New issues and PRs from new contributors are auto-closed by default. Maintainers review auto-closed issues daily. See CONTRIBUTING.md.

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

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

DM 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 dm 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 the DuckMind session publishing workflow documented in your release process. All you need is a Hugging Face account and the Hugging Face CLI.

You can also watch this video, where I show how I publish my dm sessions.

I regularly publish my own dm work sessions here:

• DuckMind OSS sessions dataset

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
  • DM Packages
• Programmatic Usage
• Philosophy
• CLI Reference

Quick Start

npm install -g @duckmind/dm@latest

Authenticate with an API key:

export ANTHROPIC_API_KEY=sk-ant-...
dm

Or use your existing subscription:

dm
/connect  # Then select provider

Then just talk to dm. By default, dm 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 dm packages.

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

Providers & Models

For each built-in provider, dm maintains a list of tool-capable models, updated with every release. Authenticate via subscription (/connect) or paste a DuckMind API Key via /connect, 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
• DuckMind
• Vercel AI Gateway
• ZAI
• OpenCode Zen
• OpenCode Go
• Hugging Face
• Kimi For Coding
• MiniMax

See docs/providers.md for detailed setup instructions.

Custom providers & models: Add providers via ~/.dm/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 the DuckMind logo. Use /resources to inspect loaded AGENTS.md files, prompt templates, skills, extensions, themes, and conflicts.
• 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 | |---------|-------------| | /connect, /logout | Connect via OAuth or DuckMind API key | | /model | Switch models | | /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 | | /resources | Show loaded context, skills, prompts, extensions, themes, and conflicts | | /hotkeys | Show all keyboard shortcuts | | /quit | Quit dm |

Keyboard Shortcuts

See /hotkeys for the full list. Customize via ~/.dm/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 scoped 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 dm 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.md for file format.

Management

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

dm -c                  # Continue most recent session
dm -r                  # Browse and select from past sessions
dm --no-session        # Ephemeral mode (don't save)
dm --session <path|id> # Use specific session file or ID
dm --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 | |----------|-------| | ~/.dm/agent/settings.json | Global (all projects) | | .dm/settings.json | Project (overrides global) |

See docs/settings.md for all options.

To opt out of anonymous install/update telemetry tied to changelog detection, set enableInstallTelemetry to false in settings.json, or set PI_TELEMETRY=0.

Context Files

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

• ~/.dm/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 .dm/SYSTEM.md (project) or ~/.dm/agent/SYSTEM.md (global). Append without replacing via APPEND_SYSTEM.md.

Customization

Prompt Templates

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

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

Place in ~/.dm/agent/prompts/, .dm/prompts/, or a dm 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.

<!-- ~/.dm/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 ~/.dm/agent/skills/, ~/.agents/skills/, .dm/skills/, or .agents/skills/ (from cwd up through parent directories) or a dm package to share with others. See docs/skills.md.

Extensions

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

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

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

What's possible:

• Custom tools (or replace built-in tools entirely)
• Sub-agents and 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 dm look like Claude Code
• Games while waiting (yes, Doom runs)
• ...anything you can dream up

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

Themes

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

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

DM Packages

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

Security: DM 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.

dm install npm:@foo/dm-tools
dm install npm:@foo/[email protected]      # pinned version
dm install git:github.com/user/repo
dm install git:github.com/user/repo@v1  # tag or commit
dm install git:[email protected]:user/repo
dm install git:[email protected]:user/repo@v1  # tag or commit
dm install https://github.com/user/repo
dm install https://github.com/user/repo@v1      # tag or commit
dm install ssh://[email protected]/user/repo
dm install ssh://[email protected]/user/repo@v1    # tag or commit
dm remove npm:@foo/dm-tools
dm uninstall npm:@foo/dm-tools          # alias for remove
dm list
dm update                               # skips pinned packages
dm config                               # enable/disable extensions, skills, prompts, themes

Packages install to ~/.dm/agent/git/ (git) or global npm. Use -l for project-local installs (.dm/git/, .dm/npm/). Git packages install dependencies with npm install --omit=dev, so runtime deps must be listed under dependencies. 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, dm auto-discovers from conventional directories (extensions/, skills/, prompts/, themes/).

See docs/packages.md.

Programmatic Usage

SDK

import { AuthStorage, createAgentSession, ModelRegistry, SessionManager } from "@mariozechner/pi-coding-agent";

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?");

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:

dm --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

DM is aggressively extensible so it doesn't have to dictate your workflow. Features that other tools bake in can be built with extensions, skills, or installed from third-party dm packages. This keeps the core minimal while letting you shape dm to fit how you work.

No MCP. Build CLI tools with READMEs (see Skills), or build an extension that adds MCP support. Why?

No sub-agents. There's many ways to do this. Spawn dm instances via tmux, or build your own with extensions, or install a package that does it your way.

No permission popups. Run in a container, or build your own confirmation flow with extensions inline with your environment and security requirements.

No plan mode. Write plans to files, or build it with extensions, or install a package.

No built-in to-dos. They confuse models. Use a TODO.md file, or build your own with extensions.

No background bash. Use tmux. Full observability, direct interaction.

Read the blog post for the full rationale.

CLI Reference

dm [options] [@files...] [messages...]

Package Commands

dm install <source> [-l]     # Install package, -l for project-local
dm remove <source> [-l]      # Remove package
dm uninstall <source> [-l]   # Alias for remove
dm update [source]           # Update packages (skips pinned)
dm list                      # List installed packages
dm 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, dm also reads piped stdin and merges it into the initial prompt:

cat README.md | dm -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 | | --models <patterns> | Comma-separated patterns for Ctrl+P cycling | | --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> | Enable specific built-in tools (default: read,bash,edit,write) | | --no-tools | Disable all built-in tools (extension tools still work) |

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:

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

Examples

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

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

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

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

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

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

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

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

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

Environment Variables

| Variable | Description | |----------|-------------| | PI_CODING_AGENT_DIR | Override config directory (default: ~/.dm/agent) | | PI_PACKAGE_DIR | Override package directory (useful for Nix/Guix where store paths tokenize poorly) | | PI_SKIP_VERSION_CHECK | Skip version check at startup | | PI_TELEMETRY | Override install telemetry. Use 1/true/yes to enable or 0/false/no to disable | | PI_CACHE_RETENTION | Set to long for extended prompt cache (Anthropic: 1h, OpenAI: 24h) | | 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

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