OpenClaw is a lot of things at once: a self-hosted assistant, a coding agent, a messaging bot, a cron runner, and the seed of a whole family of forks. That breadth is great once you know it and overwhelming when you’re starting. This guide is the map — what to set up first, how to point it at a cheap model, which skills matter, and when a fork beats the original.
Treat it as the hub. Each section is a short orientation that links to a full walkthrough, so come back here whenever you’re deciding what to do next. If you don’t yet know what OpenClaw is at all, read the explainer first.
The five things that make up OpenClaw
Hold these five pieces and the rest falls into place:
OpenClaw at a glance
| Piece | Role |
|---|---|
| Model provider | The brain — DeepSeek, GLM, Kimi, Qwen, or a local model |
| Channels | How you talk to it — terminal, Telegram, Discord, Slack |
| Skills | What it can do — including the coding agent |
| Scheduler | When it acts — unattended cron-style jobs |
| The daemon | The background process tying it all together |
You bring the model; OpenClaw supplies the rest. That’s the whole design, and it’s why this guide is organized around the model first, then everything you can do with it.
Step 1: get it running
Start with installation, because nothing else matters until the daemon runs. On Windows the clean path is WSL2 — OpenClaw expects a Unix-style environment, and running directly in PowerShell is the rougher road. The Windows and WSL install guide walks through it; if you’re on a fresh machine, the general WSL2 setup gets the environment ready first.
Step 2: pick a model
This is where you control cost and privacy. OpenClaw is model-agnostic, so the choice is yours:
- Cheapest pay-per-use: DeepSeek — very low token rates, OpenAI-compatible.
- Flat monthly plan: GLM — predictable billing for heavy daily use.
- Free and private: a local model via Ollama — no API bill, nothing leaves your machine.
- Other strong options: Kimi, Qwen, and MiniMax can fit too, but check OpenClaw’s current provider docs and each model’s pricing before wiring them in.
Not sure which? The simplest starting point is DeepSeek for hosted low cost or Ollama for local privacy. Once you know the workflow is useful, compare model prices in the broader cheapest AI coding API guide.
Step 3: use the skills
Skills are what turn a model into an assistant that acts. The coding agent is the headline one — it reads issues, writes fixes, and opens PRs as a background process, covered in the coding agent tutorial. Beyond that, browse the project’s own skill docs and install only the skills that match work you actually want automated.
Step 4: decide between OpenClaw and a fork
OpenClaw is the most feature-complete option, and also the heaviest. The fork wave produced lighter alternatives, each with a clear trade:
OpenClaw and its main forks
| Project | The pitch |
|---|---|
| OpenClaw | Most features, most channels — the full experience |
| nanobot | Python, minimal, easy to read and audit |
| ZeroClaw | Rust, runs on tiny/cheap hardware and VPSes |
| PicoClaw | Go single binary, runs on a Raspberry Pi |
| NanoClaw | TypeScript, container-isolated for safety |
If you want everything, stay on OpenClaw. If you want light, auditable, tiny-hardware, or container-isolated, a fork or rewrite may fit better. The full comparison, including source links for nanobot, ZeroClaw, PicoClaw, and NanoClaw, is in OpenClaw vs its forks.
Step 5: keep cost and security in check
Two things to get right before you lean on it daily.
Cost. An always-on assistant looping overnight on a premium model adds up. The fix is cheap hosted models, local models, and conservative schedules. Start with DeepSeek, GLM, or Ollama instead of a premium model by default.
Security. OpenClaw runs with real access to files, commands, and your messaging accounts. Scope it, keep keys in environment variables, and think before pointing it at anything sensitive.
A sensible first run
If you want a concrete starting path rather than the full menu:
Your first OpenClaw setup
- Install on Windows via WSL2 (or natively on macOS/Linux)
- Point it at DeepSeek for cheap pay-per-use, or Ollama for free/local
- Talk to it from the terminal first, add Telegram/Discord later
- Enable one skill you'll actually use — the coding agent is a good start
- Scope permissions and put your API key in an environment variable
- Only add scheduled, unattended jobs once you trust the setup
Wrapping up
OpenClaw comes down to five pieces — model, channels, skills, scheduler, daemon — and your job as a power user is to pick a model that fits your budget, enable the skills you’ll use, and decide whether the full OpenClaw or a lighter fork suits your hardware and taste. Get it running on WSL2, point it at a cheap or local model, and grow the setup from there.
Every section above links to a full guide. If you’re starting cold, go install it, then point it at DeepSeek. If you’re comparing options first, read OpenClaw vs the forks and OpenClaw vs Claude Code.
