rungent v0.5.1
EN中文

Agent-native, from the API you already have

Seven agent surfaces. One catalog. Your users' own rights.

Mark the operations of your OpenAPI with x-rungent. rungent serves the assistant beside your pages, an MCP server, your CLI, skill.md, llms.txt, ⌘K search and answers that cite your docs. Your coding agent adds it in one sentence; your users' agents start with one more.

The problem#

A product that wants agents to use it ends up building the same thing seven times:

Surface Who uses it Usually built as
An agent inside the product your users a chat widget with its own tool list
An MCP server Claude Code, Cursor, Codex a second tool list, often on a service account
A CLI developers and their agents a third copy of the API
A skill coding agents a hand-written file that drifts
Docs agents can read any agent llms.txt, if anyone remembers
Global search everyone a separate index of resources
Answers from your docs (RAG) everyone a separate pipeline with its own model

Each copy drifts from the API. Each has its own idea of permissions, often broader than the user's. Writes skip the form your page uses, so an agent asks for different fields than your UI does, and the same request gets a form one time and a chat interview the next.

What rungent is#

rungent turns one catalog, your OpenAPI with x-rungent on the operations agents may use, into all seven surfaces, and runs every one of them as the signed-in user.

Three rules hold on every surface:

  • One catalog. The agent, MCP tools, CLI commands, skill and search are all generated from your operations, so they always say the same thing.
  • One identity. rungent calls your API with the user's own credential and a signed assertion. It has no rights of its own; your permissions decide.
  • One path for changes. A request to change something opens your page's own form, then an approval card bound to the exact arguments, then the call. Never a chat interview.

rungent is one npm package, rungent, a server image for non-JavaScript stacks, and a Python kit. It runs on Node, Bun, Deno and Cloudflare Workers.

Start with one sentence#

Send your coding agent:

Install the rungent skill from https://rungent.acahti.dev/skills/rungent/SKILL.md, then make this product agent-native with it.

The skill teaches the agent the whole integration: annotate the operations, add the identity operation, verify rungent's assertion, mount rungent and the dock, add your docs as knowledge, and test it. You review a pull request. Quickstart shows what it writes, if you would rather do it by hand.

Once you ship, your product serves its own skill.md, and your users send their agents:

Install the skill at https://console.example.com/skill.md and use it to manage my servers.

Two sides, one catalog#

rungent has two audiences, and the catalog is where they meet.

Build side: you and your coding agentrungent skillone sentence installs itx-rungent annotationson the operations agents may useIdentity + assertion checkone operation, one middlewareDock and page formsone React componentYour product, with rungentOne catalogOpenAPI + x-rungentOne identitythe user's own rightsOne change pathform → approval → callKnowledgeyour docs, citedUse side: your users and their agentsAssistantbeside your pages⌘K search + answersresources and docsMCP · CLIClaude Code, Cursor, scriptsskill.md · llms.txtone sentence for their agentwritesservesBoth sides see the same operations. Each user only what they may do.Build side: you and your coding agentrungent skillone sentence installs itx-rungent annotationson the operations agents may useIdentity + assertion checkone operation, one middlewareDock and page formsone React componentwritesYour product, with rungentOne catalogOpenAPI + x-rungentOne identitythe user's own rightsOne change pathform → approval → callKnowledgeyour docs, citedservesUse side: your users and their agentsAssistantbeside your pages⌘K search + answersresources and docsMCP · CLIClaude Code, Cursor, scriptsskill.md · llms.txtone sentence for their agent

Both sides see the same operations. Each user only what they may do.

  • The build side is you and your coding agent. You read the rungent skill and these docs. You write annotations, one identity operation, one middleware and one React component. Nothing else.
  • The use side is your users and their agents. They never read these docs. They see your product: the assistant beside its pages, ⌘K, and the skill.md, /mcp and CLI it serves. Everything they can do is in your catalog, filtered to what they may do.

How it is built#

Where people and agents workIn-app assistantthe dock beside your pages⌘K searchresources and docsMCP clientsClaude Code, Cursor, …CLIyour branded commandskill.md · llms.txtfor any agentrungentOne catalogyour OpenAPI, as each user sees itRouting → form → approvalone path for every changeAgent loopmodel chain, retries, limitsThreads and streamingAG-UI events, resumableSearch and knowledgefederated, citedYour productHTTP APIOpenAPI 3.1 + x-rungentIdentitywho is signed inPermissionsyour rules decidePage formsthe same form as your pageDocsanswers cite themthe user'ssessionuser credential+ signed assertionresults,your errorsEvery call runs as the signed-in user. rungent holds no privilege of its own.Where people and agents workIn-app assistantthe dock beside your pages⌘K searchresources and docsMCP clientsClaude Code, Cursor, …CLIyour branded commandskill.md · llms.txtfor any agentthe user'ssessionrungentOne catalogyour OpenAPI, as each user sees itRouting → form → approvalone path for every changeAgent loopmodel chain, retries, limitsThreads and streamingAG-UI events, resumableSearch and knowledgefederated, citeduser credential+ signed assertionYour productHTTP APIOpenAPI 3.1 + x-rungentIdentitywho is signed inPermissionsyour rules decidePage formsthe same form as your pageDocsanswers cite them

Every call runs as the signed-in user. rungent holds no privilege of its own.

rungent sits between the surfaces and your API. It reads your catalog with each user's credential, runs the agent loop, sends every change through form and approval, streams the conversation as AG-UI events, and federates search over your resources and docs. Your product keeps the decisions: identity, permissions, forms and facts. See How it works.

Concepts#

Word Meaning Page
Catalog Your OpenAPI operations marked x-rungent, as one user sees them The catalog
Identity Whose request it is; every call is made as that user Acting as the user
Change path Route → your form → approval → call Forms and approvals
Knowledge Your docs and resources, searched and cited Search and knowledge
Surfaces Dock, ⌘K, MCP, CLI, skill.md, llms.txt Surfaces

Where to go next#

Version 0. The protocol is rungent/0 and the HTTP API lives under /rungent/v0; a minor release may still break it, and the changelog lists every break.

For agents: overview.mdEdit this page