Pi is a minimal terminal coding harness. Adapt pi to your workflows, not the other way around, without having to fork and modify pi internals. Extend it with TypeScript [Extensions](#extensions), [Skills](#skills), [Prompt Templates](#prompt-templates), and [Themes](#themes). Put your extensions, skills, prompt templates, and themes in [Pi Packages](#pi-packages) and share them with others via npm or git. Pi ships with powerful defaults but skips features like sub agents and plan mode. Instead, you can ask pi to build what you want or install a third party pi package that matches your workflow. Pi runs in four modes: interactive, print or JSON, RPC for process integration, and an SDK for embedding in your own apps. See [clawdbot/clawdbot](https://github.com/clawdbot/clawdbot) for a real-world SDK integration. ## Table of Contents - [Quick Start](#quick-start) - [Providers & Models](#providers--models) - [Interactive Mode](#interactive-mode) - [Sessions](#sessions) - [Configuration](#configuration) - [Customization](#customization) - [CLI Reference](#cli-reference) - [Programmatic Usage](#programmatic-usage) - [Philosophy](#philosophy) --- ## Quick Start ```bash npm install -g @mariozechner/pi-coding-agent ``` Authenticate with an API key: ```bash export ANTHROPIC_API_KEY=sk-ant-... pi ``` Or use your existing subscription: ```bash pi /login # Then select provider ``` Then just talk to pi. By default, pi gives the model four tools: `read`, `write`, `edit`, and `bash`. The model uses these to fulfill your requests. Add capabilities via [skills](#skills), [prompt templates](#prompt-templates), [extensions](#extensions), or [pi packages](#pi-packages). **Platform notes:** [Windows](docs/windows.md) | [Terminal setup](docs/terminal-setup.md) | [Shell aliases](docs/shell-aliases.md) --- ## Providers & Models For each built-in provider, pi maintains a list of tool-capable models, updated with every release. Authenticate via subscription (`/login`) or API key, then select any model from that provider via `/model` (or Ctrl+L). **Subscriptions:** - Anthropic Claude Pro/Max - OpenAI ChatGPT Plus/Pro (Codex) - GitHub Copilot - Google Gemini CLI - Google Antigravity **API keys:** - Anthropic - OpenAI - Azure OpenAI - Google Gemini - Google Vertex - Amazon Bedrock - Mistral - Groq - Cerebras - xAI - OpenRouter - Vercel AI Gateway - ZAI - OpenCode Zen - MiniMax See [docs/providers.md](docs/providers.md) for detailed setup instructions. **Custom providers & models:** Add providers via `~/.pi/agent/models.json` if they speak a supported API (OpenAI, Anthropic, Google). For custom APIs or OAuth, use extensions. See [docs/models.md](docs/models.md) and [docs/custom-provider.md](docs/custom-provider.md). --- ## Interactive Mode The interface from top to bottom: - **Startup header** - Shows shortcuts (`/hotkeys` for all), loaded AGENTS.md files, prompt templates, skills, and extensions - **Messages** - Your messages, assistant responses, tool calls and results, notifications, errors, and extension UI - **Editor** - Where you type; border color indicates thinking level - **Footer** - Working directory, session name, total token/cache usage, cost, context usage, current model The editor can be temporarily replaced by other UI, like built-in `/settings` or custom UI from extensions (e.g., a Q&A tool that lets the user answer model questions in a structured format). [Extensions](#extensions) can also replace the editor, add widgets above/below it, a status line, custom footer, or overlays. ### Editor | Feature | How | |---------|-----| | File reference | Type `@` to fuzzy-search project files | | Path completion | Tab to complete paths | | Multi-line | Shift+Enter (or Ctrl+Enter on Windows Terminal) | | Images | Ctrl+V to paste, or drag onto terminal | | Bash commands | `!command` runs and sends output to LLM, `!!command` runs without sending | Standard editing keybindings for delete word, undo, etc. See [docs/keybindings.md](docs/keybindings.md). ### Commands Type `/` in the editor to trigger commands. [Extensions](#extensions) can register custom commands, [skills](#skills) are available as `/skill:name`, and [prompt templates](#prompt-templates) expand via `/templatename`. | Command | Description | |---------|-------------| | `/login`, `/logout` | OAuth authentication | | `/model` | Switch models | | `/scoped-models` | Enable/disable models for Ctrl+P cycling | | `/settings` | Thinking level, theme, message delivery | | `/resume` | Pick from previous sessions | | `/new` | Start a new session | | `/name ` | Set session display name | | `/session` | Show session info (path, tokens, cost) | | `/tree` | Jump to any point in the session and continue from there | | `/fork` | Create a new session from the current branch | | `/compact [prompt]` | Manually compact context, optional custom instructions | | `/copy` | Copy last assistant message to clipboard | | `/export [file]` | Export session to HTML file | | `/share` | Upload as private GitHub gist with shareable HTML link | | `/reload` | Reload extensions, skills, prompts, themes | | `/hotkeys` | Show all keyboard shortcuts | | `/changelog` | Display version history | | `/quit`, `/exit` | Quit pi | ### Keyboard Shortcuts See `/hotkeys` for the full list. Customize via `~/.pi/agent/keybindings.json`. See [docs/keybindings.md](docs/keybindings.md). **Commonly used:** | Key | Action | |-----|--------| | Ctrl+C | Clear editor | | Ctrl+C twice | Quit | | Escape | Cancel/abort | | Escape twice | Open `/tree` | | Ctrl+L | Open model selector | | Ctrl+P / Shift+Ctrl+P | Cycle scoped models forward/backward | | Shift+Tab | Cycle thinking level | | Ctrl+O | Collapse/expand tool output | | Ctrl+T | Collapse/expand thinking blocks | --- ## Sessions Sessions are stored as JSONL files with a tree structure. Each entry has an `id` and `parentId`, enabling in-place branching without creating new files. ### Management Sessions auto-save to `~/.pi/agent/sessions/` organized by working directory. ```bash pi -c # Continue most recent session pi -r # Browse and select from past sessions pi --no-session # Ephemeral mode (don't save) pi --session # Use specific session file or ID ``` ### Branching **`/tree`** - Navigate the session tree in-place. Select any previous point, continue from there, and switch between branches. All history preserved in a single file. - Search by typing, page with ←/→ - Filter modes (Ctrl+O): default → no-tools → user-only → labeled-only → all - Press `l` to label entries as bookmarks **`/fork`** - Create a new session file from the current branch. Opens a selector, copies history up to the selected point, and places that message in the editor for modification. ### Compaction Long sessions can exhaust context windows. Compaction summarizes older messages while keeping recent ones. **Manual:** `/compact` or `/compact ` **Automatic:** Enabled by default. Triggers on context overflow (recovers and retries) or when approaching the limit (proactive). Configure via `/settings` or `settings.json`. Compaction is lossy. The full history remains in the JSONL file; use `/tree` to revisit. Customize compaction behavior via [extensions](#extensions). See [docs/session.md](docs/session.md) for file format and [docs/compaction.md](docs/compaction.md) for internals. --- ## Configuration ### Context Files Pi loads `AGENTS.md` files at startup (global `~/.pi/agent/AGENTS.md`, parent directories, current directory). Use for project instructions, conventions, common commands. ### System Prompt Replace the default system prompt with `.pi/SYSTEM.md` (project) or `~/.pi/agent/SYSTEM.md` (global). Append without replacing via `APPEND_SYSTEM.md`. ### Custom Models Add Ollama, vLLM, LM Studio, or proxy endpoints via `~/.pi/agent/models.json`: ```json { "providers": { "ollama": { "baseUrl": "http://localhost:11434/v1", "api": "openai-completions", "models": [{ "id": "llama-3.1-8b", "name": "Llama 3.1 8B", ... }] } } } ``` See [docs/models.md](docs/models.md) for full schema and examples. ### Settings Global settings in `~/.pi/agent/settings.json`, project overrides in `.pi/settings.json`. See [docs/settings.md](docs/settings.md) for all options. --- ## Customization ### Themes Built-in: `dark`, `light`. Create custom themes in `~/.pi/agent/themes/*.json` with live reload. See [docs/themes.md](docs/themes.md). ### Prompt Templates Reusable prompts as Markdown files in `~/.pi/agent/prompts/` or `.pi/prompts/`. Type `/name` to expand. See [docs/prompt-templates.md](docs/prompt-templates.md). ### Skills On-demand capability packages following the [Agent Skills standard](https://agentskills.io). Place in `~/.pi/agent/skills/` or `.pi/skills/`. Invoke via `/skill:name` or let the agent load them automatically. See [docs/skills.md](docs/skills.md). ### Extensions TypeScript modules for custom tools, commands, event interception, and UI. ```typescript export default function (pi: ExtensionAPI) { pi.registerTool({ name: "deploy", ... }); pi.registerCommand("stats", { ... }); pi.on("tool_call", async (event, ctx) => { ... }); } ``` Place in `~/.pi/agent/extensions/` or `.pi/extensions/`. See [docs/extensions.md](docs/extensions.md) and [examples/extensions/](examples/extensions/). ### Pi Packages Bundle and share extensions, skills, prompts, and themes via npm or git: ```bash pi install npm:@foo/pi-tools pi install git:github.com/user/repo pi list pi update ``` See [docs/packages.md](docs/packages.md). --- ## CLI Reference ```bash pi [options] [@files...] [messages...] ``` ### Modes | Flag | Description | |------|-------------| | (default) | Interactive mode | | `-p`, `--print` | Print response and exit | | `--mode json` | JSON event stream | | `--mode rpc` | RPC mode for process integration | ### Common Options | Option | Description | |--------|-------------| | `--provider`, `--model` | Select provider and model | | `--thinking ` | `off`, `minimal`, `low`, `medium`, `high` | | `--models ` | Patterns for Ctrl+P cycling | | `-c`, `--continue` | Continue most recent session | | `-r`, `--resume` | Browse and select session | | `--tools ` | Limit tools (default: `read,bash,edit,write`) | ### File Arguments ```bash pi @prompt.md "Answer this" pi @screenshot.png "What's in this image?" ``` See `pi --help` for all options. --- ## Programmatic Usage ### SDK ```typescript import { AuthStorage, createAgentSession, ModelRegistry, SessionManager } from "@mariozechner/pi-coding-agent"; const { session } = await createAgentSession({ sessionManager: SessionManager.inMemory(), authStorage: new AuthStorage(), modelRegistry: new ModelRegistry(authStorage), }); await session.prompt("What files are in the current directory?"); ``` See [docs/sdk.md](docs/sdk.md) and [examples/sdk/](examples/sdk/). ### RPC Mode ```bash pi --mode rpc --no-session ``` See [docs/rpc.md](docs/rpc.md) for the protocol. ### HTML Export ```bash pi --export session.jsonl output.html ``` --- ## Philosophy **No MCP.** Build CLI tools with READMEs (see [Skills](#skills)). [Why?](https://mariozechner.at/posts/2025-11-02-what-if-you-dont-need-mcp/) **No sub-agents.** Spawn pi instances via tmux, or build your own with [Extensions](#extensions). **No permission popups.** Run in a container or build your own confirmation flow. **No plan mode.** Write plans to files, start fresh for implementation. Read the [blog post](https://mariozechner.at/posts/2025-11-30-pi-coding-agent/) for the full rationale. --- ## Development See [docs/development.md](docs/development.md) for forking, rebranding, and debugging. --- ## License MIT ## See Also - [@mariozechner/pi-ai](https://www.npmjs.com/package/@mariozechner/pi-ai): Core LLM toolkit - [@mariozechner/pi-agent](https://www.npmjs.com/package/@mariozechner/pi-agent): Agent framework - [@mariozechner/pi-tui](https://www.npmjs.com/package/@mariozechner/pi-tui): Terminal UI components