explaingit

litellm-labs/lite-harness

16JavaScriptAudience · developerComplexity · 3/5LicenseSetup · moderate

TLDR

A Docker server that lets teams deploy and run AI coding agents like Claude Code, Copilot, and Codex from one shared place, with scheduling, a secrets vault, sandboxed execution, and a human-approval inbox so each team member does not need their own agent setup.

Mindmap

mindmap
  root((lite-harness))
    What it does
      Shared agent server
      Task scheduling
      Secrets vault
      Human approval inbox
    Supported agents
      Claude Code
      OpenCode
      GitHub Copilot
      Codex
    Tech stack
      JavaScript
      Docker
      LiteLLM gateway
    Access methods
      Slack integration
      REST API
      CLI slash commands
Click or tap to explore — scroll the page freely

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

Things people build with this

USE CASE 1

Give your whole team a shared server for deploying AI coding agents without each person setting up their own infrastructure.

USE CASE 2

Schedule an AI agent to run on a timer and store its API credentials in a built-in vault rather than hardcoding them.

USE CASE 3

Route agent task requests through Slack or a REST API instead of requiring everyone to use the command line.

USE CASE 4

Require a human to approve an agent's proposed actions in an Inbox before they are carried out.

Tech stack

JavaScriptDockerLiteLLM

Getting it running

Difficulty · moderate Time to first run · 30min

Requires Docker and a running LiteLLM gateway instance, agent session history is lost on restart unless a persistent storage volume is mounted.

MIT license, use freely for any purpose including commercial use, just keep the copyright notice.

In plain English

Lite-harness is a server that lets teams run AI coding agents from a single shared place instead of having each person set them up individually. It wraps several popular AI coding tools, including Claude Code, OpenCode, GitHub Copilot, and Codex, under one consistent interface so they all behave the same way regardless of which tool is underneath. The main idea is that you describe what you want an agent to do in plain language, and the server takes care of deploying it, scheduling it to run on a timer, storing any secret credentials it needs in a vault, and running it in an isolated sandbox environment so it cannot affect other things on your machine or server. If you want a human to approve the agent's actions before they happen, there is an Inbox interface built in for that. Agents can also be reached through a Slack integration or directly through an API. Setting it up involves running a Docker container and connecting it to a LiteLLM gateway, which is a separate tool that routes AI requests to whichever language model provider you prefer. Once running, team members can install a command-line skill and use slash commands inside their AI coding tool to deploy agents without touching server configuration. The project was built because the maintainers found running multiple AI coding servers separately was difficult: different APIs, different session handling, different ways to pass configuration. Combining them into one Docker image with shared session storage and shared tool access was the practical fix. By default, agent session history is lost when the server restarts. Mounting a persistent storage volume solves that. The license is MIT.

Copy-paste prompts

Prompt 1
How do I start lite-harness with Docker and connect it to a LiteLLM gateway? Which environment variables do I need to configure?
Prompt 2
I want a Claude Code agent in lite-harness to run automatically every night at midnight. How do I set up a scheduled task?
Prompt 3
How do I store my OpenAI API key securely in the lite-harness secrets vault so agents can use it without hardcoding it in task definitions?
Prompt 4
How do I enable the human-approval inbox so an agent's changes wait for my explicit OK before they are executed?
Prompt 5
How do I mount a persistent volume to lite-harness in Docker so agent session history survives a container restart?
Open on GitHub → Explain another repo

← litellm-labs on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.