Senpi is a minimal terminal coding harness. Adapt senpi to your workflows, not the other way around, without having to fork and modify core internals. Extend it with TypeScript Extensions, Skills, Prompt Templates, and Themes. Put your extensions, skills, prompt templates, and themes in Senpi Packages and share them with others via npm or git.

Senpi ships with powerful defaults but skips features like sub agents and plan mode. Instead, you can ask senpi to build what you want or install a third party package that matches your workflow.

Senpi runs in four modes: interactive, print or JSON, RPC for process integration, and an SDK for embedding in your own apps. See openclaw/openclaw for a real-world SDK integration.

Share your OSS coding agent sessions

If you use pi for open source work, please share your coding agent sessions.

Public OSS session data helps improve models, prompts, tools, and evaluations using real development workflows.

For the full explanation, see this post on X.

To publish sessions, use badlogic/pi-share-hf. Read its README.md for setup instructions. All you need is a Hugging Face account, the Hugging Face CLI, and pi-share-hf.

You can also watch this video, where I show how I publish my pi-mono sessions.

I regularly publish my own pi-mono work sessions here:

• badlogicgames/pi-mono on Hugging Face

Table of Contents

• Quick Start
• Providers & Models
• Interactive Mode
  • Editor
  • Commands
  • Keyboard Shortcuts
  • Message Queue
• Sessions
  • Branching
  • Compaction
• Settings
• Context Files
• Customization
  • Prompt Templates
  • Skills
  • Extensions
  • Themes
• Senpi Packages
• Programmatic Usage
• Philosophy
• CLI Reference

Quick Start

npm install -g @code-yeongyu/senpi

@code-yeongyu/senpi is the npm package name. The installed executable is still senpi.

Authenticate with an API key:

export ANTHROPIC_API_KEY=sk-ant-...
senpi

Or use your existing subscription:

senpi
/login  # Then select provider

Then just talk to senpi. By default, senpi gives the model four tools: read, write, edit, and bash. The model uses these to fulfill your requests. Add capabilities via skills, prompt templates, extensions, or senpi packages.

Platform notes: Windows | Termux (Android) | tmux | Terminal setup | Shell aliases

Providers & Models

For each built-in provider, senpi 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

API keys:

• Anthropic
• OpenAI
• Azure OpenAI
• DeepSeek
• Google Gemini
• Google Vertex
• Amazon Bedrock
• Mistral
• Groq
• Cerebras
• Cloudflare AI Gateway
• Cloudflare Workers AI
• xAI
• OpenRouter
• Vercel AI Gateway
• ZAI
• OpenCode Zen
• OpenCode Go
• Hugging Face
• Fireworks
• Together AI
• Kimi For Coding
• MiniMax
• Xiaomi MiMo
• Xiaomi MiMo Token Plan (China)
• Xiaomi MiMo Token Plan (Amsterdam)
• Xiaomi MiMo Token Plan (Singapore)

See docs/providers.md for detailed setup instructions.

Custom providers & models: Add providers via ~/.senpi/agent/models.json if they speak a supported API (OpenAI, Anthropic, Google). For custom APIs or OAuth, use extensions. See docs/models.md and 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 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 (Alt+V on Windows), 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.

Commands

Type / in the editor to trigger commands. Extensions can register custom commands, skills are available as /skill:name, and prompt templates expand via /templatename.

| Command | Description | |---------|-------------| | /login, /logout | OAuth authentication | | /model | Switch models | | /favorite-models | Manage favorite models for Ctrl+P cycling | | /settings | Thinking level, theme, message delivery, transport | | /resume | Pick from previous sessions | | /new | Start a new session | | /name <name> | Set session display name | | /session | Show session info (file, ID, messages, tokens, cost) | | /tree | Jump to any point in the session and continue from there | | /fork | Create a new session from a previous user message | | /clone | Duplicate the current active branch into a new session | | /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 keybindings, extensions, skills, prompts, and context files (themes hot-reload automatically) | | /hotkeys | Show all keyboard shortcuts | | /changelog | Display version history | | /quit | Quit senpi |

Keyboard Shortcuts

See /hotkeys for the full list. Customize via ~/.senpi/agent/keybindings.json. See 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 favorite models forward/backward | | Shift+Tab | Cycle thinking level | | Ctrl+O | Collapse/expand tool output | | Ctrl+T | Collapse/expand thinking blocks |

Message Queue

Submit messages while the agent is working:

• Enter queues a steering message, delivered after the current assistant turn finishes executing its tool calls
• Alt+Enter queues a follow-up message, delivered only after the agent finishes all work
• Escape aborts and restores queued messages to editor
• Alt+Up retrieves queued messages back to editor

On Windows Terminal, Alt+Enter is fullscreen by default. Remap it in docs/terminal-setup.md so senpi can receive the follow-up shortcut.

Configure delivery in settings: steeringMode and followUpMode can be "one-at-a-time" (default, waits for response) or "all" (delivers all queued at once). transport selects provider transport preference ("sse", "websocket", or "auto") for providers that support multiple transports.

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. See docs/session-format.md for file format.

Management

Sessions auto-save to ~/.senpi/agent/sessions/ organized by working directory.

senpi -c                  # Continue most recent session
senpi -r                  # Browse and select from past sessions
senpi --no-session        # Ephemeral mode (don't save)
senpi --session <path|id> # Use specific session file or ID
senpi --fork <path|id>    # Fork specific session file or ID into a new session

Use /session in interactive mode to see the current session ID before reusing it with --session <id> or --fork <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, fold/unfold and jump between branches with Ctrl+←/Ctrl+→ or Alt+←/Alt+→, page with ←/→
• Filter modes (Ctrl+O): default → no-tools → user-only → labeled-only → all
• Press Shift+L to label entries as bookmarks and Shift+T to toggle label timestamps

/fork - Create a new session file from a previous user message on the active branch. Opens a selector, copies the active path up to that point, and places the selected prompt in the editor for modification.

/clone - Duplicate the current active branch into a new session file at the current position. The new session keeps the full active-path history and opens with an empty editor.

--fork <path|id> - Fork an existing session file or partial session UUID directly from the CLI. This copies the full source session into a new session file in the current project.

Compaction

Long sessions can exhaust context windows. Compaction summarizes older messages while keeping recent ones.

Manual: /compact or /compact <custom instructions>

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. See docs/compaction.md for internals.

Settings

Use /settings to modify common options, or edit JSON files directly:

| Location | Scope | |----------|-------| | ~/.senpi/agent/settings.json | Global (all projects) | | .senpi/settings.json | Project (overrides global) |

See docs/settings.md for all options.

Telemetry and update checks

Pi has two separate startup features:

• Update check: fetches https://pi.dev/api/latest-version to check whether a newer Pi version exists. Disable it with PI_SKIP_VERSION_CHECK=1. Disabling update checks only turns off this check.
• Install/update telemetry: after first install or a changelog-detected update, sends an anonymous version ping to https://pi.dev/api/report-install. Opt out by setting enableInstallTelemetry to false in settings.json, or by setting PI_TELEMETRY=0. This does not disable update checks; Pi may still contact pi.dev for the latest version unless update checks are disabled or offline mode is enabled.

Use --offline or PI_OFFLINE=1 to disable all startup network operations described here, including update checks, package update checks, and install/update telemetry.

Context Files

Senpi loads AGENTS.md (or CLAUDE.md) at startup from:

• ~/.senpi/agent/AGENTS.md (global)
• Parent directories (walking up from cwd)
• Current directory

Use for project instructions, conventions, common commands. All matching files are concatenated.

Disable context file loading with --no-context-files (or -nc).

System Prompt

Replace the default system prompt with .senpi/SYSTEM.md (project) or ~/.senpi/agent/SYSTEM.md (global). Append without replacing via APPEND_SYSTEM.md.

Customization

Prompt Templates

Reusable prompts as Markdown files. Type /name to expand.

<!-- ~/.senpi/agent/prompts/review.md -->
Review this code for bugs, security issues, and performance problems.
Focus on: {{focus}}

Place in ~/.senpi/agent/prompts/, .senpi/prompts/, or a senpi package to share with others. See docs/prompt-templates.md.

Skills

On-demand capability packages following the Agent Skills standard. Invoke via /skill:name or let the agent load them automatically.

<!-- ~/.senpi/agent/skills/my-skill/SKILL.md -->
# My Skill
Use this skill when the user asks about X.

## Steps
1. Do this
2. Then that

Place in ~/.senpi/agent/skills/, ~/.agents/skills/, .senpi/skills/, or .agents/skills/ (from cwd up through parent directories) or a senpi package to share with others. See docs/skills.md.

Extensions

TypeScript modules that extend senpi with custom tools, commands, keyboard shortcuts, event handlers, and UI components.

export default function (pi: ExtensionAPI) {
  pi.registerTool({ name: "deploy", ... });
  pi.registerCommand("stats", { ... });
  pi.on("tool_call", async (event, ctx) => { ... });
}

The default export can also be async. pi waits for async extension factories before startup continues, which is useful for one-time initialization such as fetching remote model lists before calling pi.registerProvider().

What's possible:

• Custom tools (or replace built-in tools entirely)
• Plan mode
• Custom compaction and summarization
• Permission gates and path protection
• Custom editors and UI components
• Status lines, headers, footers
• Git checkpointing and auto-commit
• SSH and sandbox execution
• MCP server integration
• Make senpi look like Claude Code
• Games while waiting (yes, Doom runs)
• ...anything you can dream up

Place in ~/.senpi/agent/extensions/, .senpi/extensions/, or a senpi package to share with others. See docs/extensions.md and examples/extensions/.

Builtin extensions ship inside senpi and load before user extensions. Configure them in settings.json with enabledBuiltinExtensions to allow only specific builtin ids, or disabledBuiltinExtensions to skip ids while keeping the default set. The openai-api-parallel-tool-calls, bash-timeout, webfetch, and gpt-apply-patch builtin snapshots are refreshed from the sibling pi-extensions checkout at build time when available, and their source versions are recorded in src/core/extensions/builtin/external-versions.json.

Themes

Built-in: dark, light. Themes hot-reload: modify the active theme file and senpi immediately applies changes.

Place in ~/.senpi/agent/themes/, .senpi/themes/, or a senpi package to share with others. See docs/themes.md.

Senpi Packages

Bundle and share extensions, skills, prompts, and themes via npm or git. Find packages on npmjs.com or Discord.

Security: Senpi packages run with full system access. Extensions execute arbitrary code, and skills can instruct the model to perform any action including running executables. Review source code before installing third-party packages.

senpi install npm:@foo/senpi-tools
senpi install npm:@foo/[email protected]      # pinned version
senpi install git:github.com/user/repo
senpi install git:github.com/user/repo@v1  # tag or commit
senpi install git:[email protected]:user/repo
senpi install git:[email protected]:user/repo@v1  # tag or commit
senpi install https://github.com/user/repo
senpi install https://github.com/user/repo@v1      # tag or commit
senpi install ssh://[email protected]/user/repo
senpi install ssh://[email protected]/user/repo@v1    # tag or commit
senpi remove npm:@foo/senpi-tools
senpi uninstall npm:@foo/senpi-tools          # alias for remove
senpi list
senpi update                                  # update senpi and packages (skips pinned packages)
senpi update --extensions                     # update packages only
senpi update --self                           # update senpi only
senpi update --self --force                   # reinstall senpi even if current
senpi update npm:@foo/senpi-tools             # update one package
senpi config                                  # enable/disable extensions, skills, prompts, themes

Packages install to ~/.senpi/agent/git/ (git) or global npm. Use -l for project-local installs (.senpi/git/, .senpi/npm/). Git @ref values are pinned tags or commits; pinned packages are skipped by senpi update, so use senpi install git:host/user/repo@new-ref to move an existing package to a new ref. Git packages install dependencies with npm install --omit=dev by default, so runtime deps must be listed under dependencies; when npmCommand is configured, git packages use plain install for compatibility with wrappers. If you use a Node version manager and want package installs to reuse a stable npm context, set npmCommand in settings.json, for example ["mise", "exec", "node@20", "--", "npm"].

Create a package by adding a pi key to package.json:

{
  "name": "my-pi-package",
  "keywords": ["pi-package"],
  "pi": {
    "extensions": ["./extensions"],
    "skills": ["./skills"],
    "prompts": ["./prompts"],
    "themes": ["./themes"]
  }
}

Without a pi manifest, senpi auto-discovers from conventional directories (extensions/, skills/, prompts/, themes/).

See docs/packages.md.

Programmatic Usage

SDK

import { AuthStorage, createAgentSession, ModelRegistry, SessionManager } from "@code-yeongyu/senpi";

const authStorage = AuthStorage.create();
const modelRegistry = ModelRegistry.create(authStorage);
const { session } = await createAgentSession({
  sessionManager: SessionManager.inMemory(),
  authStorage,
  modelRegistry,
});

await session.prompt("What files are in the current directory?");

The package name is scoped, but runtime branding, config paths, and the CLI command stay senpi.

For advanced multi-session runtime replacement, use createAgentSessionRuntime() and AgentSessionRuntime.

See docs/sdk.md and examples/sdk/.

RPC Mode

For non-Node.js integrations, use RPC mode over stdin/stdout:

senpi --mode rpc

RPC mode uses strict LF-delimited JSONL framing. Clients must split records on \n only. Do not use generic line readers like Node readline, which also split on Unicode separators inside JSON payloads.

See docs/rpc.md for the protocol.

Philosophy

Senpi inherits upstream pi's extension-first design — the core stays minimal, every feature is reachable through the extension API. The senpi fork's bet is that a small, opinionated set of features is so commonly wanted that shipping them as builtin extensions (loaded by default, disable per-id via disabledBuiltinExtensions) beats forcing every user to bolt them on. Anything you do not want is still one settings flag away from being off.

Upstream pi-mono explicitly omits these features. Senpi ships them as builtins (see the root README for the full list):

• Permission popups — full opencode-style permission flow via permission-system. Opt-in per tool/rule; non-interactive modes auto-deny unknown calls.
• Built-in to-dos — todowrite / todoread tools with branch-aware persistence and a continuation loop. Required by senpi's dynamic prompt; remove the builtin id to opt out.
• Dynamic system prompt — intent gate + tool categorization + policy enforcement via dynamic-prompt/. Replaces upstream's static prompt.
• Per-model prompt presets — gpt-5.x, claude-opus-4-{5,6,7}, kimi-k2-6 via prompt-preset.
• GPT apply_patch tool — Codex-style freeform grammar via gpt-apply-patch, activated only for GPT models.
• Compaction pipeline — speculative + restoration + degradation monitoring via compaction.

Senpi still keeps the things upstream does drop:

No MCP — build CLI tools with READMEs (see Skills) or add MCP via an extension. Why? No plan mode — write plans to files, or build it via an extension. No background bash — use tmux for full observability and direct interaction.

Read upstream's blog post for the original rationale that senpi forks from.

CLI Reference

senpi [options] [@files...] [messages...]

Package Commands

senpi install <source> [-l]      # Install package, -l for project-local
senpi remove <source> [-l]       # Remove package
senpi uninstall <source> [-l]    # Alias for remove
senpi update [source|self|senpi] # Update senpi and packages (skips pinned packages)
senpi update --extensions        # Update packages only
senpi update --self              # Update senpi only
senpi update --self --force      # Reinstall senpi even if current
senpi update --extension <src>   # Update one package
senpi list                       # List installed packages
senpi config                     # Enable/disable package resources

Modes

| Flag | Description | |------|-------------| | (default) | Interactive mode | | -p, --print | Print response and exit | | --mode json | Output all events as JSON lines (see docs/json.md) | | --mode rpc | RPC mode for process integration (see docs/rpc.md) | | --export <in> [out] | Export session to HTML |

In print mode, senpi also reads piped stdin and merges it into the initial prompt:

cat README.md | senpi -p "Summarize this text"

Model Options

| Option | Description | |--------|-------------| | --provider <name> | Provider (anthropic, openai, google, etc.) | | --model <pattern> | Model pattern or ID (supports provider/id and optional :<thinking>) | | --api-key <key> | API key (overrides env vars) | | --thinking <level> | off, minimal, low, medium, high, xhigh, max | | --models <patterns> | Comma-separated patterns that narrow the global model catalog | | --list-models [search] | List available models |

Session Options

| Option | Description | |--------|-------------| | -c, --continue | Continue most recent session | | -r, --resume | Browse and select session | | --session <path\|id> | Use specific session file or partial UUID | | --fork <path\|id> | Fork specific session file or partial UUID into a new session | | --session-dir <dir> | Custom session storage directory | | --no-session | Ephemeral mode (don't save) |

Tool Options

| Option | Description | |--------|-------------| | --tools <list>, -t <list> | Allowlist specific tool names across built-in, extension, and custom tools | | --no-builtin-tools, -nbt | Disable built-in tools by default but keep extension/custom tools enabled | | --no-tools, -nt | Disable all tools by default |

Available built-in tools: read, bash, edit, write, grep, find, ls

Resource Options

| Option | Description | |--------|-------------| | -e, --extension <source> | Load extension from path, npm, or git (repeatable) | | --no-extensions | Disable extension discovery | | --skill <path> | Load skill (repeatable) | | --no-skills | Disable skill discovery | | --prompt-template <path> | Load prompt template (repeatable) | | --no-prompt-templates | Disable prompt template discovery | | --theme <path> | Load theme (repeatable) | | --no-themes | Disable theme discovery | | --no-context-files, -nc | Disable AGENTS.md and CLAUDE.md context file discovery |

Combine --no-* with explicit flags to load exactly what you need, ignoring settings.json (e.g., --no-extensions -e ./my-ext.ts).

Other Options

| Option | Description | |--------|-------------| | --system-prompt <text> | Replace default prompt (context files and skills still appended) | | --append-system-prompt <text> | Append to system prompt | | --verbose | Force verbose startup | | -h, --help | Show help | | -v, --version | Show version |

File Arguments

Prefix files with @ to include in the message:

senpi @prompt.md "Answer this"
senpi -p @screenshot.png "What's in this image?"
senpi @code.ts @test.ts "Review these files"

Examples

# Interactive with initial prompt
senpi "List all .ts files in src/"

# Non-interactive
senpi -p "Summarize this codebase"

# Non-interactive with piped stdin
cat README.md | senpi -p "Summarize this text"

# Different model
senpi --provider openai --model gpt-4o "Help me refactor"

# Model with provider prefix (no --provider needed)
senpi --model openai/gpt-4o "Help me refactor"

# Model with thinking level shorthand
senpi --model sonnet:high "Solve this complex problem"

# Limit model cycling
senpi --models "claude-*,gpt-4o"

# Read-only mode
senpi --tools read,grep,find,ls -p "Review the code"

# High thinking level
senpi --thinking high "Solve this complex problem"

Environment Variables

| Variable | Description | |----------|-------------| | SENPI_CODING_AGENT_DIR | Override config directory (default: ~/.senpi/agent) | | SENPI_CODING_AGENT_SESSION_DIR | Override session storage directory (overridden by --session-dir) | | PI_PACKAGE_DIR | Override package directory (useful for Nix/Guix where store paths tokenize poorly) | | PI_OFFLINE | Disable startup network operations, including update checks, package update checks, and install/update telemetry | | PI_SKIP_VERSION_CHECK | Skip the Pi version update check at startup. This prevents the pi.dev latest-version request | | PI_TELEMETRY | Override install/update telemetry. Use 1/true/yes to enable or 0/false/no to disable. This does not disable update checks | | PI_CACHE_RETENTION | Set to long for extended prompt cache (Anthropic: 1h, OpenAI: 24h) | | PI_BASH_DEFAULT_TIMEOUT_SECONDS | Default timeout in seconds applied to bash tool calls when the model omits timeout (default: 120). | | PI_BASH_MAX_TIMEOUT_SECONDS | Recommended maximum timeout in seconds for prompt guidance (default: 600, automatically raised to default if a smaller value is configured). Explicit timeout values are preserved. | | VISUAL, EDITOR | External editor for Ctrl+G |

Contributing & Development

See CONTRIBUTING.md for guidelines and docs/development.md for setup, forking, and debugging.

License

MIT

See Also

• @earendil-works/pi-ai: Core LLM toolkit
• @earendil-works/pi-agent-core: Agent framework
• @earendil-works/pi-tui: Terminal UI components