ClawixAI · cch-gh · May 6, 2026 · May 6, 2026
diff --git a/.dockerignore b/.dockerignore
@@ -0,0 +1,61 @@
+# Dependencies — must be installed inside the container, never copied from host
+node_modules
+**/node_modules
+
+# Build output
+.next
+**/.next
+dist
+**/dist
+build
+**/build
+
+# Generated Prisma client (regenerated in container)
+packages/api/src/generated
+
+# TypeScript incremental build info — stale buildinfo causes tsc to skip
+# emitting .d.ts files in the container. Must be recursive (**) since the
+# files live inside each package directory.
+*.tsbuildinfo
+**/*.tsbuildinfo
+
+# Git
+.git
+.gitignore
+
+# Editor / OS
+.vscode
+.idea
+.DS_Store
+**/.DS_Store
+
+# Logs
+*.log
+**/*.log
+npm-debug.log*
+pnpm-debug.log*
+
+# Env files (mounted at runtime, not baked into images)
+.env
+.env.local
+.env.*.local
+**/.env
+**/.env.local
+**/.env.*.local
+
+# Test artifacts
+coverage
+**/coverage
+.nyc_output
+playwright-report
+test-results
+
+# Misc
+.turbo
+.cache
+**/.turbo
+**/.cache
+
+# References / docs (not needed in image)
+references
+docs
diff --git a/README.md b/README.md
@@ -248,6 +248,49 @@ docker compose -f docker-compose.prod.yml up -d --build
 docker compose -f docker-compose.prod.yml logs api | grep '\[bootstrap\]'
 ```
 
+## Uninstallation
+
+Remove Clawix completely with:
+
+```bash
+pnpm run uninstall:clawix               # preserve host data
+pnpm run uninstall:clawix -- --full     # complete removal
+```
+
+### Flags
+
+| Flag            | Description                                                             |
+| --------------- | ----------------------------------------------------------------------- |
+| `--full` / `-f` | Remove Docker resources AND host data (.env, ./data/, ./skills/custom/) |
+| `--yes` / `-y`  | Skip confirmation prompt                                                |
+
+### What gets removed
+
+**Docker cleanup (default):**
+
+- Containers from both dev and prod environments
+- Images built by compose + `clawix-agent:latest`
+- Named volumes (`postgres_data`, `redis_data`, etc.)
+- Orphan containers
+
+**Host data (with `--full`):**
+
+- `.env` — configuration and secrets
+- `./data/` — runtime data, user workspaces
+- `./skills/custom/` — user-created skills
+
+### Fresh reinstall
+
+```bash
+# Full cleanup
+pnpm run uninstall:clawix -- --full -y
+
+# Reinstall from scratch
+pnpm run install:clawix
+```
+
+> Without `--full`, host data is preserved. The installer detects existing `.env` and skips configuration prompts, reusing your previous settings.
+
 ---
 
 ## Multi-Provider Support

diff --git a/docs/AGENTS.md b/docs/AGENTS.md
@@ -90,13 +90,13 @@ The page is divided into three sections:
 
 The **Public Agents** table columns:
 
-| Column      | Meaning                                         |
-| ----------- | ----------------------------------------------- |
-| **Agent**   | Agent name and internal identifier              |
-| **Model**   | Provider / model name (e.g., `openai / gpt-4o`) |
-| **Role**    | `primary` or `worker` badge                     |
-| **Type**    | `Public` (visible to all users)                 |
-| **Enabled** | Toggle switch; primary agents show "Always on"  |
+| Column      | Meaning                                                                                                             |
+| ----------- | ------------------------------------------------------------------------------------------------------------------- |
+| **Agent**   | Agent name and internal identifier                                                                                  |
+| **Model**   | Provider / model name (e.g., `anthropic / claude-sonnet-4-6`, `openai / gpt-4o`, `gemini / gemini-3-flash-preview`) |
+| **Role**    | `primary` or `worker` badge                                                                                         |
+| **Type**    | `Public` (visible to all users)                                                                                     |
+| **Enabled** | Toggle switch; primary agents show "Always on"                                                                      |
 
 ---
 
@@ -118,9 +118,9 @@ Public agents are available to all users and serve as the shared pool of officia
    | **Name**               | Yes      | 1–255 characters. Used to reference the agent by name in spawn calls.                                                   |
    | **Description**        | No       | Up to 2000 characters. Shown in the UI and injected into the primary agent's context so it knows what each worker does. |
    | **System Prompt**      | Yes      | 1–50 000 characters. Defines the agent's persona, instructions, and capabilities.                                       |
-   | **Provider**           | Yes      | Select from configured providers (e.g., `openai`, `anthropic`).                                                         |
-   | **Model**              | Yes      | Model identifier (e.g., `gpt-4o`, `claude-sonnet-4-6`). Must match the selected provider.                               |
-   | **API Base URL**       | No       | Override the provider's default endpoint. Leave blank for standard Anthropic/OpenAI endpoints.                          |
+   | **Provider**           | Yes      | Select from configured providers (e.g., `anthropic`, `openai`, `gemini`, `zai-coding`, `kimi-code`).                    |
+   | **Model**              | Yes      | Model identifier (e.g., `claude-sonnet-4-6`, `gpt-4o`, `gemini-3-flash-preview`). Must match the selected provider.     |
+   | **API Base URL**       | No       | Override the provider's default endpoint. Leave blank for the provider's built-in default.                              |
    | **Max Tokens per Run** | No       | Hard cap on tokens consumed per single run. Default: 100 000.                                                           |
 
 4. Click **Create**. The agent appears in the **Public Agents** table.
@@ -335,18 +335,18 @@ curl -X POST http://localhost:3001/api/v1/agents/sub-agents \
 
 ## Field Reference Summary
 
-| Field             | Type     | Constraints                               | Default             |
-| ----------------- | -------- | ----------------------------------------- | ------------------- |
-| `name`            | string   | 1–255 chars, required                     | —                   |
-| `description`     | string   | 0–2000 chars, optional                    | —                   |
-| `systemPrompt`    | string   | 1–50 000 chars, required                  | `""`                |
-| `role`            | enum     | `primary` or `worker`                     | `primary`           |
-| `provider`        | string   | Must match a configured ProviderConfig ID | `anthropic`         |
-| `model`           | string   | Must be compatible with the provider      | `claude-sonnet-4-6` |
-| `apiBaseUrl`      | URL      | Valid URL or null                         | `null`              |
-| `skillIds`        | string[] | Array of Skill CUIDs                      | `[]`                |
-| `maxTokensPerRun` | integer  | ≥ 1                                       | `100000`            |
-| `isActive`        | boolean  | —                                         | `true`              |
+| Field             | Type     | Constraints                               | Default                    |
+| ----------------- | -------- | ----------------------------------------- | -------------------------- |
+| `name`            | string   | 1–255 chars, required                     | —                          |
+| `description`     | string   | 0–2000 chars, optional                    | —                          |
+| `systemPrompt`    | string   | 1–50 000 chars, required                  | `""`                       |
+| `role`            | enum     | `primary` or `worker`                     | `primary`                  |
+| `provider`        | string   | Must match a configured ProviderConfig ID | `anthropic`                |
+| `model`           | string   | Must be compatible with the provider      | `claude-sonnet-4-20250514` |
+| `apiBaseUrl`      | URL      | Valid URL or null                         | `null`                     |
+| `skillIds`        | string[] | Array of Skill CUIDs                      | `[]`                       |
+| `maxTokensPerRun` | integer  | ≥ 1                                       | `100000`                   |
+| `isActive`        | boolean  | —                                         | `true`                     |
 
 ---
 

diff --git a/docs/CONFIG.md b/docs/CONFIG.md
@@ -101,12 +101,12 @@ A **Channel** is a configured integration that allows external messaging platfor
 
 ### Supported channel types
 
-| Type         | Use case                                           | Required credentials      |
-| ------------ | -------------------------------------------------- | ------------------------- |
-| **Telegram** | Bot receives messages from Telegram users          | Bot Token from @BotFather |
-| **Web**      | Built-in web chat widget / dashboard conversations | None — always available   |
-| **Slack**    | Slash commands and DMs via Slack Bolt              | App credentials (OAuth)   |
-| **WhatsApp** | Production messaging via WhatsApp Business API     | Business API credentials  |
+| Type         | Use case                                           | Required credentials                              |
+| ------------ | -------------------------------------------------- | ------------------------------------------------- |
+| **Telegram** | Bot receives messages from Telegram users          | Bot Token from @BotFather                         |
+| **Web**      | Built-in web chat widget / dashboard conversations | None — always available                           |
+| **Slack**    | Slash commands and DMs via Slack Bolt              | App credentials (OAuth)                           |
+| **WhatsApp** | Production messaging via WhatsApp Business API     | WhatsApp Business API via @whiskeysockets/baileys |
 
 ### Adding a Channel
 
@@ -198,6 +198,8 @@ Click **⋯** → **Edit**. API Key field: leave blank to keep the existing key;
 | `anthropic`  | `claude-opus-4-*`, `claude-sonnet-4-*`, `claude-haiku-4-*` | `ANTHROPIC_API_KEY`  |
 | `openai`     | `gpt-4.1`, `gpt-4o`, `gpt-4o-mini`, `o3`, `codex-*`        | `OPENAI_API_KEY`     |
 | `zai-coding` | `glm-*`                                                    | `ZAI_CODING_API_KEY` |
+| `gemini`     | `gemini-3-pro-preview`, `gemini-3-flash-preview`, etc.     | `GEMINI_API_KEY`     |
+| `kimi-code`  | (various)                                                  | `KIMI_CODE_API_KEY`  |
 | `custom`     | Any (OpenAI-compatible) — Base URL required                | —                    |
 
 → **Full detail:** [PROVIDERS.md](./PROVIDERS.md)

diff --git a/docs/GET_STARTED.md b/docs/GET_STARTED.md
@@ -10,7 +10,7 @@ Clawix lets you securely run AI-powered agents in isolated containers, coordinat
 
 ## Key Features
 
-- **Multi-Provider AI** - Anthropic, OpenAI, Azure, DeepSeek, Gemini, and custom endpoints
+- **Multi-Provider AI** - Anthropic, OpenAI, Z.AI Coding, Gemini, Kimi-code, and custom endpoints
 - **Container Isolation** - Every agent runs in a sandboxed Docker container with resource limits
 - **Warm Container Pool** - Eliminates cold-start latency for primary agents (1-3s → ~50ms)
 - **Swarm Orchestration** - Delegate complex tasks to specialized sub-agents with DAG dependencies
@@ -28,12 +28,13 @@ Clawix lets you securely run AI-powered agents in isolated containers, coordinat
 - [Node.js 20+](https://nodejs.org/)
 - [pnpm 9+](https://pnpm.io/installation) (`npm install -g pnpm`)
 - [Docker](https://docs.docker.com/get-docker/) + Docker Compose
+- [Docker Desktop](https://www.docker.com/products/docker-desktop/) (user-friendly platform for container management)
 
 ### Installation
 
 ```bash
 # 1. Clone the repository
-git clone https://github.com/clawixAI/clawix.git
+git clone https://github.com/jasonli0226/clawix.git
 cd clawix
 
 # 2. Prepare your environment file
@@ -118,6 +119,34 @@ docker compose -f docker-compose.prod.yml up -d --build
 docker compose -f docker-compose.prod.yml logs api | grep '\[bootstrap\]'
 ```
 
+### Uninstallation
+
+Remove Clawix completely:
+
+```bash
+pnpm run uninstall:clawix               # preserve host data
+pnpm run uninstall:clawix -- --full     # complete removal
+```
+
+| Flag            | Description                                                             |
+| --------------- | ----------------------------------------------------------------------- |
+| `--full` / `-f` | Remove Docker resources AND host data (.env, ./data/, ./skills/custom/) |
+| `--yes` / `-y`  | Skip confirmation prompt                                                |
+
+**What gets removed:**
+
+- **Docker cleanup (default):** containers, images, named volumes from both dev and prod environments
+- **Host data (with `--full`):** `.env`, `./data/` (workspaces), `./skills/custom/` (user skills)
+
+**Fresh reinstall:**
+
+```bash
+pnpm run uninstall:clawix -- --full -y
+pnpm run install:clawix
+```
+
+> Without `--full`, host data is preserved. The installer detects existing `.env` and reuses your previous settings.
+
 ## Architecture
 
 ```
@@ -134,7 +163,7 @@ docker compose -f docker-compose.prod.yml logs api | grep '\[bootstrap\]'
 ┌─────────────────────────────────────────────────────────────────┐
 │                        Core Engine                              │
 │   Reasoning Loops │ Tool Execution │ Swarm Coordinator          │
-│   Multi-Provider (Anthropic, OpenAI, Azure, Custom)             │
+│   Multi-Provider (Anthropic, OpenAI, Z.AI Coding, Gemini, Kimi-code, Custom)             │
 └─────────────────────────────────────────────────────────────────┘
                                 │
 ┌─────────────────────────────────────────────────────────────────┐
@@ -152,15 +181,17 @@ docker compose -f docker-compose.prod.yml logs api | grep '\[bootstrap\]'
 
 Clawix supports multiple AI providers through a unified interface:
 
-| Provider     | Detection                      | Notes                  | Status      |
-| ------------ | ------------------------------ | ---------------------- | ----------- |
-| Anthropic    | model contains "claude"        | Primary provider       | done        |
-| OpenAI       | model contains "gpt"           | Fallback               | done        |
-| Azure OpenAI | config key "azure_openai"      | Enterprise deployments | coming soon |
-| DeepSeek     | model contains "deepseek"      | Cost-effective         | coming soon |
-| Gemini       | model contains "gemini"        | Google AI              | coming soon |
-| OpenRouter   | API key starts with "sk-or-"   | Gateway                | coming soon |
-| Custom       | any OpenAI-compatible endpoint | vLLM, Ollama, etc.     | coming soon |
+| Provider     | Detection                      | Notes                  | Status  |
+| ------------ | ------------------------------ | ---------------------- | ------- |
+| Anthropic    | model contains "claude"        | Primary provider       | done    |
+| OpenAI       | model contains "gpt"           | Fallback               | done    |
+| Z.AI Coding  | model contains "glm"           | Z.AI Coding Plan       | done    |
+| Gemini       | model contains "gemini"        | Google AI              | done    |
+| Kimi-code    | model contains "kimi"          | Moonshot AI            | done    |
+| Azure OpenAI | config key "azure_openai"      | Enterprise deployments | planned |
+| DeepSeek     | model contains "deepseek"      | Cost-effective         | planned |
+| OpenRouter   | API key starts with "sk-or-"   | Gateway                | planned |
+| Custom       | any OpenAI-compatible endpoint | vLLM, Ollama, etc.     | done    |
 
 New providers can be added by defining a `ProviderSpec` entry—no code changes needed.
 
@@ -216,7 +247,7 @@ pnpm run test           # Run all tests (Vitest)
 pnpm run test:coverage  # Tests with coverage report
 pnpm run lint           # ESLint + type check
 pnpm run format         # Prettier format
-pnpm run docker:prod     # Start Postgres, Redis, pgAdmin, API, Web
+pnpm run docker:dev     # Start Postgres, Redis, pgAdmin
 pnpm run docker:down    # Stop local infra
 pnpm run db:migrate     # Run Prisma migrations
 pnpm run db:studio      # Open Prisma Studio
@@ -236,7 +267,7 @@ pnpm run db:studio      # Open Prisma Studio
 
 - **API:** NestJS 11 + Fastify adapter
 - **Frontend:** Next.js 15 + Tailwind CSS + shadcn/ui
-- **AI:** Multi-provider (Anthropic, OpenAI, Azure, DeepSeek, Gemini, custom)
+- **AI:** Multi-provider (Anthropic, OpenAI, Z.AI Coding, Gemini, Kimi-code, custom)
 - **Database:** Prisma + PostgreSQL 16
 - **Cache:** Redis 7 (ioredis)
 - **Testing:** Vitest + Playwright
@@ -290,7 +321,7 @@ We welcome contributions! Please see our contributing guidelines:
 
 ## Security
 
-If you discover a security vulnerability, please open a [GitHub Security Advisory](https://github.com/clawixAI/clawix/security/advisories/new) instead of using the public issue tracker.
+If you discover a security vulnerability, please open a [GitHub Security Advisory](https://github.com/jasonli0226/clawix/security/advisories/new) instead of using the public issue tracker.
 
 Security best practices:
 
@@ -301,8 +332,11 @@ Security best practices:
 
 ## Roadmap
 
-- [ ] WhatsApp Business API integration
+- [x] WhatsApp Business API integration
 - [ ] Slack integration
+- [ ] Azure OpenAI provider support
+- [ ] DeepSeek provider support
+- [ ] OpenRouter gateway support
 - [ ] Advanced analytics dashboard
 - [ ] Skill marketplace UI
 - [ ] Multi-region deployment support

diff --git a/docs/MULTI-USERS.md b/docs/MULTI-USERS.md
@@ -117,7 +117,8 @@ flowchart LR
 
 - **Web** — the authenticated JWT carries `userId`; the WebSocket gateway verifies the JWT on connect.
 - **Telegram** — each Clawix user can claim one `telegramId`. Messages from an un-claimed Telegram id are rejected.
-- **WhatsApp / Slack** — **[pending]** (adapters not implemented).
+- **WhatsApp** — implemented via `@whiskeysockets/baileys` (Business API).
+- **Slack** — **[pending]** (adapter not implemented).
 
 ---