explaingit

gitlawb/zero

Analysis updated 2026-05-18

803GoAudience · developerComplexity · 2/5LicenseSetup · easy

TLDR

A local terminal coding assistant that reads, edits, and runs code using your choice of AI model, with sessions stored on your own machine and a layered permission system for file and shell access.

Mindmap

mindmap
  root((zero))
    What it does
      Edit and read code
      Run shell commands
      Search codebase
      Resume sessions
    Model flexibility
      25+ AI providers
      Local Ollama support
      Switch mid-session
    Interfaces
      Interactive terminal UI
      Headless exec command
      Stream JSON for CI
    Safety
      Permission levels
      File write controls
      Secrets redaction
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

What do people build with it?

USE CASE 1

Ask Zero to fix a failing test in a Go package without leaving the terminal or pasting code into a browser.

USE CASE 2

Run `zero exec` in a CI pipeline to automatically apply a code change described in plain English and check the exit code for success.

USE CASE 3

Switch between OpenAI and a locally running Ollama model mid-session depending on the task without changing any configuration files.

USE CASE 4

Resume a previous coding session exactly where it left off, including the conversation history and any partial edits.

What is it built with?

GoNode.jsnpm

How does it compare?

gitlawb/zeromitchellh/hashstructuremitchellh/panicwrap
Stars803768453
LanguageGoGoGo
Last pushed2023-01-032024-04-05
MaintenanceDormantDormant
Setup difficultyeasyeasyeasy
Complexity2/52/52/5
Audiencedeveloperdeveloperdeveloper

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

How do you get it running?

Difficulty · easy Time to first run · 5min

Requires an API key for a cloud AI provider, or a locally running Ollama or LM Studio instance for fully offline use.

MIT license, use, modify, and distribute freely for any purpose including commercial, as long as the copyright notice is kept.

In plain English

Zero is a coding assistant that runs in your terminal and takes instructions in plain English to read, edit, and run code in a project. Unlike cloud-hosted AI coding tools where sessions and data pass through a company's servers, Zero keeps everything local: your conversations are stored on your own disk, never uploaded as telemetry, and can be picked up again in a later session from where you left off. One of the main design choices is that Zero does not lock you into a single AI model. You can connect it to over 25 different providers, including OpenAI, Anthropic, Gemini, Groq, DeepSeek, Mistral, and others. Local model runners like Ollama and LM Studio also work, so you can run entirely offline if you prefer. Switching the model is a single command or a menu selection. When you open Zero it launches a terminal interface with a text area for your request, a sidebar that shows what the assistant is planning and doing, and controls for adjusting settings mid-session. You can ask it to fix a failing test, refactor a file, explain a piece of code, or work through a larger task step by step. For scripted use, a separate command called zero exec runs a single task without the interface, accepts and produces structured data formats, and exits with a meaningful status code so it can fit into automated workflows. Zero has a layered permission system. Reading files is allowed by default. Writing files, running shell commands, and accessing the network require either your approval or a permission level you set upfront. If you want the assistant to also write to a folder outside the current project, you grant that explicitly with a flag or a slash command. This design is meant to make it clear what the assistant is doing and limit unintended changes. The tool is written in Go, distributed as a single binary, and installs via npm, a curl script, or from source. It runs on Linux, macOS, and Windows.

Copy-paste prompts

Prompt 1
I am trying Zero for the first time. Walk me through setting up an Anthropic provider, picking a model, and running my first coding task in the terminal UI.
Prompt 2
I want to use `zero exec` in a GitHub Actions workflow to automatically fix a specific code smell on each push. Show me the workflow step and the zero exec command with stream-JSON output.
Prompt 3
How do I configure Zero to use a locally running Ollama model instead of a cloud provider? Walk me through the provider detection and setup commands.
Prompt 4
I want Zero to be able to write files in both my main project and a sibling docs folder. How do I grant that extra write directory, and what is the command syntax?

Frequently asked questions

What is zero?

A local terminal coding assistant that reads, edits, and runs code using your choice of AI model, with sessions stored on your own machine and a layered permission system for file and shell access.

What language is zero written in?

Mainly Go. The stack also includes Go, Node.js, npm.

What license does zero use?

MIT license, use, modify, and distribute freely for any purpose including commercial, as long as the copyright notice is kept.

How hard is zero to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is zero for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub gitlawb on gitmyhub

Verify against the repo before relying on details.