Skip to content
Back to search

cligate

Private AI assistant, AI agent, and unified model proxy for Claude Code, Codex CLI, Gemini CLI & OpenClaw. Skills, MCP, tools, channels, tasks,model routing, accounts, keys, logs, dashboard.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/codeking-ai--cligate/badge.svg)](/listings/codeking-ai--cligate)

HTML

<a href="/listings/codeking-ai--cligate"><img src="/api/listings/codeking-ai--cligate/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Start CliGate

npx cligate@latest start

Or install globally:

npm install -g cligate
cligate start

Or use a desktop release package:

1. Download the installer or app package for your platform from [Releases](https://github.com/codeking-ai/cligate/releases). 2. Install or open the package, then launch `CliGate`. 3. CliGate will start the local service and open the desktop window automatically.

Default dashboard:

`http://localhost:8081`

2. Add at least one working credential

Use the dashboard:

- `Accounts` for ChatGPT / Claude / Antigravity - `API Keys` for provider keys - `Local Models` for on-device runtimes

3. Choose your first path

For Assistant use, open `Chat` or `Assistant Tasks` and tell the private assistant what you want done.

For Model Proxy use, point a CLI tool or API-compatible client to CliGate.

Claude Code:

export ANTHROPIC_BASE_URL=http://localhost:8081
export ANTHROPIC_API_KEY=any-key
claude

Codex CLI:

# ~/.codex/config.toml
chatgpt_base_url = "http://localhost:8081/backend-api/"
openai_base_url = "http://localhost:8081"

Gemini CLI and OpenClaw can also be configured from the dashboard.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 213 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # CliGate
  2. ![CliGate Dashboard](./images/dashboard.png)
  3. [![AGPL-3.0 License](https://img.shields.io/badge/License-AGPL--3.0-blue.svg)](https://www.gnu.org/licenses/agpl-3.0)
  4. [![Node.js Version](https://img.shields.io/badge/Node.js-24%2B-blue.svg)](https://nodejs.org/)
  5. [![npm Version](https://img.shields.io/npm/v/cligate)](https://www.npmjs.com/package/cligate)
  6. [![GitHub stars](https://img.shields.io/github/stars/codeking-ai/cligate?style=social)](https://github.com/codeking-ai/cligate)
  7. **[English](./README.md) | [中文](./README_CN.md)**
  8. CliGate is a local AI control plane built around two core capabilities:
  9. - **Assistant**: a resident private assistant that stays available in the background, understands user tasks, remembers context, uses tools, schedules work, operates channels, and can execute actions through MCP, skills, desktop automation, shell/file tools, or delegated runtimes.
  10. - **Model Proxy**: one local API and model-routing layer for Claude Code, Codex CLI, Gemini CLI, OpenClaw, and API-compatible clients, with unified accounts, API keys, model mapping, logs, usage, and cost visibility.
  11. It keeps both layers local-first on `localhost`: the assistant acts like a personal operator for real tasks, while the proxy owns provider access, routing, credentials, unified model names, and observability.
  12. ## Why CliGate
  13. - One local dashboard for a resident private assistant and unified model routing
  14. - Assistant tasks with memory, approvals, follow-ups, scheduled work, channels, and tool execution
  15. - Account pools, API keys, local runtimes, app routing, and model mapping in one proxy layer
  16. - Channels for Telegram, Feishu, and DingTalk workflows
  17. - Local-first deployment without a hosted relay
  18. ## What It Includes
  19. ### Assistant
  20. - Dashboard chat and Assistant Tasks for personal task execution
  21. - A persistent assistant agent with task records, memory, policies, approvals, and resumable executions
  22. - Tool execution through skills, MCP, shell/file tools, scheduled tasks, channels, and optional desktop automation
  23. - Optional delegation to Codex / Claude Code runtime sessions when a task needs an external coding agent
  24. - Telegram, Feishu, and DingTalk channel workflows
  25. ### Model Proxy
  26. - Anthropic Messages, OpenAI Chat Completions, OpenAI Responses, Codex, and Gemini-compatible endpoints
  27. - One-click configuration for Claude Code, Codex CLI, Gemini CLI, and OpenClaw
  28. - ChatGPT, Claude, and Antigravity account pools
  29. - API key pools for OpenAI, Azure OpenAI, Anthropic, Gemini, Vertex AI, MiniMax, Moonshot, ZhipuAI, DeepSeek, Qwen, and OpenRouter
  30. - Routing priority, app-level bindings, provider model mapping, and free-model routing
  31. - Optional local model routing through Ollama-style runtimes
  32. ### Observability and operations
  33. - Usage and pricing views
  34. - Request logs and live log streaming
  35. - API explorer
  36. - Tool installer and CLI config helpers
  37. - Resources catalog for free/trial model providers
  38. ## Quick Start
  39. ### 1. Start CliGate
  40. ```bash
  41. npx cligate@latest start
  42. ```
  43. Or install globally:
  44. ```bash
  45. npm install -g cligate
  46. cligate start
  47. ```
  48. Or use a desktop release package:
  49. 1. Download the installer or app package for your platform from [Releases](https://github.com/codeking-ai/cligate/releases).
  50. 2. Install or open the package, then launch `CliGate`.
  51. 3. CliGate will start the local service and open the desktop window automatically.
  52. Default dashboard:
  53. `http://localhost:8081`
  54. ### 2. Add at least one working credential
  55. Use the dashboard:
  56. - `Accounts` for ChatGPT / Claude / Antigravity
  57. - `API Keys` for provider keys
  58. - `Local Models` for on-device runtimes
  59. ### 3. Choose your first path
  60. For Assistant use, open `Chat` or `Assistant Tasks` and tell the private assistant what you want done.
  61. For Model Proxy use, point a CLI tool or API-compatible client to CliGate.
  62. Claude Code:
  63. ```bash
  64. export ANTHROPIC_BASE_URL=http://localhost:8081
  65. export ANTHROPIC_API_KEY=any-key
  66. claude
  67. ```
  68. Codex CLI:
  69. ```toml
  70. # ~/.codex/config.toml
  71. chatgpt_base_url = "http://localhost:8081/backend-api/"
  72. openai_base_url = "http://localhost:8081"
  73. ```
  74. Gemini CLI and OpenClaw can also be configured from the dashboard.
  75. ## User Paths
  76. ### Assistant users
  77. Use `Chat`, `Assistant Tasks`, `Conversation Records`, `Scheduled`, `Skills`, `MCP`, and channels to ask the resident assistant to execute real tasks, remember context, use tools, send follow-ups, and keep working in the background.
  78. ### Model Proxy users
  79. Start the service, add one credential, run one-click config, and send your first proxied request from Claude Code, Codex CLI, Gemini CLI, OpenClaw, or an API-compatible client.
  80. ### Dashboard operators
  81. Use the dashboard to manage accounts, API keys, routing priority, model mapping, local runtimes, pricing, request logs, usage, channel settings, skills, MCP, and desktop-agent settings.
  82. ## Documentation
  83. Start here if you want the shortest path to the right document:
  84. - [Documentation Hub](./docs/README.md)
  85. - [Product Manual (English)](./docs/product-manual.en.md)
  86. - [Product Manual (Chinese)](./docs/product-manual.zh-CN.md)
  87. - [Architecture](./docs/ARCHITECTURE.md)
  88. - [API Reference](./docs/API.md)
  89. - [App Routing](./docs/APP_ROUTING.md)
  90. - [Accounts](./docs/ACCOUNTS.md)
  91. - [OpenClaw Integration](./docs/OPENCLAW.md)
  92. - [Screenshot Guide](./docs/SCREENSHOTS.md)
  93. - [Release Guide](./docs/RELEASING.md)
  94. - [Community](./docs/COMMUNITY.md)
  95. - [Contributing](./CONTRIBUTING.md)
  96. - [Security](./SECURITY.md)
  97. - [Support](./SUPPORT.md)
  98. - [Changelog](./CHANGELOG.md)
  99. After the server starts, a lightweight product guide is also available at:
  100. - `http://localhost:8081/manual/`
  101. - `http://localhost:8081/resources/`
  102. ## Local Architecture
  103. ```text
  104. Assistant Surfaces
  105. Web Chat / Assistant Tasks / Telegram / Feishu / DingTalk / Scheduled Tasks
  106. |
  107. v
  108. Private Assistant and Tools
  109. Memory / Policies / Skills / MCP / Desktop Agent / Shell + File Tools / Optional Codex + Claude Code Delegation
  110. |
  111. v
  112. CliGate Local Control Plane (localhost:8081)
  113. |
  114. +--> Model Proxy
  115. | - Protocol translation
  116. | - Account and API key routing
  117. | - App-level bindings and model mapping
  118. | - Local model routing
  119. |
  120. v
  121. Upstream Providers and Local Runtimes
  122. OpenAI / Anthropic / Gemini / Vertex AI / Kilo / Ollama / others
  123. ```
  124. ## API Surface
  125. | Endpoint | Use |
  126. |:--|:--|
  127. | `POST /v1/messages` | Anthropic Messages proxy |
  128. | `POST /v1/chat/completions` | OpenAI Chat Completions proxy |
  129. | `POST /v1/responses` | OpenAI Responses proxy |
  130. | `POST /backend-api/codex/responses` | Codex internal compatibility |
  131. | `POST /v1beta/models/*` | Gemini CLI proxy |
  132. | `GET /api/agent-runtimes/providers` | Runtime provider catalog |
  133. | `GET /api/agent-channels/conversations` | Channel conversation records |
  134. | `GET /api/assistant/tasks` | Assistant task records |
  135. | `GET /api/assistant/mcp/servers` | MCP server management |
  136. | `GET /api/assistant/skills` | Assistant skill management |
  137. | `GET /api/desktop-agent/status` | Desktop-agent status |
  138. | `GET /api/local-runtimes` | Local runtime status |
  139. | `GET /api/resources` | Resource catalog |
  140. | `GET /health` | Health and version |
  141. See [docs/API.md](./docs/API.md) for more detail.
  142. ## Community
  143. - [GitHub Discussions](https://github.com/codeking-ai/cligate/discussions)
  144. - [Issues](https://github.com/codeking-ai/cligate/issues)
  145. - [Discord](https://discord.gg/GgxZSehxqG)
  146. - [X](https://x.com/GengSteven58767)
  147. - [Community Guide](./docs/COMMUNITY.md)
  148. - [Releases](https://github.com/codeking-ai/cligate/releases)
  149. If you plan to contribute, read [CONTRIBUTING.md](./CONTRIBUTING.md) before opening a pull request.
  150. ## License
  151. This project is licensed under [AGPL-3.0](https://www.gnu.org/licenses/agpl-3.0).
  152. ## Disclaimer
  153. CliGate is an independent open-source project and is not affiliated with Anthropic, OpenAI, Google, or other upstream providers.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.