Add nano-gpt.com as a provider

docs/cli/index.md

@@ -297,7 +297,7 @@ Options:
 - `--non-interactive`
 - `--mode <local|remote>`
 - `--flow <quickstart|advanced|manual>` (manual is an alias for advanced)
-- `--auth-choice <setup-token|claude-cli|token|openai-codex|openai-api-key|openrouter-api-key|ai-gateway-api-key|moonshot-api-key|kimi-code-api-key|codex-cli|gemini-api-key|zai-api-key|apiKey|minimax-api|opencode-zen|skip>`
+- `--auth-choice <setup-token|claude-cli|token|openai-codex|openai-api-key|openrouter-api-key|ai-gateway-api-key|moonshot-api-key|kimi-code-api-key|nanogpt-api-key|codex-cli|gemini-api-key|zai-api-key|apiKey|minimax-api|opencode-zen|skip>`
 - `--token-provider <id>` (non-interactive; used with `--auth-choice token`)
 - `--token <token>` (non-interactive; used with `--auth-choice token`)
 - `--token-profile-id <id>` (non-interactive; default: `<provider>:manual`)
@@ -308,6 +308,7 @@ Options:
 - `--ai-gateway-api-key <key>`
 - `--moonshot-api-key <key>`
 - `--kimi-code-api-key <key>`
+- `--nanogpt-api-key <key>`
 - `--gemini-api-key <key>`
 - `--zai-api-key <key>`
 - `--minimax-api-key <key>`

docs/concepts/model-providers.md

@@ -157,6 +157,34 @@ Moonshot uses OpenAI-compatible endpoints, so configure it as a custom provider:
 }
 ```
 
+### NanoGPT
+
+NanoGPT exposes OpenAI-compatible endpoints:
+
+- Provider: `nanogpt`
+- Auth: `NANOGPT_API_KEY`
+- Example model: `nanogpt/zai-org/glm-4.7`
+- CLI: `clawdbot onboard --auth-choice nanogpt-api-key`
+
+```json5
+{
+  agents: {
+    defaults: { model: { primary: "nanogpt/zai-org/glm-4.7" } }
+  },
+  models: {
+    mode: "merge",
+    providers: {
+      nanogpt: {
+        baseUrl: "https://nano-gpt.com/api/v1",
+        apiKey: "${NANOGPT_API_KEY}",
+        api: "openai-completions",
+        models: [{ id: "zai-org/glm-4.7", name: "GLM 4.7" }]
+      }
+    }
+  }
+}
+```
+
 ### Kimi Code
 
 Kimi Code uses a dedicated endpoint and key (separate from Moonshot):

docs/providers/index.md

@@ -36,6 +36,7 @@ See [Venice AI](/providers/venice).
 - [OpenAI (API + Codex)](/providers/openai)
 - [Anthropic (API + Claude Code CLI)](/providers/anthropic)
 - [Qwen (OAuth)](/providers/qwen)
+- [NanoGPT](/providers/nanogpt)
 - [OpenRouter](/providers/openrouter)
 - [Vercel AI Gateway](/providers/vercel-ai-gateway)
 - [Moonshot AI (Kimi + Kimi Code)](/providers/moonshot)

docs/providers/models.md

@@ -33,6 +33,7 @@ See [Venice AI](/providers/venice).
 
 - [OpenAI (API + Codex)](/providers/openai)
 - [Anthropic (API + Claude Code CLI)](/providers/anthropic)
+- [NanoGPT](/providers/nanogpt)
 - [OpenRouter](/providers/openrouter)
 - [Vercel AI Gateway](/providers/vercel-ai-gateway)
 - [Moonshot AI (Kimi + Kimi Code)](/providers/moonshot)

docs/providers/nanogpt.md

@@ -0,0 +1,66 @@
+---
+summary: "Use NanoGPT's OpenAI-compatible API in Clawdbot"
+read_when:
+  - You want to use NanoGPT as a model provider
+  - You need a NanoGPT API key or base URL setup
+---
+# NanoGPT
+
+NanoGPT exposes OpenAI-compatible endpoints. Clawdbot registers it as the
+`nanogpt` provider.
+
+## Quick setup
+
+1) Set `NANOGPT_API_KEY` (or run the wizard below).
+2) Run onboarding:
+
+```bash
+clawdbot onboard --auth-choice nanogpt-api-key
+```
+
+The default model is set to:
+
+```
+nanogpt/zai-org/glm-4.7
+```
+
+## Config example
+
+```json5
+{
+  env: { NANOGPT_API_KEY: "sk-..." },
+  agents: {
+    defaults: {
+      model: { primary: "nanogpt/zai-org/glm-4.7" },
+      models: { "nanogpt/zai-org/glm-4.7": { alias: "GLM 4.7" } }
+    }
+  },
+  models: {
+    mode: "merge",
+    providers: {
+      nanogpt: {
+        baseUrl: "https://nano-gpt.com/api/v1",
+        apiKey: "${NANOGPT_API_KEY}",
+        api: "openai-completions",
+        models: [
+          {
+            id: "zai-org/glm-4.7",
+            name: "GLM 4.7",
+            reasoning: true,
+            input: ["text"],
+            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+            contextWindow: 200000,
+            maxTokens: 65535
+          }
+        ]
+      }
+    }
+  }
+}
+```
+
+## Notes
+
+- Model refs use `nanogpt/<modelId>`.
+- If you enable a model allowlist (`agents.defaults.models`), add every model you plan to use.
+- For the full provider catalog and configuration rules, see [Model providers](/concepts/model-providers).

docs/start/wizard.md

@@ -248,6 +248,17 @@ clawdbot onboard --non-interactive \
   --gateway-bind loopback
 ```
 
+NanoGPT example:
+
+```bash
+clawdbot onboard --non-interactive \
+  --mode local \
+  --auth-choice nanogpt-api-key \
+  --nanogpt-api-key "$NANOGPT_API_KEY" \
+  --gateway-port 18789 \
+  --gateway-bind loopback
+```
+
 OpenCode Zen example:
 
 ```bash