gitwtfhub

wtf is steerplane?

vijaym2k6/steerplane — explained in plain English

Analysis updated 2026-05-18

2PythonAudience · developerComplexity · 3/5LicenseSetup · easy

TL;DR

A runtime guardrail library that wraps autonomous AI agents with cost limits, loop detection, and observability using a single decorator.

Mindmap

mindmap
  root((repo))
    What it does
      Wraps AI agents with limits
      Detects repeating loops
      Logs cost and steps in real time
    Tech stack
      Python
      TypeScript
      Docker
    Use cases
      Cap agent spending
      Stop stuck agent loops
      Add human approval steps
    Audience
      AI agent developers
      Platform teams

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

Why would anyone build with this?

REASON 1

Cap how much an autonomous AI agent can spend before it gets shut down.

REASON 2

Detect and stop an AI agent stuck in a repeating action loop.

REASON 3

Add a human approval step before an AI agent can exceed a cost or action limit.

What's in the stack?

PythonTypeScriptFastAPINext.jsDocker

How it stacks up

vijaym2k6/steerplane0-bingwu-0/live-interpreter010zx00x1/faresnipe
Stars222
LanguagePythonPythonPython
Setup difficultyeasymoderateeasy
Complexity3/52/52/5
Audiencedevelopergeneralgeneral

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

How do you spin it up?

Difficulty · easy Time to first run · 30min

Docker Compose is the recommended path, manual setup needs Python and Node.js installed separately.

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

Wtf does this do

SteerPlane is a runtime safety layer for autonomous AI agents, the kind of software that can call APIs, run code, and take actions on its own. Without any oversight, that kind of agent can get stuck repeating the same actions in a loop, spend an enormous amount of money on API calls overnight, or take a destructive action with nobody noticing until it is too late. SteerPlane's stated goal is to prevent those failure modes by wrapping an agent's run loop with limits and monitoring, added with a single decorator around the function that runs the agent. Once wrapped, every step the agent takes is logged along with its token usage, dollar cost, and how long it took. You can set a maximum dollar budget and a maximum number of steps for a single run, deny specific kinds of actions by name pattern, such as anything starting with delete or sudo, and set rate limits on how often a particular action can happen in a given time window. SteerPlane can either kill a run outright when a limit is broken, or pause it and alert a human for approval before continuing, depending on how it is configured. It also includes a sliding window algorithm for detecting when an agent is repeating the same action or pattern of actions, catching this without needing an extra call to a language model to check. Beyond the core Python and TypeScript libraries, the project includes a proxy gateway that can enforce these same limits on API traffic without changing any application code, a real time web dashboard for watching runs as they happen, a command line tool for managing runs and API keys, and ready made integrations for popular agent frameworks including LangChain, the OpenAI Agents SDK, CrewAI, and AutoGen. If the central service is ever unreachable, the underlying library keeps enforcing limits locally so an agent is never left unprotected. The core project runs on Docker with a bundled database, and its code is released under the MIT license, though some advanced features such as human approval notifications are reserved for a separate hosted plan.

Yoink these prompts

Prompt 1
Help me wrap my Python AI agent with SteerPlane's guard decorator and set a cost limit.
Prompt 2
Explain the difference between SteerPlane's kill and alert enforcement modes.
Prompt 3
Help me set up the SteerPlane gateway proxy so it enforces limits on my OpenAI API calls.
Prompt 4
Walk me through integrating SteerPlane with my LangChain agent.

Frequently asked questions

wtf is steerplane?

A runtime guardrail library that wraps autonomous AI agents with cost limits, loop detection, and observability using a single decorator.

What language is steerplane written in?

Mainly Python. The stack also includes Python, TypeScript, FastAPI.

What license does steerplane use?

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

How hard is steerplane to set up?

Setup difficulty is rated easy, with roughly 30min to a first successful run.

Who is steerplane for?

Mainly developer.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.