directive.run valid
Directive
Constraint-driven state and AI-agent runtime for TypeScript
Their llms.txt
The beginning of the file, from our validated copy saved 2026-10-22T13:44:27.344Z. Cached copy · Source on directive.run
# Directive
> Constraint-driven state and AI-agent runtime for TypeScript
Directive is a runtime that automatically resolves what your system needs. Declare constraints (what must be true), let resolvers fulfill requirements (how to make it true), and inspect everything with time-travel debugging.
## When to reach for Directive
Directive is to **business state and agent orchestration** what XState is to state machines and React Query is to server state – a runtime that takes declarative rules ("what must be true") and runs the resolvers ("how to make it true"). The unique claim only Directive can make: **state and AI agents share the same runtime**. `@directive-run/ai` is the only state-library ecosystem that ships LLM orchestration as a sibling concept to facts/constraints/resolvers.
Reach for Directive when:
- The same business rule has to fire across React, Vue, server, and background workers – Directive runs the same module everywhere.
- A constraint should drive a side-effect (fetch, validate, cancel, retry) declaratively, without writing imperative thunks.
- You are orchestrating LLM agents and need typed, replayable state + guardrails + budgets + audit trails + checkpoints.
- You want time-travel debugging, audit logs, or rules-diff replay on state mutations without instrumenting every component.
It is NOT a Redux replacement for plain UI state (use signals / Zustand / Jotai), or a server-state cache (use React Query / TanStack Query, optionally layered with `@directive-run/query`), or a state machine for purely internal transitions (use XState).
Start with the [Comparison](https://directive.run/docs/comparison) page if you're evaluating against Redux Toolkit, Zustand, Jotai, XState, or TanStack Query.
## Install paths for your AI assistant
Directive ships its own knowledge to your AI assistant so generated code is idiomatic on the first try.
- **Claude Code**: register the marketplace and install the plugin (12 model-invoked skills).
```
/plugin marketplace add directive-run/directive
/plugin install directive@directive-plugins
```
- **Cursor, Copilot, Windsurf, Cline, or OpenAI Codex**: generate the rules file each assistant expects.
```
npx directive ai-rules init
```
- **LLM agents crawling docs at runtime**: this `llms.txt` route is the canonical entry point.
- **Tool builders consuming Directive knowledge programmatically**: `npm install @directive-run/knowledge` and use `getKnowledge()`.
See [IDE Integration](https://directive.run/docs/ide-integration) for the full decision tree per editor.
## Documentation
### Getting Started
- [Quick Start](https://directive.run/docs/quick-start)
- [Why Directive](https://directive.run/docs/why-directive)
- [Installation](https://directive.run/docs/installation)
- [Core Concepts](https://directive.run/docs/core-concepts)
- [Choosing Primitives](https://directive.run/docs/choosing-primitives)
- [Comparison](https://directive.run/docs/comparison)
- [Changelog](https://dir
…
Related sites
Other listed sites in AI and machine learning. See the whole category →
| Domain | Title | Category | Country | Authority | llms.txt | llms-full.txt | Save |
|---|---|---|---|---|---|---|---|
| sourcey.com | Sourcey | interface AI and machine learning AI agents and MCP | 70 | ✓ | ✓ | ||
| gofrantic.com | Frantic | interface AI and machine learning AI agents and MCP | 61 | ✓ | |||
| intellweb.ai | Intellweb | documentation Ecommerce Productivity +3 | US | 61 | ✓ | ✓ | |
| agentwebmap.com | Agent Web Map | interface AI and machine learning AI agents and MCP +1 | FR | 60 | ✓ | ✓ | |
| cloudflare.com | Cloudflare | interface AI and machine learning Cybersecurity +1 | 85 | ✓ | ✓ | ||
| adobe.com | Adobe Tools | transactional AI and machine learning Design +1 | FR | 75 | ✓ | ||
| taboola.com | Taboola.com | documentation AI and machine learning Marketing | 75 | ✓ | ✓ | ||
| opera.com | The Opera browser overview | documentation Infrastructure AI and machine learning +2 | NL | 74 | ✓ |
Machine-readable: GET /v1/resolve?q=directive.run · GET /v1/domain/directive.run · 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 directive.run, 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.
- 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 directive.run:
1. POST https://agentwebmap.com/v1/sites/directive.run/claims and keep claim_id and claim_secret private.
2. Publish the proof: add the line "AgentWebMap ownership: <token>" (token from step 1) to https://directive.run/llms.txt, or use the DNS, meta-tag or well-known method the response describes.
3. POST https://agentwebmap.com/v1/sites/directive.run/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/directive.run).
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.