Package Exports
- codebase-cli
- codebase-cli/dist/cli.js
This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (codebase-cli) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.
Readme
codebase
An AI coding agent for builders.
Lives in your terminal. Reads your project, writes code, runs commands, ships work.
Built on pi — the agent loop, provider adapters, and session protocol that make this whole thing tick. Go give them a star.
Two ways to run it
Bring your own LLM. Drop an API key in your shell and go — Anthropic, OpenAI, Groq, OpenRouter, Mistral, Ollama, any OpenAI-compatible endpoint.
ANTHROPIC_API_KEY=sk-ant-... codebase
# or
OPENAI_API_KEY=sk-... codebaseSign in to codebase.design and skip key wrangling. One auth, every model.
- Free tier — try open-weight models (MiniMax, Qwen, Llama, etc.) with a 10-turn taste so you can kick the tires before paying anyone for anything. No API keys to set up.
- Paid account — uncaps the open-weights, adds the frontier models (Claude Opus / Sonnet, GPT-5, …), higher rate limits, and longer context windows. One subscription replaces N provider bills.
codebase auth login
codebaseSwitch between models any time with /model (interactive picker) or /model <id>.
Install
Requires Node.js ≥ 20.
# one-liner (macOS / Linux)
curl -fsSL https://codebase.design/install.sh | sh
# Windows (PowerShell)
irm https://codebase.design/install.ps1 | iex
# any platform
npm i -g codebase-cliQuick start
cd your-project
codebaseType. Hit enter. The agent reads files, runs tests, edits code, and shows you what it did. Slash /help for the rest.
A few things worth knowing:
/model— pick a model interactively, live list of what your account can hit/plan— Q&A before the agent touches anything!cmd— run a shell command without spending a turn@path— pin a file into the next prompt\<Enter>— multi-line input- Type while the agent is working — your prompt queues, fires when the current turn ends (
Ctrl-Cwhile busy clears the queue along with the turn) - Ctrl-C stops the current turn, twice fast exits
What it does
- Streaming responses. Real-time token output, coalesced to 60 fps so the TUI doesn't thrash.
- Multi-turn agentic loop. Tool call → result → next turn, automatically.
- Parallel tool execution. Read-only tools (grep, glob, read, git status…) run concurrently within a turn.
- Project awareness. Auto-loads
AGENTS.md,CLAUDE.md,CODEX.md, or.cursorrulesfrom the project root into the system prompt. - Conversation compaction. Long sessions automatically summarize older turns to stay under the context window.
- Session persistence. Auto-resume from where you left off;
--newfor a clean slate. - Plan mode. A cheap-model Q&A pass surfaces the right plan before the expensive agent starts editing.
- Intent routing. Chit-chat doesn't burn a full agent turn; complex asks roll into plan mode automatically.
- Subagent dispatch. Spawn isolated research agents that keep their tool noise out of your main context.
Builder-focused defaults
- Any LLM, not just Anthropic. Provider choice is config.
- 45+ tools behind one small interface — adding one is mechanical.
- Effect-based permissions instead of tool-name allowlists.
- Single immutable state driven by a typed reducer — the UI is one render of one value.
- Multi-process safe OAuth with lockfile-coordinated token refresh — run 10 instances of codebase at once and they share a single refresh per hour.
- Plain
npm i -g, no bundler lock-in.
More
.settings/— orientation: tenets, architecture, extending, testingCLAUDE.md— quick reference for AI agents working in this repodocs/MIGRATION_v1_to_v2.md— upgrading from the Go v1 binary/helpinside the CLI — every slash command and shortcut
License
MIT. Built on pi-mono (MIT).