whatisgithub

What is auto?

rightnow-ai/auto — explained in plain English

Analysis updated 2026-05-18

116RustAudience · developerComplexity · 4/5LicenseSetup · hard

In one sentence

A tool that watches an AI agent work, converts its repeated predictable behavior into small fast programs, and only calls the expensive AI model again when it sees something genuinely new.

Mindmap

mindmap
  root((Auto))
    What it does
      Records agent behavior
      Extracts predictable parts
      Compiles to small programs
    Tech stack
      Rust
      WebAssembly
      Python
    Use cases
      Cut AI model costs
      Verify agent logic
      Sandbox execution
    Audience
      AI agent developers
      Infrastructure engineers

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Cut down on repeated AI model calls for an agent that performs the same kind of task often.

USE CASE 2

Turn recorded AI agent behavior into a small, fast, verified program.

USE CASE 3

Run AI-agent-derived logic safely inside a restricted sandbox environment.

USE CASE 4

Track and cap real dollar spend on AI model calls used as a fallback path.

What is it built with?

RustWebAssemblyPython

How does it compare?

rightnow-ai/autoyarlabs/hyperspace-dbxqnode/codex-helper
Stars116113110
LanguageRustRustRust
Setup difficultyhardhardeasy
Complexity4/55/52/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1h+

Requires a pinned Rust toolchain and an exact-version flatc compiler, paid fallback paths need an OpenAI API key.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

So what is it?

Auto is a tool that watches an AI agent work and turns the repeated, predictable parts of what it does into small, fast, cheap programs, so the expensive AI model does not have to be called again for the same kind of task. It first records what an agent actually does when performing a task: which tools it calls, what arguments it passes, what results come back. It then checks which of those actions always turn out the same way given the same input, since those parts do not really need an AI model at all, just ordinary code. Those predictable parts get extracted into small, verified programs, and anything left over that still varies gets compressed into much smaller specialist models. The result is a compact package, called a cbin, containing code, small models, and a report describing what was measured about it. When Auto runs, it first tries the compiled, fast path for a given input. If that input looks unfamiliar or too different from what was recorded before, it falls back to the original, larger AI model, records what happens this time, and folds that new information back into the compiled version so the same situation is not solved from scratch again next time. The project calls this a ratchet: nothing gets figured out twice. The compiled programs run inside a sandbox, a restricted environment that can only do what it is explicitly allowed to do, so a compiled program cannot exceed its stated capabilities. According to the measurements reported in the project's own results, the cost of running each task fell from about 59 millionths of a dollar using the large AI model every time, down to about 2 millionths of a dollar per task once the compiled path took over, while matching the reference AI model's answers on familiar inputs the large majority of the time. Response speed on the compiled path was also reported as dramatically faster than calling the AI model directly. This project is built with the Rust programming language and is aimed at people building AI agent systems who want to cut down on repeated AI model costs. The project's own documentation includes a research paper describing the measurements in detail. It is released under the Apache 2.0 license, which permits free use, including commercial use.

Copy-paste prompts

Prompt 1
Help me set up Auto to record my AI agent's behavior using the Python SDK.
Prompt 2
Walk me through building a .cbin artifact from recorded agent traces with the auto-cli tool.
Prompt 3
Explain what determinism the auto-cli report command found in my recorded agent behavior.
Prompt 4
Show me how to safely enable the paid frontier fallback path with a spend cap.

Frequently asked questions

What is auto?

A tool that watches an AI agent work, converts its repeated predictable behavior into small fast programs, and only calls the expensive AI model again when it sees something genuinely new.

What language is auto written in?

Mainly Rust. The stack also includes Rust, WebAssembly, Python.

What license does auto use?

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

How hard is auto to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is auto for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.