安装
在本地安装 CLI。Codna 可运行于你的本地机器、云端或自托管基础设施。
pip install codna codna --version
快速上手
首先理解代码库，然后让 Codna 修复具体问题。
codna triage . codna fix . --issue "the checkout test is failing"
CLI
核心命令精简且易于脚本化。
codna triage . --json codna fix . --issue "..." --tests codna fix https://github.com/org/repo --issue "..."
MCP 服务器
一行命令将 Codna 添加到 Cursor 或 Claude。你的智能体可向 Codna 查询符号映射、依赖关系、测试影响和聚焦证据包。
codna mcp start --repo .
原生 GitHub App
安装 GitHub App，让 Codna 自动分类问题、评论根因证据，并开启修复 Pull Request。
# App flow Install codna → select repos → enable fix PRs
配置
Bring your own model key, or use Codna's managed model — it's the same Codna either way.
model: provider: openai key: env:CODNA_MODEL_KEY privacy: egress: fail-closed redact_secrets: true
常见问题
Codna 会用我的代码进行训练吗？ 不会。Codna 的设计原则是不对客户代码进行任何训练。
我可以自托管吗？ 可以。自托管永久可用，企业版还提供有支持的本地和气隔部署选项。
Frequently asked
Install with a single command from your terminal. The codna cli runs locally, so you bring your own API key and your code never leaves your machine unless you choose otherwise.
The MCP server for coding integrates natively with Cursor and Claude. Add it to your editor's MCP config and Codna's graph engine becomes available to your AI assistant without any extra steps.
The GitHub App monitors your repository and opens pull requests with verified fixes automatically. Every fix is validated by your own test suite before the PR is created.
No. Codna is self-hostable, and egress is fail-closed by default. You supply your own API key, and the system is designed so your code is never used for model training.
The deterministic graph engine maps the relevant code first, producing an evidence bundle measured at around 600 tokens. Head-to-head against Cursor, Codna used 5× fewer tokens and ran 1.7× faster, every fix test-verified (87/87).
Codna supports 250+ languages, and has mapped 130 repositories in 9.2 seconds for zero LLM tokens. If your project compiles or resolves dependencies, Codna can graph it.