Disclaimer: This project is not affiliated with, endorsed by, or associated with OpenClaw. It is an independent .NET implementation inspired by their work.
Self-hosted AI agent runtime and gateway for .NET with 48 native tools, 9 channel adapters, multi-agent routing, review-first self-evolving features, built-in OpenAI/Claude/Gemini provider support, NativeAOT support, and practical OpenClaw ecosystem compatibility.
- NativeAOT-friendly runtime and gateway for .NET agent workloads
- 48 native tools covering file ops, sessions, memory, web, messaging, home automation, databases, email, and more
- 9 channel adapters (Telegram, SMS, WhatsApp, Teams, Slack, Discord, Signal, email, webhooks) with DM policy, allowlists, and signature validation
- Native LLM providers for OpenAI, Claude, Gemini, Azure OpenAI, Ollama, and OpenAI-compatible endpoints
- Practical reuse of existing OpenClaw TS/JS plugins and
SKILL.mdpackages - Review-first self-evolving workflows โ the runtime proposes profile updates, automation drafts, and skill drafts from observed sessions; operators approve or reject
git clone https://github.com/clawdotnet/openclaw.net
cd openclaw.net
export MODEL_PROVIDER_KEY="sk-..."
dotnet run --project src/OpenClaw.Cli -c Release -- setup
dotnet run --project src/OpenClaw.Cli -c Release -- setup launch --config ~/.openclaw/config/openclaw.settings.jsonWhen the gateway prints its Gateway ready banner, open:
| Surface | URL |
|---|---|
| Web UI / Live Chat | http://127.0.0.1:18789/chat |
| Admin UI | http://127.0.0.1:18789/admin |
| Integration API | http://127.0.0.1:18789/api/integration/status |
| MCP endpoint | http://127.0.0.1:18789/mcp |
The root URL redirects to /chat. For the full first-run walkthrough (including the "First 10 Minutes" runbook and debugging flow), see docs/QUICKSTART.md. For the project shape and repository map before changing code, see docs/GETTING_STARTED.md.
If the CLI is already on your PATH, the same guided entrypoints are:
openclaw setup
openclaw setup launch --config ~/.openclaw/config/openclaw.settings.json
openclaw setup service --config ~/.openclaw/config/openclaw.settings.json --platform all
openclaw setup status --config ~/.openclaw/config/openclaw.settings.jsonUseful follow-up commands and surfaces:
openclaw skills inspect ./skills/my-skill
openclaw compatibility catalog
openclaw migrate upstream --source ./upstream-agent --target-config ~/.openclaw/config/openclaw.settings.json- Skill inventory:
/admin/skills - Observability summary:
/admin/observability/summary - Audit export:
/admin/audit/export - Compatibility matrix: docs/COMPATIBILITY.md
Breaking change: browser admin usage is account/session-first. Use named operator accounts for
/admin, and use operator account tokens for Companion, CLI, API, and websocket clients.
When binding to a non-loopback address, the gateway refuses to start unless dangerous settings are explicitly hardened (auth token required, tooling roots restricted, signature validation enforced, raw: secret refs rejected). See SECURITY.md before exposing the gateway publicly.
The full documentation map lives at docs/README.md. Starting points:
| Doc | When to read |
|---|---|
| docs/GETTING_STARTED.md | Project shape, repository map, and first-run debugging flow |
| docs/QUICKSTART.md | Shortest supported path to a running local instance |
| docs/USER_GUIDE.md | Providers, tools, skills, memory, channels, and day-to-day operation |
| docs/TOOLS_GUIDE.md | Native tool catalog and configuration |
| docs/MODEL_PROFILES.md | Provider-agnostic named model profiles (including Gemma) |
| docs/COMPATIBILITY.md | Supported upstream skill, plugin, and channel surface |
| SECURITY.md | Hardening guidance for public deployments |
Contributions welcome โ especially security review, NativeAOT trimming improvements, sandboxing ideas, new channel adapters, and performance benchmarks. See CONTRIBUTING.md.
If this project helps your .NET AI work, please star it.