~/ domain/runx.ai.mdTHE AGENT-READABLE WEB

runx.ai valid ✓ ownership confirmed

Submitted listing, checked from public files. Domain ownership has been confirmed. Inclusion does not imply endorsement or publisher participation.

Manage this listing · Visit publisher ↗

Corrections or removal requests: contact the directory. Ownership management is optional.

runx

Runx is an Apache-2.0 open-source Rust runtime for portable agent skills. It admits acts under explicit authority, supervises execution, and signs receipts. The local runtime runs skills; its hosted catalog and read-only MCP support discovery.

agent-skillsmcprustopen-sourcegoverned-execution

For agents: Apache-2.0 Rust runtime for portable agent skills with bounded authority and signed receipts. Docs cover quickstart, concepts and first-party skills; read-only

agent-skillsgoverned-runtimerustmcp-serversigned-receiptsopen-source

Authority
65 reach 0 · trust 25 · quality 25 · freshness 15
Tier
featured
llms.txt
https://runx.ai/llms.txt
llms-full.txt
https://runx.ai/llms-full.txt
nested
https://runx.ai/docs/llms.txt
Sections
2
Links
190
Size
31656 bytes
Registered
2023-05-07
Contact
ask@runx.ai
Categories
AI agents and MCP · Open source projects
For agents
Interface: a documented API or declared MCP endpoint an agent can call
Audience
developers · agents can: read docs, download data · en
First seen
2026-10-22T02:19:51.468Z
Last checked
2026-10-22T02:50:51.254Z
Verified
2026-10-22T02:49:42.745Z via dns
Badge
Agent Web Map badge for runx.ai

Their llms.txt

The beginning of the file, from our validated copy saved 2026-10-22T02:49:42.792Z. Cached copy · Source on runx.ai

# runx

> Governed runtime for agent skills: discover and install portable skills, run bounded skill graphs with explicit authority, and inspect signed receipts for what happened.

runx is the governed runtime for agent skills: the skill being run is explicit, the authority granted to it is bounded, consequential actions pass through a gate, and every run leaves a signed receipt.

## Start here

- [Agent skill](https://runx.ai/SKILL.md): what runx is and how an agent uses it
- [AGENTS.md](https://runx.ai/AGENTS.md): the condensed machine-surface guide
- [MCP server](https://api.runx.ai/mcp): search the catalog and read a skill over MCP, no auth
- [MCP manifest](https://api.runx.ai/mcp.json): the tools, resources and prompts that server offers
- [Documentation](https://runx.ai/docs): hosted product and API docs
- [Documentation index](https://runx.ai/docs/llms.txt): every documentation page as a plain-text index
- [Hosted API contract](https://runx.ai/openapi.json): OpenAPI for the runx hosted API
- [Skill catalog](https://runx.ai/x): every published skill, searchable
- [llms-full.txt](https://runx.ai/llms-full.txt): the setup skill and the complete documentation in one document
- [ARD catalog](https://runx.ai/.well-known/ard.json): these surfaces as agentic resource discovery entries
- [Spec](https://runx.ai/spec): the runx contract and its schemas
- [Install](https://runx.ai/install): the CLI install script

## First-party skills

- [Agency](https://runx.ai/x/runx/agency): Record a bounded multi-turn case and propose one roster-constrained member dispatch at a time; a trusted external driver must execute and verify each member. [SKILL.md](https://api.runx.ai/v1/skills/runx/agency/versions/sha-b14b0075b493/files/SKILL.md)
- [Agent session](https://runx.ai/x/runx/agent-session): Work one turn of a host's agent through runx. Read, search and ask in the read runner; also edit the workspace and run commands in the develop runner. Every call is admitted, recorded and receipted, and the turn ends with a summary of what it did. [SKILL.md](https://api.runx.ai/v1/skills/runx/agent-session/versions/sha-1aad1fec5288/files/SKILL.md)
- [Attention review](https://runx.ai/x/runx/attention-review): Decide which bounded personal observations warrant attention, then return a source-bound private briefing intent and next-check proposal. [SKILL.md](https://api.runx.ai/v1/skills/runx/attention-review/versions/sha-3fcaf1656849/files/SKILL.md)
- [Brand voice](https://runx.ai/x/runx/brand-voice): Build a scoped brand voice packet from source material so downstream agents can write, review, and adapt content without inventing brand claims. [SKILL.md](https://api.runx.ai/v1/skills/runx/brand-voice/versions/sha-911985c99e8e/files/SKILL.md)
- [Business operations](https://runx.ai/x/runx/operations-review): Operate a project, workspace, or account from an agent or manager dashboard: inspect state, triage risks, prepare governed actions, route to the right skill lane, require
…

Related sites

Other listed sites in AI agents and MCP. See the whole category →

DomainTitleCategoryCountryAuthorityllms.txtllms-full.txtSave
ausca.com Ausca interface AI agents and MCP APIs and SDKs 65 ✓ ✓
nitrosend.com Nitrosend interface Marketing Communications +1 65 ✓ ✓
0state.com 0state documentation Open source projects AI agents and MCP +1 61 ✓
optimizely.com Optimizely documentation Marketing AI agents and MCP US 69 ✓
getpostman.com Postman interface APIs and SDKs Developer tools +1 US 68 ✓ ✓
openweathermap.org OpenWeather interface APIs and SDKs AI agents and MCP +1 FR 68 ✓ ✓
att.com AT&T interface Telecom AI agents and MCP US 67 ✓ ✓
pydantic.dev Pydantic interface AI agents and MCP Developer tools +1 66 ✓ ✓

Terms for agents

Stated by the verified owner.

notes
Public catalog and documentation reads are available; execution, provider access, and payments require their own authority and terms.
terms url
https://runx.ai/terms
rate limit
Respect Runx and provider rate limits; do not circumvent usage limits.
automated access
limited

Optional directory badge

Put this on your site; it links back to this page and updates by itself.

<a href="https://agentwebmap.com/domain/runx.ai"><img src="https://agentwebmap.com/badge/runx.ai.svg" alt="Agent Web Map listing status" height="20"></a>

Markdown: [![Agent Web Map listing status](https://agentwebmap.com/badge/runx.ai.svg)](https://agentwebmap.com/domain/runx.ai)

Open your owner dashboard → to review file health, discovery activity and score history, or update your listing.

Machine-readable: GET /v1/resolve?q=runx.ai · GET /v1/domain/runx.ai · this page as Accept: application/json or text/markdown · MCP lookup_domain

agent web map / a clearer way in.API & MCP · Contact