Disclaimer: This project is not affiliated with, endorsed by, or associated with OpenClaw. It is an independent .NET implementation inspired by their work.
OpenClaw.NET is a NativeAOT-friendly AI agent runtime and gateway for .NET with practical OpenClaw ecosystem compatibility.
It is for .NET developers and operators who want a local or self-hosted agent gateway with explicit diagnostics, first-party .NET tools, OpenAI-compatible HTTP surfaces, and a path from source checkout to NativeAOT release artifacts.
- NativeAOT-friendly runtime and gateway for .NET agent workloads
- Agent runtime with tool execution, streaming, cancellation, retry, memory, and session support
- Gateway with chat UI, admin UI, OpenAI-compatible endpoints, MCP, websocket, health, and diagnostics
- CLI and Companion setup flows for source checkouts and desktop bundles
- 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
Start with docs/START_HERE.md for the evaluator overview, docs/QUICKSTART.md for the supported local setup path, or docs/RELEASES.md for desktop downloads.
For the experimental A2A v1 surface, see docs/a2a.md.
This deterministic sample proves the runtime loop and tool path without provider keys, Ollama, Docker, or a browser:
git clone https://github.com/clawdotnet/openclaw.net
cd openclaw.net
dotnet restore OpenClaw.Net.slnx
dotnet build OpenClaw.Net.slnx --configuration Release --no-restore
dotnet run --project samples/OpenClaw.HelloAgent -c Release --no-buildExpected output:
OpenClaw.HelloAgent
User: hello
Agent: hello from OpenClaw.NET
Tool: echo(hello): ok
For the lowest-friction desktop start, download the latest desktop bundle for your platform:
| Platform | Download |
|---|---|
| Windows x64 | openclaw-desktop-win-x64.zip |
| Apple Silicon macOS | openclaw-desktop-osx-arm64.zip |
| Linux x64 | openclaw-desktop-linux-x64.zip |
Each desktop bundle includes Companion, the standard NativeAOT gateway, and the NativeAOT CLI.
- Extract the archive.
- Launch Companion from the
companionfolder. - Open the Setup tab.
- Choose a provider/model and enter the provider key, or choose Ollama for a local model.
- Click Set Up and Start.
Companion writes a local config, starts the bundled gateway on 127.0.0.1, and connects to it. The current Windows and macOS release archives are unsigned, so first-run OS warnings are expected. See docs/RELEASES.md for checksums, standalone CLI/gateway archives, signing status, and maintainer release flow.
For a real local gateway from source:
export MODEL_PROVIDER_KEY="sk-..."
dotnet run --project src/OpenClaw.Cli -c Release -- startWhen the gateway finishes startup it now prints explicit phase markers, a final OpenClaw gateway ready. block, the localhost URLs, Ctrl-C to stop, and any non-fatal startup notices under Started with notices:. Then 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 you want a direct gateway fallback instead of the full CLI onboarding flow, run:
dotnet run --project src/OpenClaw.Gateway -c Release -- --quickstart--quickstart is interactive-only. It applies a minimal loopback-local profile for the current process, prompts for missing provider inputs, retries on the common first-run failures, and after a successful start can save the working setup to ~/.openclaw/config/openclaw.settings.json.
If the CLI is already on your PATH, the same guided entrypoints are:
openclaw start
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.json
openclaw upgrade check --config ~/.openclaw/config/openclaw.settings.json
openclaw upgrade rollback --config ~/.openclaw/config/openclaw.settings.json --offlineUseful follow-up commands and surfaces:
openclaw models presets
openclaw models doctor
openclaw maintenance scan --config ~/.openclaw/config/openclaw.settings.json
openclaw maintenance fix --config ~/.openclaw/config/openclaw.settings.json --dry-run
openclaw skills inspect ./skills/my-skill
openclaw compatibility catalog
openclaw insights
openclaw admin trajectory export --anonymize --output ./trajectory.jsonl
openclaw upgrade check --config ~/.openclaw/config/openclaw.settings.json --offline
openclaw upgrade rollback --config ~/.openclaw/config/openclaw.settings.json --offline
openclaw migrate upstream --source ./upstream-agent --target-config ~/.openclaw/config/openclaw.settings.json- Skill inventory:
/admin/skills - Maintenance report:
/admin/maintenance - Observability summary:
/admin/observability/summary - Operator insights:
/admin/insights - Audit export:
/admin/audit/export - Trajectory export:
/admin/trajectory/export - Compatibility matrix: docs/COMPATIBILITY.md
For local Ollama setups, prefer the native root endpoint and an explicit preset:
openclaw setup --non-interactive --profile local --workspace ./workspace --provider ollama --model llama3.2 --model-preset ollama-generalOpenClaw.NET now treats Ollama as a first-class native provider at http://127.0.0.1:11434. Older /v1 endpoints still work for one compatibility cycle, but openclaw models doctor will flag them so you can migrate cleanly.
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.
Outbound web fetches and browser navigations run through OpenClaw:Tooling:UrlSafety by default. The safe default blocks loopback, private/link-local, multicast, and metadata hosts; operators can disable the policy intentionally or add BlockedHostGlobs and BlockedCidrs for environment-specific deny lists.
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/RELEASES.md | Desktop downloads, release assets, and signing status |
| docs/TOOLS_GUIDE.md | Native tool catalog and configuration |
| docs/mempalace-memory.md | Optional MemPalace.NET memory provider and temporal knowledge graph |
| docs/CANVAS_A2UI.md | Supported Canvas and A2UI visual workspace behavior |
| 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 — 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.