AgentRun

Open-source packages for your pi agent. Install the ones you need.

This repository holds the AgentRun harness: the workflow DSL and the pi extensions around it.

pi-vision lets a pi agent answer questions about documents, images and video, and show the page, second or region each answer rests on. Try it free, with no key (the models are scripted), in a checkout built as under Run the support example: npm run demo:vision -- examples/document-check. It needs ffmpeg, ffprobe, pdftoppm and pdftotext (brew install ffmpeg poppler, or sudo apt-get install ffmpeg poppler-utils). See pi-vision.

Quickstart · Packages · Documentation · Examples · Pi extension · Agent instructions

View the static diagram · Run this example

The support example below follows this workflow with scripted tools and model responses.

Quickstart

The DSL defines repeatable steps, uses Jev for focused decisions, and calls an agent when the work needs investigation. Your application keeps its tools, model access, permissions and budgets.

Requires Node 22.19+ and npm. In your project:

npm install @parcha/agentrun-dsl@beta
npx @parcha/agentrun-dsl@beta demo

This ticket-routing demo uses scripted decisions and needs no API key. Next, run and change a workflow in your own app. To run the support workflow shown above, use the checkout below. To build workflows with your agent, install the Pi extension.

Run the support example

To run the workflow in the animation, clone the examples and build:

git clone --branch main --single-branch https://github.com/Parcha-ai/agentrun.git
cd agentrun
# With nvm: nvm install && nvm use
npm ci --ignore-scripts
npm run build
npm run demo:support

This runs the interpreter with scripted tools, Jev answers, and agent responses. It needs no API key and sends no customer replies.

The command prints a report for each case:

npm run demo:support -- payment
npm run test:support

Try npm run demo:support -- unresolved to see an escalation. It exits with code 2. The responses are scripted; changing a prompt does not change them.

Connect live Jev and your agent, or give these instructions to your coding agent.

Use one piece, or all of it

Use one piece

Each package works on its own. Pi is an open-source coding agent; pi-durable is Pi's runtime that commits each turn and tool call to storage; chord is the plugin and service runtime pi-durable is built on; Archil is a network disk you mount on any Linux host.

A held package is built, tested and verified with the others, and its manifest says "private": true; it installs from a packed tarball, not from npm.

Use all of it

One program puts the packages together and runs a job end to end on pi-durable: a durable run, the recovery driver, the node runner, the browser and vision. It uses a scripted model and a fake browser, needs no key, and prints the record and the receipts it cites.

npm ci --ignore-scripts
npm run build
npm run demo:reference

examples/reference/ has the job; the host is the package @parcha/agentrun-harness. What a host supplies lists the seven functions the packages ask a host for, the install order and why, and what the example does not do yet.

What a workflow looks like

The support workflow requires answer text and a source reference. Jev must also answer yes with confidence of at least 0.8. Otherwise, the workflow allows one agent attempt and checks again. If the answer still fails those checks, it escalates for review. You choose the criteria and thresholds for your task.

These are the search and decision nodes from that workflow:

{
  node: 'call', label: 'find-answer', via: 'tool',
  tool: 'help.search', args: { request: '{request}' },
  out: 'Candidate', as: 'answer', deadline_s: 10,
},
{
  node: 'judge', label: 'check-existing-answer',
  state: { request: '{request}', answer: '{answer}' },
  out: 'Fit', as: 'fit',
}

Candidate and Fit refer to schemas in the workflow. Fit defines the question and its yes, no, and uncertain criteria. Code reads the decision and its confidence to choose the next step. Read the complete definition, including the agent and review path.

Write workflows as JSON or use the TypeScript builder and Zod contracts. The builder infers input and output types. The interpreter checks intermediate state paths at runtime. Workflows can call other workflows, map work in parallel, and run bounded loops.

Connect your application

Install the core and Jev adapter in your application with npm install @parcha/agentrun-dsl@beta @parcha/agentrun-jev@beta. Then:

1. Supply adapters. Connect tools through runEffect, your existing agent through runNode, and Jev decisions through createJevRunner() as runJudge.
2. Define and test the workflow. Write its schemas, steps, thresholds, and review path. Start with fixtures, then evaluate real decisions on labeled cases from your task.
3. Give your agent a workflow tool. Register a function that calls runWorkflow as one of your agent's tools. Handle the workflow's output, escalation, and errors.

The support integration guide has a config template and live command. Live Jev calls need TYPESAFE_API_KEY from the TypeSafe dashboard, separate from your coding-agent login. Workflows without Jev decisions do not need that key. See host integration for permissions, cancellation, and recovery.

Use it in Pi

With Pi installed (1.0.4 to below 1.4; CI tests 1.0.4, 1.1.0, 1.2.0 and 1.3.0), run these commands in your project:

pi install npm:@parcha/agentrun-pi@beta -l
pi --offline

-l installs in this project; --offline skips startup downloads. Pi asks whether you trust the project before loading its extension. No AgentRun checkout is needed.

• /agentrun demo loads the scripted research example; /agentrun run repeats it without model calls.
• /agentrun demo live uses your configured Pi model and Jev.
• /agentrun status checks setup; /agentrun shows the graph; /agentrun stop requests cancellation.

Once Pi has model access, ask it to build a workflow:

/agentrun Research how this repository handles cancellation. Investigate the runtime and tests separately, then report gaps with file references.

Pi uses the packaged skill to build, inspect, and run the workflow. Run /reload if you install into an open Pi session. Use /agentrun save <name> and /agentrun load <name> for project-local definition revisions. Saves contain neither run input nor execution permission. Pi setup and limits.

More examples

Research demo

From the built checkout, run a scripted research workflow: "Should our team move its docs from a wiki into the code repository?"

npm run demo
npm run eval:research

It plans subquestions, researches them in parallel, screens evidence, and writes a report. The evaluation checks six labeled cases with scripted responses. Connect real Jev and Pi models.

Packages, status, and contributing

Every published package is at one version under npm's beta dist-tag; npm view @parcha/agentrun-dsl dist-tags prints it. The status column of Use one piece says which packages are published. See the changelog and contracts and limits.

Ordinary functions may be enough for a fixed sequence. AgentRun stores the steps in a workflow document that you can inspect, rerun, or call from an agent. Code nodes execute JavaScript with process privileges; untrusted workflow authors require a host-controlled sandbox. Typed decisions and validated output shapes do not prove that an answer is factually correct.

For development setup and checks, see Contributing. Open an issue for bugs or proposals.

Code and documentation use Apache-2.0. Copyright 2026 Parcha Labs, Inc. Dependencies retain their own licenses. Built by Grep.ai.