ai-agent

openinterpreter

Name: openinterpreter
Author: openinterpreter

A coding agent for open models like Kimi K3

68,564 stars+54★ this week5,895 forksRustUpdated 10/11/2026100% free · open source

What it does

OpenInterpreter is a coding agent that allows you to interact with open models like Kimi K3, enabling you to generate code and explore their capabilities

When to use it

•You need to generate code for a specific task using an open model
•You want to explore the capabilities of a model like Kimi K3
•You need to integrate a coding agent into your development workflow

Ready-to-paste prompt

openinterpreter --model kimi_k3 --prompt 'generate a simple Rust program to print Hello World'

Heads up: Make sure you have Rust and Cargo installed on your system, as OpenInterpreter is built using Rust and relies on Cargo for building and dependency management

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/openinterpreter && curl -fsSL https://workflowstacks.com/api/skills/openinterpreter/claude-skill -o ~/.claude/skills/openinterpreter/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How openinterpreter works

Codeflow

Free to inspect

Openinterpreter is a very large Rust project (~995k lines across 3463 code files, plus 488 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~995k lines · 3463 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Node.js

No API keys detected

Rust 96%Python 3%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
package.json
Dependencies and the commands it exposes
4
codex-rs/core/README.md
Inside codex-rs/core/ — the main logic begins here

What's in each folder

codex-rs/core/Core code — the actual logic691 files

codex-rs/skills/Prompts, skills & agent definitions79 files

codex-rs/prompts/Prompts, skills & agent definitions33 files

codex-rs/core-skills/Prompts, skills & agent definitions19 files

codex-rs/cli/Command-line entry points60 files

codex-rs/connectors/Sub-packages / plugins22 files

codex-rs/plugin/Sub-packages / plugins9 files

docs/Documentation104 files

READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month