Imanol Maiztegui
ecc2f7af19
Replace raw `Effect.promise` calls across HTTP API handlers with `EffectBridge.fromPromise` / `EffectBridge.make` to ensure proper error propagation and context forwarding when bridging imperative async code into the Effect runtime. Wrap top-level `makeRuntime` calls in `plan-followup.ts` with `lazy()` to defer service instantiation until first access, avoiding eager initialization side-effects during module loading. Also reorder SDK event union members and type definitions to reflect updated OpenAPI schema generation output.
Kilo Code CLI
The AI coding agent built for the terminal. Generate code from natural language, automate tasks, and run terminal commands -- powered by 500+ AI models.
Install
npm install -g @kilocode/cli
Or run directly with npx:
npx --package @kilocode/cli kilo
Getting Started
Run kilo in any project directory to launch the interactive TUI:
kilo
Run a one-off task:
kilo run "add input validation to the signup form"
Features
- Code generation -- describe what you want in natural language
- Terminal commands -- the agent can run shell commands on your behalf
- 500+ AI models -- use models from OpenAI, Anthropic, Google, and more
- MCP servers -- extend agent capabilities with the Model Context Protocol
- Multiple modes -- Plan with Architect, code with Coder, debug with Debugger, or create your own
- Sessions -- resume previous conversations and export transcripts
- API keys optional -- bring your own keys or use Kilo credits
Commands
| Command | Description |
|---|---|
kilo |
Launch interactive TUI |
kilo run "<task>" |
Run a one-off task |
kilo auth |
Manage authentication |
kilo models |
List available models |
kilo mcp |
Manage MCP servers |
kilo session list |
List sessions |
kilo session delete |
Delete a session |
kilo export |
Export session transcripts |
Run kilo --help for the full list.
Alternative Installation
Homebrew (macOS/Linux)
brew install Kilo-Org/tap/kilo
GitHub Releases
Download pre-built binaries from the Releases page.
Documentation
Links
License
MIT