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

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

Loom runs in four modes: interactive, print or JSON, RPC for process integration, and an SDK for embedding in your own apps.

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
  • Loom Packages
• Programmatic Usage
• Philosophy
• CLI Reference

Quick Start

npm install -g --ignore-scripts @ianncity/coding-agent

--ignore-scripts disables dependency lifecycle scripts during install. Loom does not require install scripts for normal npm installs.

Installer alternative:

curl -fsSL https://loom.dev/install.sh | sh

Authenticate with an API key:

export ANTHROPIC_API_KEY=sk-ant-...
loom

Or use your existing subscription:

loom
/login  # Then select provider

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

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

Providers & Models

For each built-in provider, loom maintains a list of tool-capable models. Configured provider catalogs refresh automatically; run loom update --models to force an immediate refresh. 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
• Ant Ling
• OpenAI
• Azure OpenAI
• DeepSeek
• NVIDIA NIM
• Google Gemini
• Google Vertex
• Amazon Bedrock
• Mistral
• Groq
• Cerebras
• Cloudflare AI Gateway
• Cloudflare Workers AI
• xAI
• OpenRouter
• Vercel AI Gateway
• ZAI Coding Plan (Global)
• ZAI Coding Plan (China)
• OpenCode Zen
• OpenCode Go
• Hugging Face
• Fireworks
• Together AI
• Baseten
• Kimi For Coding
• MiniMax
• Xiaomi MiMo
• Xiaomi MiMo Token Plan (China)
• Xiaomi MiMo Token Plan (Amsterdam)
• Xiaomi MiMo Token Plan (Singapore)

Loom also supports the llama.cpp router server. Configure it with /login llama.cpp, manage downloads and loaded models with /llama, then select a loaded model with /model. See docs/llama-cpp.md for setup and usage.

See docs/providers.md for other provider setup instructions.

Custom providers & models: Add providers via ~/.loom/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 (↑ input, ↓ output, R cache read, W cache write, CH latest cache hit rate), cost, context usage, current model. Totals include assistant responses, usage reported by tools, and summary generation.

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) | | External editor | Ctrl+G opens externalEditor, $VISUAL, $EDITOR, Notepad on Windows, or nano elsewhere | | Clipboard | Ctrl+V to paste an image or text (Alt+V on Windows), or drag images 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 | Manage provider credentials | | /llama | Download, load, and unload llama.cpp router models | | /model | Switch models | | /scoped-models | Enable/disable 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 | | /trust | Save project trust decision for future sessions (restart required) | | /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 or JSONL file | | /import <file> | Import and resume a session from a JSONL file | | /share | Upload as private GitHub gist with shareable HTML link | | /reload | Reload keybindings, extensions, skills, prompts, themes, and context files | | /hotkeys | Show all keyboard shortcuts | | /changelog | Display version history | | /quit | Quit loom |

Keyboard Shortcuts

See /hotkeys for the full list. Customize via ~/.loom/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 | | Ctrl+X | Copy the last assistant message |

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 loom 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 ~/.loom/agent/sessions/ organized by working directory.

loom -c                  # Continue most recent session
loom -r                  # Browse and select from past sessions
loom --no-session        # Ephemeral mode (don't save)
loom --name "my task"    # Set session display name at startup
loom --session <path|id> # Use specific session file or ID
loom --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 Ctrl+X to copy the selected message
• 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 | |----------|-------| | ~/.loom/agent/settings.json | Global (all projects) | | .loom/settings.json | Project (overrides global) |

See docs/settings.md for all options.

Project Trust

On interactive startup, loom asks before trusting a project folder that contains project-local settings, resources, or project .agents/skills and has no saved decision for the folder or a parent folder in ~/.loom/agent/trust.json. Trusting a project allows loom to load .loom/settings.json and .loom resources, install missing project packages, and execute project extensions.

Before the trust decision, loom loads only context files, user/global extensions, and CLI -e extensions so they can handle the project_trust event. Project-local extensions, project package-managed extensions, and project settings are loaded only after the project is trusted. This split also applies when switching to a session from a different cwd whose trust has not been resolved in the current process.

Non-interactive modes (-p, --mode json, and --mode rpc) do not show a trust prompt. Without an applicable saved trust decision, they use defaultProjectTrust from global settings: ask (default) and never ignore those project resources, while always trusts them. Pass --approve/-a or --no-approve/-na to override project trust for one run.

If no extension or saved decision applies, defaultProjectTrust controls the fallback behavior. Set it to "ask", "always", or "never" in ~/.loom/agent/settings.json, or change it with /settings.

loom config and package commands use the same project trust flow, except loom update never prompts. Pass --approve to trust project-local settings for one command or --no-approve to ignore them.

Use /trust in interactive mode to save a project trust decision for future sessions, including trust for the immediate parent folder. It writes ~/.loom/agent/trust.json only; the current session is not reloaded, so restart loom for changes to take effect.

Telemetry and update checks

Loom has two separate startup features:

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

Context Files

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

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

If a directory contains AGENTS.override.md, Loom loads it instead of AGENTS.md or CLAUDE.md from that directory. Context files from other directories are still concatenated.

Use for project instructions (AGENTS.md/CLAUDE.md), 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 .loom/SYSTEM.md (project) or ~/.loom/agent/SYSTEM.md (global). Append without replacing via APPEND_SYSTEM.md.

Customization

Prompt Templates

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

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

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

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

Extensions

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

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

The default export can also be async. loom waits for async extension factories before startup continues, which is useful for one-time initialization such as fetching remote model lists before calling loom.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 loom look like Claude Code
• Games while waiting (yes, Doom runs)
• ...anything you can dream up

Place in ~/.loom/agent/extensions/, .loom/extensions/, or a loom 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 loom immediately applies changes.

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

Loom Packages

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

Security: Loom 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.

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

Packages install to ~/.loom/agent/git/ (git) or ~/.loom/agent/npm/ (npm). Use -l for project-local installs (.loom/git/, .loom/npm/). Git @ref values are pinned tags or commits; pinned packages are skipped by loom update --extensions and loom update --all, so use loom 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 loom key to package.json:

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

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

See docs/packages.md.

Programmatic Usage

SDK

import { createAgentSession, ModelRuntime, SessionManager } from "@ianncity/coding-agent";

const modelRuntime = await ModelRuntime.create();
const { session } = await createAgentSession({
  sessionManager: SessionManager.inMemory(),
  modelRuntime,
});

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:

loom --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

Loom 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 loom packages. This keeps the core minimal while letting you shape loom to fit how you work.

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

No sub-agents. There's many ways to do this. Spawn loom 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.

See the project documentation for the full rationale.

CLI Reference

loom [options] [@files...] [messages...]

Package Commands

loom install <source> [-l]     # Install package, -l for project-local
loom remove <source> [-l]      # Remove package
loom uninstall <source> [-l]   # Alias for remove
loom update [source|self|loom]   # Update loom only, or one package source
loom update --all              # Update loom and packages
loom update --extensions       # Update packages only
loom update --models           # Refresh model catalogs only
loom update --self             # Update loom only
loom update --self --force     # Reinstall loom even if current
loom update --extension <src>  # Update one package
loom list                      # List installed packages
loom config                    # Enable/disable package resources

loom config and project package commands accept --approve/--no-approve to trust or ignore project-local settings for one command. loom update never prompts for project trust.

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, loom also reads piped stdin and merges it into the initial prompt:

cat README.md | loom -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 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) | | --name <name>, -n <name> | Set session display name at startup |

Tool Options

| Option | Description | |--------|-------------| | --tools <list>, -t <list> | Allowlist specific tool names across built-in, extension, and custom tools | | --exclude-tools <list>, -xt <list> | Disable 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 | | --tui-mode <mode> | TUI mode: regular (default) or experimental fullscreen | | --verbose | Force verbose startup | | -a, --approve | Trust project-local files for this run | | -na, --no-approve | Ignore project-local files for this run | | -h, --help | Show help | | -v, --version | Show version |

File Arguments

Prefix files with @ to include in the message:

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

Examples

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

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

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

# Named one-shot session
loom --name "release audit" -p "Audit this repository"

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

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

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

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

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

# Disable one extension or built-in tool while keeping the rest available
loom --exclude-tools ask_question

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

Environment Variables

| Variable | Description | |----------|-------------| | AI_AGENT | Set to loom by the CLI and RPC entry points so generic tooling can attribute child processes to Loom | | LOOM_CODING_AGENT | Set to true by the CLI and RPC entry points so child processes can detect that they run inside Loom | | LOOM_CODING_AGENT_DIR | Override config directory (default: ~/.loom/agent) | | LOOM_CODING_AGENT_SESSION_DIR | Override session storage directory (overridden by --session-dir) | | LOOM_PACKAGE_DIR | Override package directory (useful for Nix/Guix where store paths tokenize poorly) | | LOOM_OFFLINE | Disable startup network operations, including update checks, package update checks, and install/update telemetry | | LOOM_CACHE_RETENTION | Set to long for extended prompt cache (Anthropic: 1h, OpenAI: 24h) | | VISUAL, EDITOR | Fallback external editor for Ctrl+G when externalEditor is unset; defaults to Notepad on Windows and nano elsewhere |

Commands run by the LLM-callable bash tool also receive current session metadata:

| Variable | Description | |----------|-------------| | LOOM_SESSION_ID | Current session ID | | LOOM_SESSION_FILE | Absolute session JSONL path; unset for ephemeral sessions | | LOOM_PROVIDER | Currently selected model provider | | LOOM_MODEL | Currently selected model ID | | LOOM_REASONING_LEVEL | Current effective reasoning level |

These values are resolved when each command starts. See Environment Variables for semantics, examples, and custom-tool opt-out.

Development

See docs/development.md for setup, debugging, and development workflows.

License

MIT

See Also

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