miii webSee it ›
Free forever. Works with any model.
A professional-grade coding agent for your terminal or your browser — it plans, reads, writes and verifies code. Bring your own keys (Claude, GPT, Gemini, DeepSeek) or run it 100% locally on your GPU.
Apna code, apna model, apni marzi.
The model runs on your GPU. Nothing is metered, nothing is uploaded, and it keeps working with the wifi off.
Private by default
Cloud agents ask you to trust your codebase to someone else's server. miii talks to a model on localhost, so nothing touches the wire.
Cost
No per-token billing. It runs on your hardware.
Offline
No keys, no account, no network needed.
A real agent, not a chat box
Exact edits instead of blind rewrites, and it runs your tests before it says it's done.
Permission-gated
Every write and shell command asks first, and file tools stay inside your workspace. "Always" rules are saved per project.
Runs on
Lossless output
Huge tool output goes to disk with a preview of the start and end, and the model reads the middle when it needs to.
Model doctor
miii doctor tests your local models on real engineering tasks.
Requires Node.js 18 or later and Ollama running locally.
ollama pull qwen2.5-coder:14b
npm install -g miii-agent
miii > @src/server.ts add rate limiting > why are my tests failing?
miii webThe same agent in a desktop-style app in your browser — for when you'd rather click than type. Same sessions, same models, same permission rules as the terminal.
Chat, diffs and approvals
Replies stream in, each tool call opens to show the exact command and its output, edits show as real diffs, and every write waits for your click.
One command
It starts a local server and opens your browser. Add --port, --no-open or -c to resume your last chat.
miii web # or: miii --web
Locked to your machine
It listens on localhost only, and every request needs the one-time key in the link miii prints. Other sites can't reach it.
/ away.The same command list you get inside miii. Type to filter, then press enter or click to copy. Press / anywhere on this page to jump here.
Read live from CHANGELOG.md every time the page loads.
Yes. miii is MIT-licensed with no paid tier, no account and no sign-up. With a local model you pay nothing at all.
With a local provider, your code only ever travels to localhost. No telemetry and no analytics — the one outbound call miii makes on its own is a version check against registry.npmjs.org, which carries nothing but the package name.
Every write and every shell command asks first, and file tools are confined to the working directory. When something does go wrong, /rewind puts the files and the conversation back.
Yes — run miii web in any project and it opens in your browser: a chat sidebar, streaming replies, real diffs and one-click approvals. It's the same agent and sessions as the terminal, served only on localhost, and every request needs the key in the link it prints.
For fully local models you want one — qwen2.5-coder:3b runs on CPU, but it will be slow and need more hand-holding. Apple Silicon works well: unified memory counts as VRAM here.
Use them if you can. miii is for when you want the same workflow without being tied to one vendor or one subscription — or you need to go fully offline for air-gapped work, NDA'd code, or a flight with no wifi.
No keys, no billing, no cloud. A coding agent in your terminal in under a minute.