ninan-nn
1d3a412c4d
* docs: comprehensive docs site refactoring - Replace 856-line manifest auto-generation with direct VitePress docs - Restructure from flat 4-section layout to 10-section information architecture (Getting Started, Architecture, Guides, SDKs, Components, Kubernetes, API, CLI, Examples, Community) - Establish single source of truth: docs/ owns user-facing content, READMEs are slim pointers - Remove incomplete Chinese i18n (30-40% coverage), keep English only - Add VitePress features: custom containers, code groups, edit links, footer, dark mode - Simplify build: just `vitepress build`, no docs:sync or docs:spec preprocessing - Add documentation rules to AGENTS.md and CLAUDE.md Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: simplify CLAUDE.md to point at AGENTS.md Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: resolve 38 broken links, stale paths, and content issues across docs - Fix 16 broken inbound links to moved docs pages (README, CONTRIBUTING, SECURITY, ROADMAP, GOVERNANCE, server/configuration, kubernetes/) - Move sandbox.kill() inside async-with block in quick start and README - Update execd paths from /opt/opensandbox/bin/ to /opt/opensandbox/ - Fix wrong batchsandbox-template GitHub raw URL - Remove references to deleted RELEASE_NOTE_TEMPLATE and removed scripts - Add missing cd context to server, egress, and MCP command snippets - Add missing OSEP-0012 (multi-tenancy) and OSEP-0013 to index - Fix timeout described as mandatory (it is optional) - Replace duplicated contributing/code-of-conduct with GitHub pointers - Fix broken Chinese doc references in SDK README_zh files - Remove dead Chinese docs link from README Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: align README links with versioned docs * docs: address remaining review comments * docs: clarify README ownership for components * docs: fix remaining navigation and example comments * docs: refine documentation ownership rules * docs: remove obsolete spec doc generator --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2.2 KiB
2.2 KiB
title, description
| title | description |
|---|---|
| Kimi CLI | Run Kimi Code CLI (Moonshot AI) inside an OpenSandbox container. |
Kimi CLI Example
Run Kimi Code CLI (Moonshot AI) inside an OpenSandbox container.
Start OpenSandbox server [local]
Pre-pull the code-interpreter image (includes Python 3.12+):
docker pull sandbox-registry.cn-zhangjiakou.cr.aliyuncs.com/opensandbox/code-interpreter:v1.1.0
# use docker hub
# docker pull opensandbox/code-interpreter:v1.1.0
Then start the local OpenSandbox server, stdout logs will be visible in the terminal:
uv pip install opensandbox-server
opensandbox-server init-config ~/.sandbox.toml --example docker
opensandbox-server
Create and Access the Kimi Sandbox
# Install OpenSandbox package
uv pip install opensandbox
# Run the example (requires SANDBOX_DOMAIN / SANDBOX_API_KEY / KIMI_API_KEY)
uv run python examples/kimi-cli/main.py
The script installs Kimi Code CLI (pip install kimi-cli) at runtime (Python 3.12+ is already in the code-interpreter image), then sends a simple request kimi -p "Compute 1+1=?.". Auth is passed via KIMI_API_KEY, and you can override endpoint/model with KIMI_BASE_URL / KIMI_MODEL_NAME.
Environment Variables
| Variable | Default | Description |
|---|---|---|
SANDBOX_DOMAIN |
localhost:8080 |
Sandbox service address |
SANDBOX_API_KEY |
(optional for local) | API key if your server requires authentication |
SANDBOX_IMAGE |
sandbox-registry.cn-zhangjiakou.cr.aliyuncs.com/opensandbox/code-interpreter:v1.1.0 |
Sandbox image to use |
KIMI_API_KEY |
(required) | Your Moonshot AI / Kimi API key |
KIMI_BASE_URL |
(optional) | Kimi API endpoint (defaults to Kimi's official endpoint) |
KIMI_MODEL_NAME |
kimi-k2.5 |
Model to use |
References
- Kimi Code CLI - Official Kimi Code CLI repository
- Moonshot AI Platform - API key management and documentation
- Kimi CLI Documentation - Full CLI documentation
- Source code on GitHub