`harness` is the thin, durable turn loop that turns a model plus a few iii
workers into an agent. It takes an incoming message, persists it, assembles a
context, streams a completion, runs any function calls the model requests, and
repeats until the turn stops — all as durable, resumable steps so a crash or
restart picks up mid-turn. It wires [`session-manager`](https://github.com/iii-hq/workers/tree/main/session-manager)
(transcript), [`context-manager`](https://github.com/iii-hq/workers/tree/main/context-manager) (token budgeting, soft
dependency), and [`llm-router`](https://github.com/iii-hq/workers/tree/main/llm-router) (generation); install those
alongside it for the full loop.
## Quickstart
Install the engine, start it, then add harness and the console from a second
terminal in the same folder:
```bash
curl -fsSL https://install.iii.dev/iii/main/install.sh | sh
mkdir iii-app && cd iii-app
touch config.yaml
iii -c config.yaml
```
```bash
# New terminal, SAME folder. `iii worker add` writes to the config.yaml in the
# current directory, so it has to match the directory the engine runs in.
cd iii-app
iii worker add harness console
```
```bash
open http://localhost:3113
```
Add a model key from the console: open the model picker and use **configure
Anthropic** / **configure OpenAI** to paste a key. It is stored in the
`llm-router` worker config and the model catalog populates within seconds.
Until a provider is configured the picker is empty and chat will not generate.
