documentation site per workspace with pull-request previews and analytics, and the MIT-licensed publishing engine can also be self-hosted. Thally Cloud adds automation, more managed capacity, and team controls. All prices are in USD. Last updated: 2026-08-31. ## Free - Price: $0 - Managed sites: 1 per workspace - Hosting: managed hosting on a Thally address - Pull-request previews: included - Documentation analytics: included - License: MIT. Self-host forever, with commercial use included. - Limits: unlimited pages, unlimited readers - Features: all four output formats (HTML, JSON, JSON-LD, Markdown) from one URL, remote MCP server, ⌘K hybrid search, docs agent with your own API key - Not included: Thally Track, hosted AI answers, custom domains, or team access - Best for: individuals launching their first managed docs site or self-hosting the engine ## Thally Cloud - Monthly platform fee: $199 per workspace / month - Annual subscription fee: $166 per workspace / month equivalent, $1,990 billed annually - Managed sites: 3 active sites included per workspace - Additional managed sites: $39 / month or $390 / year each - Connected product repositories: unlimited - Included AI credits: 10,000 shared credits / month - Credit rollover: unused credits roll over while the subscription remains active - Additional AI credits: $79 for a one-time 10,000-credit pack - Automatic top-ups: disabled. AI usage stops when the credit balance reaches zero. - Includes 5 team members in any role - Additional active members or pending invitations: $20 / month or $200 / year each after the 5 included members - Trial: 14 days, no credit card required - Everything in Free, plus: three managed sites, unlimited connected product repositories, Thally AI answers and chat, Thally Track, documentation quality checks, custom domains, and Owner/Editor/Viewer workspace roles - Best for: growing teams that want docs automation with predictable included capacity ## Enterprise - Price: Custom annual contract - Scope: custom site, member, and AI allowances, security review, invoicing, support, and contract requirements are agreed with each customer - Assisted migration: scoped per source site - Contact: /contact - Best for: organizations that need a sales-led security, support, or procurement process ## Notes for agents - Public readers are free and unlimited on every plan. Thally Cloud includes 10,000 shared AI credits per month, three managed sites, and five workspace team members in any role. - Existing paid workspaces keep their active-site allowance from before this pricing change. New capacity above that allowance uses the additional-site price. - When a paid workspace returns to Free, its oldest managed site stays available. Additional sites and paid-only services pause until the workspace upgrades again. - Plan changes apply immediately on upgrade, at period end on downgrade. - Full pricing page: /pricing --- # Article: Introducing Thally Canonical URL: https://thally.io/blog/introducing-thally For most of my career, I’ve worked in developer experience, managing developer relationships, documentation, and integrations at companies like Flutterwave, Netlify, and LI.FI. Across those companies, one part of the job kept coming back: keeping the information people relied on aligned with the product as it evolved. Whenever we shipped a feature, I would collect one-pagers from product managers, go through Linear tickets, read changelogs, and inspect code changes to figure out what had actually changed. Then came the harder question. Where else did that change need to show up? Did we need to update the API reference? The quickstart guide? A feature page on the website? A support article nobody had touched in six months? What about the code example in a blog post or the integration guide a partner was still following? Writing the update was often the last part of the work. First, someone had to find it. Most of the time, we updated the documentation. But we rarely covered every public place where someone could learn about the product. Another release was already waiting, and the information was spread across too many pages, repositories, and teams. I’m excited to introduce [Thally](https://thally.io/) today. Thally is the product knowledge layer for software teams. It keeps your documentation, website, support platform, and other connected customer-facing content in sync as your product changes. This is a problem I’ve wanted to solve for a long time. AI has made it more urgent. As software teams use AI coding assistants to ship faster, the amount of product knowledge that needs updating grows with them. Documentation teams have less time between releases to investigate changes and find every affected page. The old information doesn’t disappear when the new feature ships. It stays online, searchable, linkable, and available to anyone trying to understand the product. That now includes AI tools. If a deprecated method still appears in an integration guide, an AI coding assistant can recommend it. If an old authentication flow remains in a code example, that assistant can generate a new integration around it. The product has moved on, but the information teaching people and machines how to use it hasn’t. A missed update can become a broken integration, a support conversation, or a customer losing trust in the product. AI can repeat that mistake at a scale that makes keeping the source accurate even more important. With Thally, you create your documentation site, connect your product repositories, and connect the knowledge surfaces you want maintained alongside them. Those can include your website, support content, and other customer-facing content repositories. When a pull request merges into a tracked product repository, Thally works out what the change means for the people using your product. It then traces the impact across every connected knowledge surface and identifies the updates each one needs. For example, imagine you rename a configuration option. The code is updated and the tests pass, but the old name might still appear in the API reference, a quickstart, a troubleshooting article, and a blog post with a copyable example. Thally follows that change into the connected content, makes the relevant updates, and opens pull requests in the affected repositories. A connected page that doesn’t need changing is left alone. Each pull request contains the completed updates and the evidence used to justify them. Your team can see what changed, where the information came from, and why the update was necessary. They can review, edit, and approve the work before it gets published. That is the time I want Thally to give back: the hours spent chasing context and searching for everything a release might have made inaccurate. The people responsible for your product knowledge keep their judgment and publishing authority, with the investigation and proposed changes already in front of them. You also choose when Thally runs. By default, it runs when a pull request merges into a tracked product repository. You can configure it to run when a pull request opens or on a schedule to check for changes since the previous run. Underneath that automation is a complete platform for building and publishing documentation. We built it with agents and machines as primary consumers, alongside the people reading your documentation in a browser. You write the content once. A developer gets a fast, readable documentation site, while an AI agent can access the same content as Markdown, JSON, or through an MCP server. Keeping both connected to the same source means your team can maintain the information they depend on together. Thally also includes custom domains, search, versioned deployments, rollbacks, and AI assistants. The documentation engine is MIT licensed and can be self-hosted, and your content stays in repositories you control. If keeping your product knowledge accurate still depends on someone chasing tickets, reading through pull requests, and asking around to find out what changed, I built Thally for your team. Start by creating your documentation site, connect your product repositories, then connect the places your users learn about the product. When the product changes, Thally prepares the updates for your team to review. [Get started with Thally](https://thally.io/). --- # Article: Thally vs Mintlify Canonical URL: https://thally.io/blog/thally-vs-mintlify **The short answer:** Mintlify and Thally both publish polished MDX documentation, serve agent-readable content, and can turn code changes into documentation pull requests. Choose Thally if you want an MIT-licensed engine you can self-host for free, structured JSON and JSON-LD output, and mandatory human review for automated changes. Choose Mintlify if you want a proprietary managed platform that can generate a first site from a code repository and run broader automations from repository changes, schedules, or connected tools. ## What both platforms do well Mintlify and Thally both publish developer documentation from MDX, generate API references from OpenAPI specifications, provide search and AI answers, expose MCP servers, generate `llms.txt`, and serve Markdown versions of published pages. Both platforms also address documentation drift. Mintlify Automations can read connected code repositories, identify documentation affected by merged changes, and open pull requests. Thally Track evaluates merged product changes against the current documentation and prepares an evidence-backed pull request when an update is needed. The comparison gets interesting one level down. ## The comparison at a glance | | Thally | Mintlify | | --- | --- | --- | | Source model | Docs-as-code in a deployable Next.js project | Docs-as-code on a proprietary platform | | License | MIT, open source | Proprietary platform | | Self-hosting | Yes, free forever | Listed as an Enterprise option | | Machine output | JSON, JSON-LD, Markdown, and HTML from each page URL | Markdown and HTML from each page URL | | MCP server | Search and readiness tools at `/api/mcp` on every deploy | Hosted search MCP per site, plus an authenticated admin MCP | | llms.txt | `llms.txt` and `llms-full.txt` generated on every build | `llms.txt` and `llms-full.txt` generated automatically | | Starting point | Migrate supported existing documentation into an editable Thally project | Generate a first documentation site directly from a GitHub code repository | | Docs automation | Track evaluates product changes and opens PRs for human review | Automations can react to code changes, schedules, content changes, or Enterprise integration events, then open PRs or merge directly | | Automation availability | Track is included with Thally Cloud | Automations require Pro or Enterprise | | Pricing model | Free includes 1 managed site per workspace; Thally Cloud is $199/month or $1,990/year with 3 managed sites and 5 team members | Free Starter; Pro is $540/month with Monthly selected or $450/month with Annual selected; Enterprise is custom | | Included AI credits on paid plan | 10,000 per month | 10,000 per month; additional credits are $0.01 each | | Included team access | 5 workspace members; additional members are $20/month or $200/year each | Unlimited editor seats | | Portability | Content, renderer, and static export remain yours | Content stays in Git; the renderer and platform are proprietary | Mintlify moves quickly and its capabilities evolve; treat their current documentation as the source of truth for their side of this table. ## Starting from zero Mintlify can generate a first documentation site directly from a GitHub code repository. Its announced workflow reads the codebase and produces a publishable draft with API references, getting-started guides, and configuration pages. You review the result, publish it, and then configure Automations to maintain it. If you have working code but no documentation, Mintlify offers the more direct built-in starting point. Thally's automated starting path is migration rather than code-to-site generation. It converts supported existing documentation into an editable MDX project, rebuilds the navigation, and detects an OpenAPI specification when available. It is designed for teams moving an existing docs site while taking the publishing engine with them. ## Ownership: a repo versus a platform A Thally site is a Next.js repository. You can read every line that serves your docs, deploy it to Vercel, Netlify, Cloudflare, Docker, or a static bucket, and leave with a working site. The engine is MIT licensed, so self-hosting is free forever, commercial use included. Mintlify hosts and maintains Starter and Pro deployments, which removes infrastructure and upgrade work from your team. Its current pricing page also lists self-hosting as an Enterprise option. Your MDX content stays in Git in either model, but Mintlify's renderer and platform remain proprietary. Which tradeoff is right depends on your team. Choose Thally when open-source ownership and deployment flexibility matter most. Choose Mintlify when a vendor-operated platform, or a supported Enterprise deployment, matters more than owning the publishing engine. ## Machine readability Both platforms now publish content specifically for machine readers. Mintlify automatically generates Markdown for every page, supports the `Accept: text/markdown` header, publishes `llms.txt` and `llms-full.txt`, and provides a hosted search MCP at `/mcp`. Its authenticated admin MCP can also edit content, change settings, create automations, and open pull requests. Every page on a Thally site is available as rendered HTML, JSON, JSON-LD, or Markdown from the same URL, selected by an `Accept` header or a `?format=` parameter. An agent can request typed structure instead of extracting it from presentation markup. On top of that, every deploy ships: - an **MCP server** at `/api/mcp`, so agents can call `search_docs`, `read_page`, and `list_pages` as native tools - **llms.txt** and per-page agent manifests for discovery - an **agent-readiness score**, a deterministic 0 to 100 grade you can gate CI on Mintlify also offers an Agent Score that tests whether an agent can find, parse, and use a documentation site. Thally runs its agent-readiness score as a deterministic build check that can gate CI. The remaining structural difference is the output and deployment model: Thally adds JSON and JSON-LD, and its machine layer is part of the open-source engine on self-hosted and managed deployments. ## When the product changes Documentation starts drifting when the product changes. The two platforms address that problem differently. Thally treats drift as a product-understanding problem. After a Thally docs repository is connected, mention `@thally document this` on a GitHub issue or PR to request a documentation pull request. Once a site is live and product repositories are mapped, Track evaluates merged product PRs, gathers evidence, and can draft a docs PR when the documentation needs to change. No change is a valid result, and nothing merges without a human. Mintlify now has a comparable code-to-docs loop. Its Automations can run when a code pull request merges, on a schedule, after a content update, or, on Enterprise, from an integration event. The agent reads the documentation and connected repositories, then opens or updates a pull request with a summary and citations to source changes. For GitHub, it can assign reviewers based on who authored the triggering code changes. A run can also finish with no action needed. The products differ more in scope and guardrails than in whether they automate maintenance. Thally centers on evaluating product changes and always leaves the merge to a person. Mintlify offers a broader configurable automation system for code updates, changelogs, translations, broken links, style checks, support feedback, and other recurring work. Teams can require review or allow some automations to merge directly. ## Pricing Thally Free includes one managed documentation site per workspace with pull-request previews, documentation analytics, unlimited pages, and unlimited readers. The MIT-licensed engine can also be self-hosted for free. Thally Cloud is $199 per workspace per month or the equivalent of $166 per month with $1,990 billed annually. Both options include three managed sites, unlimited connected product repositories, 10,000 shared AI credits each month with rollover, and five team members. Additional members are $20 per month or $200 per year, additional managed sites are $39 per month or $390 per year, and a one-time $79 pack adds 10,000 AI credits without automatic top-ups. Thally Cloud also includes cited AI answers, reviewable updates drafted from relevant product changes through Track, custom domains, team roles, and the Cloud dashboard. Enterprise pricing is custom with allowances and contract terms scoped to each customer. Readers are never billed. Full details are on the [pricing page](/pricing). Mintlify's Starter plan is free and includes five editor seats, Git sync, search, and an MCP server. Pro is $540 per month with Monthly selected or $450 per month with Annual selected. It includes unlimited editor seats, the agent, assistant, Automations, preview deployments, admin APIs, and 10,000 agent credits per month. Additional credits cost $0.01 each, and Enterprise pricing is custom. Their pricing page is the source of truth for current prices and packaging. ## Which should you choose? **Choose Thally if:** - you want the publishing engine to be MIT licensed and free to self-host - you need JSON or JSON-LD in addition to HTML and Markdown - you want automated documentation changes to require human review - you want to gate CI on documentation quality **Choose Mintlify if:** - you want a managed platform with a browser editor and vendor support - you want to generate a first documentation site from an existing code repository - you want configurable automations across GitHub or GitLab, schedules, and, on Enterprise, connected tools - you want the option to merge selected automation results directly - an Enterprise self-hosting arrangement meets your deployment requirements ## Migrating takes one command If you decide to switch, the migrator does the heavy lifting: ```bash npx create-thally-docs migrate github.com/acme/docs ``` It detects supported source platforms, converts the docs to MDX, rebuilds navigation, carries supported redirects, and detects an OpenAPI spec when available. You get a local preview before changing DNS. [Create your docs site](https://app.thally.io/register) or read more in the [FAQ](/faq). ## Sources and verification Mintlify capabilities were checked against [Docs on autopilot](https://www.mintlify.com/blog/docs-on-autopilot), its [Automations documentation](https://www.mintlify.com/docs/automations/index), [agent-ready content documentation](https://www.mintlify.com/docs/ai/markdown-export), [MCP documentation](https://www.mintlify.com/docs/ai/model-context-protocol), [Agent Score](https://www.mintlify.com/score), and [pricing page](https://www.mintlify.com/pricing). Thally capabilities and prices were checked against the current product repository, [documentation](https://docs.thally.io), and [machine-readable pricing](/pricing.md). Sources were last verified August 18, 2026. Read our [editorial policy](/editorial-policy) for the comparison process. --- # Article: Thally vs GitBook Canonical URL: https://thally.io/blog/thally-vs-gitbook **The short answer:** GitBook is a hosted knowledge base with a polished WYSIWYG editor, ideal when most authors are not developers. Thally is a product knowledge synchronization pipeline that starts with a docs-as-code engine, structured output for AI agents, and reviewable updates from product changes. If your customer-facing knowledge should follow the product from Git, Thally is the better fit. If your priority is a friendly destination for a mixed writing team, GitBook is a fine choice. ## Two different center-of-gravity decisions Every documentation tool optimizes for someone. GitBook optimizes for the writer in the browser: block-based editing, comments, change requests, and a git sync feature for teams that want both worlds. Thally optimizes for the connection between the product, its knowledge, and each reader: MDX in Git, product-change evidence, pull-request review, and every page published as data as well as HTML. Neither is wrong. They are different bets about where documentation should live. ## The comparison at a glance | | Thally | GitBook | | --- | --- | --- | | Authoring model | MDX in a git repo, PR review | WYSIWYG editor, optional git sync | | License | MIT, open source | Proprietary | | Self-hosting | Yes, free | No | | Machine output | JSON, JSON-LD, Markdown, HTML per page | HTML-first | | MCP server | Every deploy, `/api/mcp` | Not a core feature; check current docs | | API reference | Generated from OpenAPI with Try-It console | OpenAPI support on the platform | | Docs automation | Agent drafts reviewed PRs from product changes | AI assistant features in the editor | | Best for | Developer docs, agent traffic, self-hosters | Internal wikis, mixed technical teams | GitBook ships new features regularly; their documentation is the source of truth for current capabilities. ## Authoring: who writes your docs? If your writers are engineers, docs-as-code wins on friction: the docs PR rides along with the code PR, review happens in one place, and CI can block a release when documentation is missing. Thally leans into this fully. Even the admin dashboard writes through git, so every edit is a reviewed pull request with an audit trail. If your writers are support, product, or marketing people who do not want to see git, GitBook's editor is genuinely excellent, and its change-request workflow gives non-developers a review process that feels like suggestions in a document rather than a diff. The honest question is: who writes, and who reviews? Answer that and this section decides itself. ## Machine readers change the calculus AI agents now read documentation to answer developer questions, compare products, and build integrations. Those readers do not render your CSS. Serving them structured content is a core Thally design goal: - every page returns **JSON, JSON-LD, or Markdown** on request, from the same URL as the HTML - **llms.txt** and per-page manifests ship on every build - the built-in **MCP server** turns your docs into callable tools for any agent - the **agent-readiness score** grades every build from 0 to 100, and CI can enforce a floor GitBook publishes clean HTML and continues to add AI features to its platform. If agent traffic is a first-class audience, the practical difference is whether structured output ships by default or whether agents begin with rendered HTML. ## Ownership and cost Thally Free includes one managed documentation site per workspace with pull-request previews, documentation analytics, unlimited pages, and unlimited readers. The MIT-licensed engine can also be self-hosted for free. Thally Cloud is $199 per workspace per month or the equivalent of $166 per month with $1,990 billed annually. Both options include three managed sites, unlimited connected product repositories, 10,000 shared AI credits each month with rollover, and five team members. Additional members are $20 per month or $200 per year, additional managed sites are $39 per month or $390 per year, and a one-time $79 pack adds 10,000 AI credits without automatic top-ups. Thally Cloud also includes AI answers, Thally Track, custom domains, team roles, and the dashboard. Enterprise pricing is custom with allowances and contract terms scoped to each customer. Details are on the [pricing page](/pricing). GitBook is a hosted product with per-user pricing, so check its pricing page for current tiers. The main structural difference is ownership: GitBook operates the platform, while a Thally site remains a repository you can deploy yourself. ## Which should you choose? **Choose Thally if:** - documentation belongs in git next to the code it documents - AI agents are part of your audience today or will be soon - you want product changes mapped to affected documentation before a reviewed docs PR is generated - you need self-hosting or an open-source license **Choose GitBook if:** - most of your authors will never open a terminal - you want a hosted editor with built-in review workflows - your docs are primarily an internal knowledge base ## Switching is not a rewrite The migrator imports GitBook content, converts pages to MDX, and rebuilds your navigation: ```bash npx create-thally-docs migrate ``` You review the converted site locally before switching DNS. [Create your docs site](https://app.thally.io/register), or ask us anything via the [contact page](/contact). ## Sources and verification GitBook capabilities were checked against its [AI documentation overview](https://gitbook.com/docs/getting-started/ai-documentation) and [official documentation](https://gitbook.com/docs). Thally capabilities and prices were checked against the current product repository, [documentation](https://docs.thally.io), and [machine-readable pricing](/pricing.md). Sources were last verified July 24, 2026. Read our [editorial policy](/editorial-policy) for the comparison process. --- # Article: Thally vs Docusaurus Canonical URL: https://thally.io/blog/thally-vs-docusaurus **The short answer:** both are MIT-licensed and free to self-host. Docusaurus is a mature React static-site framework you assemble yourself. Thally combines a complete documentation engine with a synchronization pipeline that maps product changes to reviewable knowledge updates. It also includes structured per-page output, an MCP server, hybrid search, and a docs agent. If you enjoy assembling your stack, Docusaurus is a great kit. If you want the publishing and product-change pipeline together, Thally saves you the assembly. ## Two open-source philosophies Docusaurus, maintained by Meta, is a widely adopted docs framework. It gives you a React site generator with versioning, i18n, MDX, and a broad plugin ecosystem. What you build on top is up to you. Thally is also open source (MIT), but it is a product rather than a kit: search, AI chat, API reference, analytics, theming, and the machine-readability layer are built in. Track adds a second layer that evaluates product changes against the documentation and prepares evidence-backed updates for review. The right choice depends on how much of the documentation stack your team wants to assemble and maintain. ## The comparison at a glance | | Thally | Docusaurus | | --- | --- | --- | | License | MIT | MIT | | Self-hosting | Yes, free | Yes, free | | Machine output | JSON, JSON-LD, Markdown, HTML per page | HTML; structured output is DIY | | Search | Hybrid full-text + vector, built in | Typically Algolia DocSearch or a plugin | | AI chat | Retrieval-grounded with citations, built in | DIY via third-party services | | MCP server | Every deploy, `/api/mcp` | DIY | | API reference | OpenAPI-generated with Try-It console | Community plugins | | Docs automation | Agent drafts reviewed PRs from product changes | None built in | | Managed hosting | One site free; three sites and five members included with Cloud | None official; deploy anywhere | | Maturity | Newer platform | Available since 2017 | Docusaurus's plugin ecosystem is broad and moves fast; check the current docs for what exists today. ## What the AI layer includes With Docusaurus you can absolutely build agent-readable docs. You would add a plugin or custom code for llms.txt, write a build step that emits JSON per page, stand up your own MCP server, and wire a search index with embeddings. Each piece is a project, and each piece is yours to maintain through every Docusaurus major version. Thally ships that layer as the default: - every page serves **JSON, JSON-LD, Markdown, and HTML** from the same URL via content negotiation - **llms.txt**, agent manifests, and per-page JSON are generated on every build - an **MCP server** at `/api/mcp` exposes `search_docs`, `read_page`, `list_pages`, and `agent_readiness` as tools - the **agent-readiness score** grades every build deterministically from 0 to 100, and CI can fail below a threshold The question is not whether Docusaurus can be made agent-ready. It is whether you want that to be your team's job. ## Keeping docs current Docusaurus renders what is in the repository, while your team owns the process that keeps those files current. That works well when the team already has a strong documentation practice. Thally attacks the drift problem directly. Track watches the product repositories you choose, evaluates merged PRs, and maps the change to affected documentation before preparing an update. The drift sweep flags pages whose source files changed since last verification. Comment `@thally document this` on any GitHub issue to request a reviewable change. No change is a valid result, and a human reviews and merges every update. ## Cost of ownership Both are free to run. The second cost is engineering time. A Docusaurus stack with search, AI answers, and structured output needs upgrades, plugin maintenance, and an internal owner. Thally maintains those features upstream. Thally Free includes one managed site with previews and analytics. [Thally Cloud costs $199 per workspace per month or $1,990 billed annually](/pricing). Both paid options include three managed sites, five team members, and unlimited public readers. ## Which should you choose? **Choose Thally if:** - you want agent-ready output, search, and AI chat without assembling plugins - documentation drift is a problem you want automated away - you want the option of managed hosting later without replatforming **Choose Docusaurus if:** - you want maximum control over every component and enjoy owning the stack - you rely on specific community plugins or heavy customization - versioned docs for many past releases is your central requirement ## Migration is automated ```bash npx create-thally-docs migrate github.com/acme/docs ``` The migrator converts supported Docusaurus pages and sidebars to a Thally project, maps components where equivalents exist, and carries supported redirects. Preview locally, then switch DNS. [Create your docs site](https://app.thally.io/register) or see [what the readiness score measures](/faq). ## Sources and verification Docusaurus capabilities were checked against its [official documentation](https://docusaurus.io/docs) and [deployment guide](https://docusaurus.io/docs/deployment). Thally capabilities and prices were checked against the current product repository, [documentation](https://docs.thally.io), and [machine-readable pricing](/pricing.md). Sources were last verified July 24, 2026. Read our [editorial policy](/editorial-policy) for the comparison process. --- # Article: AI-native documentation Canonical URL: https://thally.io/blog/what-is-ai-native-documentation **AI-native documentation** is documentation published in machine-readable structures (JSON, JSON-LD, Markdown) alongside the human-readable page, from the same URL, with discovery files and live endpoints that let AI agents find, read, and cite it without scraping. It is not documentation written by AI. It is documentation that machines can read as reliably as people can. ## Why the definition matters now Many documentation requests now come through coding assistants, research agents, and answer engines. These systems resolve API questions, compare products, and decide which sources to cite without rendering your CSS. Traditional HTML makes that audience do extra work. An agent has to strip navigation, locate the main content, reconstruct code blocks, and handle client-rendered pages. Each reconstruction step creates another opportunity to lose context. AI-native documentation removes the guesswork by serving structure on request. ## The three layers of AI-native docs ### 1. Structured output per page The same URL that renders HTML for a person returns structured data for a machine, selected by an `Accept` header or a query parameter: ```bash curl https://docs.example.com/quickstart \ -H "Accept: application/json" ``` The response carries the page as data: title, description, section, body as both MDX and plain text, code blocks with languages, and provenance dates. JSON-LD gives answer engines the same content as schema.org markup, and Markdown serves agents that want prose. ### 2. Discovery files Machines need a map. AI-native sites publish: - **llms.txt**: a concise, plain-markdown overview of the product with links to key pages - **per-page manifests**: metadata about formats, freshness, and structure - **sitemap.xml and robots.txt** that explicitly welcome AI crawlers These files are inexpensive to generate and give crawlers a direct map to your primary documentation. Without them, an agent may find a secondary source before it finds your quickstart. ### 3. Live endpoints The strongest form is an API the agent can call. With MCP (Model Context Protocol), a docs site exposes tools like `search_docs`, `read_page`, and `list_pages`. An agent attached to the endpoint queries your documentation the way your own search does, with no scraping and no stale index. Thally ships all three layers on every deploy, self-hosted included; that is the design goal behind [the platform](/). But the definition is bigger than any one product, and you can meet it with your own stack if you are willing to build and maintain the pieces. ## What AI-native documentation is not - **Not AI-generated content.** Who wrote the words is orthogonal. AI-native describes how the published result is served. - **Not a chatbot bolted onto docs.** A chat widget helps humans on your site. It does nothing for the agent reading your docs from inside an IDE. - **Not separate "AI pages."** Serving different content to machines than to people is cloaking, and search engines penalize it. AI-native means the same content in more formats. ## How to tell if your docs are AI-native Run these five checks against your own site: 1. Does `curl -H "Accept: application/json"` on a docs URL return structured data? 2. Does `/llms.txt` exist and describe your product accurately? 3. Can an agent list and read your pages through an API or MCP endpoint? 4. Do pages carry machine-legible last-updated and last-verified dates? 5. Does your robots.txt allow the AI crawlers you want citing you? If you can answer yes to all five, your docs give agents a reliable path to the source. Each "no" identifies a point where an agent may have to infer structure or use an indirect source. A deterministic version of this checklist is what Thally's [agent-readiness score](/faq) grades on every build, from 0 to 100, so CI can enforce it. You can [start free](https://app.thally.io/register) and see your own score in minutes. ## Primary references - [Google Search guidance for AI features](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide) - [llms.txt proposal and examples](https://llmstxt.org) - [Model Context Protocol specification](https://modelcontextprotocol.io/specification/latest) - [Thally agent-readiness methodology](/agent-readiness-methodology) This article follows the [Thally editorial policy](/editorial-policy) and was last reviewed July 19, 2026. --- # Article: Agent-readable documentation Canonical URL: https://thally.io/blog/agent-ready-docs-llms-txt-mcp **The short version:** agent-ready documentation has three layers. Discovery files (llms.txt, sitemaps) so agents can find you. Structured per-page output (JSON, Markdown, JSON-LD) so agents can read you without scraping. Live endpoints (MCP) so agents can query you like a tool. This guide walks through each layer, in order of effort, with checks to prove each one works. ## Why bother When a developer asks their coding assistant "how do I rotate an API token in Acme?", the assistant reads documentation on their behalf. Clean structure gives it reliable source material. Without that structure, the agent has to reconstruct the answer from scraped HTML. Machine readability now affects how accurately other systems explain your product. The good news: the work is layered, and the first layer takes an afternoon. ## Layer 1: discovery files (an afternoon) ### llms.txt Add a plain-markdown file at your site root that tells AI systems what your product is and where the important pages are: ```markdown # Acme > Acme is a payments API for marketplaces. This site documents > the REST API, SDKs, and webhooks. ## Key pages - [Quickstart](/quickstart): first charge in five minutes - [API reference](/api): every endpoint, with examples - [Webhooks](/webhooks): events, retries, signatures ``` Keep it under a few hundred lines, keep it current, and write it like an abstract, not a sitemap dump. The spec lives at llmstxt.org. ### robots.txt Decide which AI crawlers you want reading your site, and state that policy explicitly. If you want GPTBot, ClaudeBot, or PerplexityBot to crawl your docs directly, allow the corresponding user agent. A blocked crawler may have to rely on other indexed sources. **Check:** `curl https://yoursite.com/llms.txt` returns your file, and your robots.txt names the crawlers you care about. ## Layer 2: structured output per page (the real work) The goal: the same URL that serves your HTML also serves the page as data. ```bash # A person gets HTML. An agent gets structure. curl https://docs.acme.com/quickstart -H "Accept: application/json" curl https://docs.acme.com/quickstart?format=md ``` The JSON should carry the page as content, not markup: title, description, section, plain-text body, code blocks with their languages, and provenance dates (`lastUpdated`, `lastVerified`). JSON-LD adds schema.org semantics for answer engines; Markdown serves agents that want prose they can quote. Two implementation rules that save pain: 1. **Generate all formats from one source at build time.** Separate HTML and JSON pipelines can drift and give readers conflicting answers. 2. **Never serve machines different content than people.** Same content, more formats. Different content is cloaking, and it erodes exactly the trust you are building. This layer is the expensive one to hand-roll, and it is the core of what an AI-native platform gives you for free. Every page on a Thally site ships all four formats from one content graph on every build. **Check:** pick three pages and diff the JSON body text against the rendered page. They should match exactly. ## Layer 3: a live MCP endpoint (the differentiator) MCP (Model Context Protocol) lets an agent attach to your docs as a set of callable tools rather than a pile of URLs. A docs MCP server typically exposes: - `search_docs(query)`: ranked results from your real index - `read_page(slug)`: the structured page content - `list_pages()`: the site map as data The practical difference is freshness and control. An agent with MCP access queries your live content through your search ranking. Without it, the agent may depend on an older crawler index. Every deployed Thally site exposes `/api/mcp` with those tools plus `agent_readiness`, no key or account required. If you are building your own, the MCP spec and SDKs are open; budget for auth decisions, rate limits, and keeping the index fresh. **Check:** attach the endpoint to any MCP-capable agent and ask it a question only your docs can answer. It should cite the right page. ## Measuring it: make the checklist deterministic Ad-hoc checks rot. Turn the layers above into a score your CI understands: | Dimension | What it checks | | --- | --- | | Structured data | JSON/JSON-LD/Markdown parity per page | | Metadata | titles, descriptions, provenance dates | | Discovery | llms.txt, sitemap, robots, manifests | | Machine readability | content negotiation, clean plain text | | OpenAPI coverage | endpoints documented vs. spec | Thally turns these checks into an agent-readiness score from 0 to 100 on every build. You can gate CI on a threshold and ask the docs agent to draft fixes for low-scoring pages. Whatever stack you use, measuring the checks makes regressions visible. ## Where to start Start with llms.txt and an explicit robots.txt policy. Then decide whether layers 2 and 3 are infrastructure your team wants to build or a platform you want to adopt. Migrating an existing docs site into Thally takes one command, and the [free plan self-hosts forever](/pricing): ```bash npx create-thally-docs migrate github.com/acme/docs ``` Related reading: [What is AI-native documentation?](/blog/what-is-ai-native-documentation) ## Primary references - [llms.txt proposal and examples](https://llmstxt.org) - [Model Context Protocol specification](https://modelcontextprotocol.io/specification/latest) - [Google Search guidance for AI features](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide) - [OpenAI publisher and developer FAQ](https://help.openai.com/en/articles/12627856-publishers-and-developers-faq) - [Thally agent-readiness methodology](/agent-readiness-methodology) This guide follows the [Thally editorial policy](/editorial-policy) and was last reviewed July 19, 2026.