Who is openclaude for?

Developers comfortable in a terminal who want a coding agent that is not tied to one model vendor; you should have Node.js 22 or newer and an API key or a local model server.

What can you build with openclaude?

Run a coding agent against a local Ollama model so your code stays on your machine. Switch between OpenAI, Gemini and OpenRouter models from the same terminal tool to compare results. Start a long refactor in the background and follow its logs while you do other work. Connect MCP servers to a coding agent that uses the model provider you already pay for. Resume or branch an earlier conversation to try a different approach to the same task.

Twigpine /

openclaude

A terminal coding agent that works with cloud and local models from one interface

34.1k stars
500 stars since 3 Oct
TypeScript
Updated today
Some experience
Coding agents & dev tools

Open on GitHub (opens in a new tab) Website (opens in a new tab)

OpenClaude is a command-line coding assistant. You open it in a project folder, describe a task, and it can run shell commands, read and edit files, search code, and call tools for you. It streams its output as it works.

The main idea is that the model behind it is your choice. You can point it at a hosted service such as OpenAI, Gemini, OpenRouter, DeepSeek or Groq, or at a model on your own machine through Ollama or LM Studio. A /provider command walks you through setup and saves profiles so you can switch later.

It keeps its own config under ~/.openclaude and does not read Claude Code settings, so Claude Code does not need to be installed. It also supports background sessions, resuming or forking past conversations, a headless gRPC server, and a bundled VS Code extension.

What it does

Many model backends
Works with OpenAI-compatible servers, Gemini, GitHub Models, Codex, Ollama, Atomic Chat and others. You can use local or hosted models.
Guided provider setup
The /provider command helps you configure a backend and saves profiles and credentials. /onboard-github covers GitHub Models.
Coding-agent toolset
Bash, file tools, grep, glob, agents, tasks, MCP, slash commands and web tools live in one terminal workflow.
Background sessions
Run long prompts detached with --bg, then check them with ps, logs and kill. They run as local child processes with no daemon.
Resume and fork conversations
Use --resume or --continue to pick up earlier work, and --fork-session to branch the history. Forking does not copy your working tree.

What you could build

Run a coding agent against a local Ollama model so your code stays on your machine.
Switch between OpenAI, Gemini and OpenRouter models from the same terminal tool to compare results.
Start a long refactor in the background and follow its logs while you do other work.
Connect MCP servers to a coding agent that uses the model provider you already pay for.
Resume or branch an earlier conversation to try a different approach to the same task.

Get started

Install it with npm (Node.js 22 or newer), then run openclaude in your project folder. Inside it, run /provider to pick a model backend and save your credentials.

npm install -g @gitlawb/openclaude@latest

openclaude

Commands are copied from the project's README. Read it on GitHub for the full setup.