Pre-release Harn is pre-1.0 — the language, standard library, and CLI may change between releases. See the release notes

Harn

Harn is a programming language and runtime for building AI agents. Model calls, tools, retries, concurrency, transcripts, and workflows are language and standard-library features, so programs need less orchestration glue.

example.harn
fn main(harness: Harness) {
  const response = harness.llm.call(
    "Explain quicksort in two sentences.",
    "You are a computer science tutor.",
    { provider: "mock" }
  )
  harness.stdio.println(response.text)
}

That runs with no API key: the mock provider is deterministic and offline. Getting started installs Harn and runs it.

When Harn helps#

Harn helps when you want agent behavior to read like a program: which model runs, when a tool fires, how a failure is handled, and what the run records. You do not need experience with an agent framework. Familiarity with one programming language or with large language models (LLMs) will make some terms feel familiar, but it is not required.

For one model call, an existing SDK may be enough. Harn becomes more useful as your program gains tools, retries, multiple providers, concurrency, replay, or long-running work. Harn also includes a portal for inspecting persisted runs.

Building blocks#

Harn supports one model request, an agent loop, or a multi-stage workflow. Start with the smallest building block that fits the task:

NeedStart with
One request and one responseharness.llm.call
A model that can use tools across turnsagent_loop
Named stages with joins and retriesworkflow_execute

Put any of these in fn main or a named pipeline. Add a larger abstraction only when the program needs it. The expressiveness spectrum shows the same task as a model call, an agent loop, and a workflow.

Where to go next#

  • Why Harn? explains the design with the same program in Python and Harn.
  • Coming from elsewhere maps Harn terms to other agent tools and protocols.
  • The feature matrix compares runtime guarantees across Harn, Inngest, Temporal, LangGraph, and Cursor Automations.
  • The mental model shows how Harn's parts fit.
  • Common tasks starts from a goal you want to complete.

Harn owns the reusable agent behavior: orchestration, model and tool calls, transcripts, replay and evaluation, worker lineage, and capability policy. Your application keeps its own interface, approval flow, file changes, and product data. In practice, you write the steps the agent should take. The Harn virtual machine (VM) handles provider adapters, retries, transcripts, and runtime policy. The host boundary explains the full split.

Harn at a glance#

Paradigm
Pipeline-oriented, imperative, with structured concurrency
Typing
Gradual and structural. Annotations are optional everywhere.
Implemented in
Rust, as a lexer, parser, type checker, and tree-walking VM
Runs on
macOS and Linux on Intel and ARM, Windows on x86-64. Platform support has the detail.
File extensions
.harn for programs. .harn.prompt for prompt templates.
Speaks
MCP, ACP, and A2A, natively
License
MIT or Apache-2.0, at your option
Maturity
Pre-1.0. Surface-level breaking changes are possible between minor and patch releases. See the changelog.
Edit this page on GitHub