tai42.ai valid
TAI42
tai is an open-source runtime for MCP tools, agents, and workflows — the server that hosts tools, agents, extensions, connectors, hooks, and storage for the TAI42 ecosystem.
- Authority
- 45 reach 0 · trust 5 · quality 25 · freshness 15
- Tier
- listed
- llms.txt
- https://docs.tai42.ai/llms.txt
- llms-full.txt
- https://docs.tai42.ai/llms-full.txt
- Sections
- 1
- Links
- 481
- Size
- 84476 bytes
- Country
- — Publisher location unknown; CDN address excluded
- Country evidence
- No published address evidence collected yet
- For agents
- Documentation: developer or product docs worth reading, nothing to call
- First seen
- 2026-10-25T18:53:46.225Z
- Last checked
- 2026-10-25T18:53:50.239Z
- Badge
Their llms.txt
The beginning of the file, from our validated copy saved 2026-10-25T18:53:46.342Z. Cached copy · Source on tai42.ai
# TAI42
> tai is an open-source runtime for MCP tools, agents, and workflows — the server that hosts tools, agents, extensions, connectors, hooks, and storage for the TAI42 ecosystem.
- [TAI42 — the OS for AI tools](https://docs.tai42.ai/index.md): An open-source runtime for MCP tools, agents, and workflows — the server that runs them.
- [Installation](https://docs.tai42.ai/getting-started/installation.md): Install the tai runtime and its packages.
- [Quickstart](https://docs.tai42.ai/getting-started/quickstart.md): Boot a server and call a tool over MCP.
- [Mental model](https://docs.tai42.ai/getting-started/mental-model.md): How the runtime fits together in one page.
- [Concepts](https://docs.tai42.ai/concepts/index.md): The core subsystems of the platform, one page per pillar.
- [The layering](https://docs.tai42.ai/concepts/layering.md): How contract, kit, cli, skeleton, and Studio stack.
- [The manifest](https://docs.tai42.ai/concepts/manifest.md): The declarative file a server loads at startup.
- [Tools and extensions](https://docs.tai42.ai/concepts/tools-and-extensions.md): Atoms of work and the clip-on powers over them.
- [Presets](https://docs.tai42.ai/concepts/presets.md): Versioned, named wraps of a tool.
- [Tool organization](https://docs.tai42.ai/concepts/tool-organization.md): Folders, display names, tags, and visibility — an unversioned metadata overlay over any tool.
- [Agents](https://docs.tai42.ai/concepts/agents.md): LLM-driven capabilities and how they are authored.
- [Deep agents](https://docs.tai42.ai/concepts/deep-agents.md): Durable, code-executing agents on the ordinary Agent contract.
- [Classifiers](https://docs.tai42.ai/concepts/classifiers.md): The classifier model type: typed questions about JSON state, typed answers with probabilities.
- [Client conversations](https://docs.tai42.ai/concepts/client-conversations.md): Route a client message from a messaging channel or an API caller to an agent run or a tool dispatch and deliver the answer back.
- [Interactions](https://docs.tai42.ai/concepts/interactions.md): Human-in-the-loop, in-client and external.
- [Asking the caller](https://docs.tai42.ai/concepts/asking-the-caller.md): A run that pauses to ask the run that called it, and the door contract that resolves it.
- [Notifications](https://docs.tai42.ai/concepts/notifications.md): Send a one-way message to a person — to an in-app inbox, an external channel, or both.
- [Connectors](https://docs.tai42.ai/concepts/connectors.md): OAuth connections to outside apps.
- [Hooks](https://docs.tai42.ai/concepts/hooks.md): Logic that runs at points in the request lifecycle.
- [Triggers and webhook verifiers](https://docs.tai42.ai/concepts/triggers-and-webhooks.md): Firing tools from outside events.
- [Storage and resources](https://docs.tai42.ai/concepts/storage-and-resources.md): The ResourceManager and stored content.
- [Backends](https://docs.tai42.ai/concepts/backends.md): Where tools run: background, scheduled, distributed.
…Machine-readable: GET /v1/resolve?q=tai42.ai · GET /v1/domain/tai42.ai · this page as Accept: application/json or text/markdown · MCP lookup_domain
Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.
Own or manage this website?
If you own or manage tai42.ai, you can update its listing and review file health, discovery activity and score history.
Manage this listing — optional
What verification unlocks
See how your site is discovered—and control what agents see.
- See your website in the map
Review your indexed topics, nearby publishers sharing headings, measured listing exposure and map snapshots in a private report for your website.
- Control what agents see
Edit your listing description, tags, public contact details and additional llms.txt paths. Publish your terms for automated access, attribution and pricing.
- Make your profile eligible for search
A valid, listed, unblocked, verified profile can appear in our publisher sitemap and become eligible for search-engine visibility. Search engines decide what to index and rank.
- Appear in our llms-full.txt
Eligible verified publishers are listed by name, with their file links and summaries, in the service overview agents can read.
Free. No account registration, backlink or payment required. Public discovery remains available without verification.
Let your coding agent verify it
If your coding agent is authorized to manage this website, paste these instructions into it.
Claim my listing on Agent Web Map for tai42.ai:
1. POST https://agentwebmap.com/v1/sites/tai42.ai/claims and keep claim_id and claim_secret private.
2. Publish the verification line "AgentWebMap verification: <token>" (token from step 1) in https://tai42.ai/llms.txt, or use the DNS, meta-tag or well-known method the response describes. This only verifies the listing; your website and domain remain yours.
3. POST https://agentwebmap.com/v1/sites/tai42.ai/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/tai42.ai).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verifyCorrections or removal requests: contact the directory.