Zorro Agent

Zorro Agent is an open-source AI agent framework by Brax that runs in your terminal, messaging platforms, and IDEs. It belongs to the same category as Claude Code (Anthropic), Codex (OpenAI), and OpenClaw — autonomous coding and task-execution agents that use tool calling to interact with your system. Zorro works with any LLM provider (OpenRouter, Anthropic, OpenAI, DeepSeek, local models, and 15+ others) and runs on Linux, macOS, and WSL.

What makes Zorro different:

• Self-improving through skills — Zorro learns from experience by saving reusable procedures as skills. When it solves a complex problem, discovers a workflow, or gets corrected, it can persist that knowledge as a skill document that loads into future sessions. Skills accumulate over time, making the agent better at your specific tasks and environment.
• Persistent memory across sessions — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends (built-in, Honcho, Mem0, and more) let you choose how memory works.
• Multi-platform gateway — the same agent runs on Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, and 10+ other platforms with full tool access, not just chat.
• Provider-agnostic — swap models and providers mid-workflow without changing anything else. Credential pools rotate across multiple API keys automatically.
• Profiles — run multiple independent Zorro instances with isolated configs, sessions, skills, and memory.
• Extensible — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, and the full Python ecosystem.

People use Zorro for software development, research, system administration, data analysis, content creation, home automation, and anything else that benefits from an AI agent with persistent context and full system access.

This skill helps you work with Zorro Agent effectively — setting it up, configuring features, spawning additional agent instances, troubleshooting issues, finding the right commands and settings, and understanding how the system works when you need to extend or contribute to it.

Docs: https://zorro-agent.nousresearch.com/docs/

Quick Start

# Install
curl -fsSL https://raw.githubusercontent.com/NousResearch/zorro-agent/main/scripts/install.sh | bash

# Interactive chat (default)
zorro

# Single query
zorro chat -q "What is the capital of France?"

# Setup wizard
zorro setup

# Change model/provider
zorro model

# Check health
zorro doctor

CLI Reference

Global Flags

zorro [flags] [command]

  --version, -V             Show version
  --resume, -r SESSION      Resume session by ID or title
  --continue, -c [NAME]     Resume by name, or most recent session
  --worktree, -w            Isolated git worktree mode (parallel agents)
  --skills, -s SKILL        Preload skills (comma-separate or repeat)
  --profile, -p NAME        Use a named profile
  --yolo                    Skip dangerous command approval
  --pass-session-id         Include session ID in system prompt

No subcommand defaults to chat.

Chat

zorro chat [flags]
  -q, --query TEXT          Single query, non-interactive
  -m, --model MODEL         Model (e.g. anthropic/claude-sonnet-4)
  -t, --toolsets LIST       Comma-separated toolsets
  --provider PROVIDER       Force provider (openrouter, anthropic, nous, etc.)
  -v, --verbose             Verbose output
  -Q, --quiet               Suppress banner, spinner, tool previews
  --checkpoints             Enable filesystem checkpoints (/rollback)
  --source TAG              Session source tag (default: cli)

Configuration

zorro setup [section]      Interactive wizard (model|terminal|gateway|tools|agent)
zorro model                Interactive model/provider picker
zorro config               View current config
zorro config edit          Open config.yaml in $EDITOR
zorro config set KEY VAL   Set a config value
zorro config path          Print config.yaml path
zorro config env-path      Print .env path
zorro config check         Check for missing/outdated config
zorro config migrate       Update config with new options
zorro login [--provider P] OAuth login (nous, openai-codex)
zorro logout               Clear stored auth
zorro doctor [--fix]       Check dependencies and config
zorro status [--all]       Show component status

Tools & Skills

zorro tools                Interactive tool enable/disable (curses UI)
zorro tools list           Show all tools and status
zorro tools enable NAME    Enable a toolset
zorro tools disable NAME   Disable a toolset

zorro skills list          List installed skills
zorro skills search QUERY  Search the skills hub
zorro skills install ID    Install a skill
zorro skills inspect ID    Preview without installing
zorro skills config        Enable/disable skills per platform
zorro skills check         Check for updates
zorro skills update        Update outdated skills
zorro skills uninstall N   Remove a hub skill
zorro skills publish PATH  Publish to registry
zorro skills browse        Browse all available skills
zorro skills tap add REPO  Add a GitHub repo as skill source

MCP Servers

zorro mcp serve            Run Zorro as an MCP server
zorro mcp add NAME         Add an MCP server (--url or --command)
zorro mcp remove NAME      Remove an MCP server
zorro mcp list             List configured servers
zorro mcp test NAME        Test connection
zorro mcp configure NAME   Toggle tool selection

Gateway (Messaging Platforms)

zorro gateway run          Start gateway foreground
zorro gateway install      Install as background service
zorro gateway start/stop   Control the service
zorro gateway restart      Restart the service
zorro gateway status       Check status
zorro gateway setup        Configure platforms

Supported platforms: Telegram, Discord, Slack, WhatsApp, Signal, Email, SMS, Matrix, Mattermost, Home Assistant, DingTalk, Feishu, WeCom, BlueBubbles (iMessage), Weixin (WeChat), API Server, Webhooks. Open WebUI connects via the API Server adapter.

Platform docs: https://zorro-agent.nousresearch.com/docs/user-guide/messaging/

Sessions

zorro sessions list        List recent sessions
zorro sessions browse      Interactive picker
zorro sessions export OUT  Export to JSONL
zorro sessions rename ID T Rename a session
zorro sessions delete ID   Delete a session
zorro sessions prune       Clean up old sessions (--older-than N days)
zorro sessions stats       Session store statistics

Cron Jobs

zorro cron list            List jobs (--all for disabled)
zorro cron create SCHED    Create: '30m', 'every 2h', '0 9 * * *'
zorro cron edit ID         Edit schedule, prompt, delivery
zorro cron pause/resume ID Control job state
zorro cron run ID          Trigger on next tick
zorro cron remove ID       Delete a job
zorro cron status          Scheduler status

Webhooks

zorro webhook subscribe N  Create route at /webhooks/<name>
zorro webhook list         List subscriptions
zorro webhook remove NAME  Remove a subscription
zorro webhook test NAME    Send a test POST

Profiles

zorro profile list         List all profiles
zorro profile create NAME  Create (--clone, --clone-all, --clone-from)
zorro profile use NAME     Set sticky default
zorro profile delete NAME  Delete a profile
zorro profile show NAME    Show details
zorro profile alias NAME   Manage wrapper scripts
zorro profile rename A B   Rename a profile
zorro profile export NAME  Export to tar.gz
zorro profile import FILE  Import from archive

Credential Pools

zorro auth add             Interactive credential wizard
zorro auth list [PROVIDER] List pooled credentials
zorro auth remove P INDEX  Remove by provider + index
zorro auth reset PROVIDER  Clear exhaustion status

Other

zorro insights [--days N]  Usage analytics
zorro update               Update to latest version
zorro pairing list/approve/revoke  DM authorization
zorro plugins list/install/remove  Plugin management
zorro honcho setup/status  Honcho memory integration (requires honcho plugin)
zorro memory setup/status/off  Memory provider config
zorro completion bash|zsh  Shell completions
zorro acp                  ACP server (IDE integration)
zorro claw migrate         Migrate from OpenClaw
zorro uninstall            Uninstall Zorro

Slash Commands (In-Session)

Type these during an interactive chat session.

Session Control

/new (/reset)        Fresh session
/clear               Clear screen + new session (CLI)
/retry               Resend last message
/undo                Remove last exchange
/title [name]        Name the session
/compress            Manually compress context
/stop                Kill background processes
/rollback [N]        Restore filesystem checkpoint
/background <prompt> Run prompt in background
/queue <prompt>      Queue for next turn
/resume [name]       Resume a named session

Configuration

/config              Show config (CLI)
/model [name]        Show or change model
/provider            Show provider info
/personality [name]  Set personality
/reasoning [level]   Set reasoning (none|minimal|low|medium|high|xhigh|show|hide)
/verbose             Cycle: off → new → all → verbose
/voice [on|off|tts]  Voice mode
/yolo                Toggle approval bypass
/skin [name]         Change theme (CLI)
/statusbar           Toggle status bar (CLI)

Tools & Skills

/tools               Manage tools (CLI)
/toolsets            List toolsets (CLI)
/skills              Search/install skills (CLI)
/skill <name>        Load a skill into session
/cron                Manage cron jobs (CLI)
/reload-mcp          Reload MCP servers
/plugins             List plugins (CLI)

Gateway

/approve             Approve a pending command (gateway)
/deny                Deny a pending command (gateway)
/restart             Restart gateway (gateway)
/sethome             Set current chat as home channel (gateway)
/update              Update Zorro to latest (gateway)
/platforms (/gateway) Show platform connection status (gateway)

Utility

/branch (/fork)      Branch the current session
/btw                 Ephemeral side question (doesn't interrupt main task)
/fast                Toggle priority/fast processing
/browser             Open CDP browser connection
/history             Show conversation history (CLI)
/save                Save conversation to file (CLI)
/paste               Attach clipboard image (CLI)
/image               Attach local image file (CLI)

Info

/help                Show commands
/commands [page]     Browse all commands (gateway)
/usage               Token usage
/insights [days]     Usage analytics
/status              Session info (gateway)
/profile             Active profile info

Exit

/quit (/exit, /q)    Exit CLI

Key Paths & Config

~/.zorro/config.yaml       Main configuration
~/.zorro/.env              API keys and secrets
~/.zorro/skills/           Installed skills
~/.zorro/sessions/         Session transcripts
~/.zorro/logs/             Gateway and error logs
~/.zorro/auth.json         OAuth tokens and credential pools
~/.zorro/zorro-agent/     Source code (if git-installed)

Profiles use ~/.zorro/profiles/<name>/ with the same layout.

Config Sections

Edit with zorro config edit or zorro config set section.key value.

Full config reference: https://zorro-agent.nousresearch.com/docs/user-guide/configuration

Providers

20+ providers supported. Set via zorro model or zorro setup.

Full provider docs: https://zorro-agent.nousresearch.com/docs/integrations/providers

Toolsets

Enable/disable via zorro tools (interactive) or zorro tools enable/disable NAME.

Tool changes take effect on /reset (new session). They do NOT apply mid-conversation to preserve prompt caching.

Voice & Transcription

STT (Voice → Text)

Voice messages from messaging platforms are auto-transcribed.

Provider priority (auto-detected):

1. Local faster-whisper — free, no API key: pip install faster-whisper
2. Groq Whisper — free tier: set GROQ_API_KEY
3. OpenAI Whisper — paid: set VOICE_TOOLS_OPENAI_KEY
4. Mistral Voxtral — set MISTRAL_API_KEY

Config:

stt:
  enabled: true
  provider: local        # local, groq, openai, mistral
  local:
    model: base          # tiny, base, small, medium, large-v3

TTS (Text → Voice)

Voice commands: /voice on (voice-to-voice), /voice tts (always voice), /voice off.

Spawning Additional Zorro Instances

Run additional Zorro processes as fully independent subprocesses — separate sessions, tools, and environments.

When to Use This vs delegate_task

One-Shot Mode

terminal(command="zorro chat -q 'Research GRPO papers and write summary to ~/research/grpo.md'", timeout=300)

# Background for long tasks:
terminal(command="zorro chat -q 'Set up CI/CD for ~/myapp'", background=true)

Interactive PTY Mode (via tmux)

Zorro uses prompt_toolkit, which requires a real terminal. Use tmux for interactive spawning:

# Start
terminal(command="tmux new-session -d -s agent1 -x 120 -y 40 'zorro'", timeout=10)

# Wait for startup, then send a message
terminal(command="sleep 8 && tmux send-keys -t agent1 'Build a FastAPI auth service' Enter", timeout=15)

# Read output
terminal(command="sleep 20 && tmux capture-pane -t agent1 -p", timeout=5)

# Send follow-up
terminal(command="tmux send-keys -t agent1 'Add rate limiting middleware' Enter", timeout=5)

# Exit
terminal(command="tmux send-keys -t agent1 '/exit' Enter && sleep 2 && tmux kill-session -t agent1", timeout=10)

Multi-Agent Coordination

# Agent A: backend
terminal(command="tmux new-session -d -s backend -x 120 -y 40 'zorro -w'", timeout=10)
terminal(command="sleep 8 && tmux send-keys -t backend 'Build REST API for user management' Enter", timeout=15)

# Agent B: frontend
terminal(command="tmux new-session -d -s frontend -x 120 -y 40 'zorro -w'", timeout=10)
terminal(command="sleep 8 && tmux send-keys -t frontend 'Build React dashboard for user management' Enter", timeout=15)

# Check progress, relay context between them
terminal(command="tmux capture-pane -t backend -p | tail -30", timeout=5)
terminal(command="tmux send-keys -t frontend 'Here is the API schema from the backend agent: ...' Enter", timeout=5)

Session Resume

# Resume most recent session
terminal(command="tmux new-session -d -s resumed 'zorro --continue'", timeout=10)

# Resume specific session
terminal(command="tmux new-session -d -s resumed 'zorro --resume 20260225_143052_a1b2c3'", timeout=10)

Tips

• Prefer `delegate_task` for quick subtasks — less overhead than spawning a full process
• Use `-w` (worktree mode) when spawning agents that edit code — prevents git conflicts
• Set timeouts for one-shot mode — complex tasks can take 5-10 minutes
• Use `zorro chat -q` for fire-and-forget — no PTY needed
• Use tmux for interactive sessions — raw PTY mode has \r vs \n issues with prompt_toolkit
• For scheduled tasks, use the cronjob tool instead of spawning — handles delivery and retry

Troubleshooting

Voice not working

1. Check stt.enabled: true in config.yaml
2. Verify provider: pip install faster-whisper or set API key
3. In gateway: /restart. In CLI: exit and relaunch.

Tool not available

1. zorro tools — check if toolset is enabled for your platform
2. Some tools need env vars (check .env)
3. /reset after enabling tools

Model/provider issues

1. zorro doctor — check config and dependencies
2. zorro login — re-authenticate OAuth providers
3. Check .env has the right API key
4. Copilot 403: gh auth login tokens do NOT work for Copilot API. You must use the Copilot-specific OAuth device code flow via zorro model → GitHub Copilot.

Changes not taking effect

• Tools/skills: /reset starts a new session with updated toolset
• Config changes: In gateway: /restart. In CLI: exit and relaunch.
• Code changes: Restart the CLI or gateway process

Skills not showing

1. zorro skills list — verify installed
2. zorro skills config — check platform enablement
3. Load explicitly: /skill name or zorro -s name

Gateway issues

Check logs first:

grep -i "failed to send\|error" ~/.zorro/logs/gateway.log | tail -20

Common gateway problems:

• Gateway dies on SSH logout: Enable linger: sudo loginctl enable-linger $USER
• Gateway dies on WSL2 close: WSL2 requires systemd=true in /etc/wsl.conf for systemd services to work. Without it, gateway falls back to nohup (dies when session closes).
• Gateway crash loop: Reset the failed state: systemctl --user reset-failed zorro-gateway

Platform-specific issues

• Discord bot silent: Must enable Message Content Intent in Bot → Privileged Gateway Intents.
• Slack bot only works in DMs: Must subscribe to message.channels event. Without it, the bot ignores public channels.
• Windows HTTP 400 "No models provided": Config file encoding issue (BOM). Ensure config.yaml is saved as UTF-8 without BOM.

Auxiliary models not working

If auxiliary tasks (vision, compression, session_search) fail silently, the auto provider can't find a backend. Either set OPENROUTER_API_KEY or GOOGLE_API_KEY, or explicitly configure each auxiliary task's provider:

zorro config set auxiliary.vision.provider <your_provider>
zorro config set auxiliary.vision.model <model_name>

Where to Find Things

Contributor Quick Reference

For occasional contributors and PR authors. Full developer docs: https://zorro-agent.nousresearch.com/docs/developer-guide/

Project Layout

zorro-agent/
├── run_agent.py          # AIAgent — core conversation loop
├── model_tools.py        # Tool discovery and dispatch
├── toolsets.py           # Toolset definitions
├── cli.py                # Interactive CLI (ZorroCLI)
├── zorro_state.py       # SQLite session store
├── agent/                # Prompt builder, context compression, memory, model routing, credential pooling, skill dispatch
├── zorro_cli/           # CLI subcommands, config, setup, commands
│   ├── commands.py       # Slash command registry (CommandDef)
│   ├── config.py         # DEFAULT_CONFIG, env var definitions
│   └── main.py           # CLI entry point and argparse
├── tools/                # One file per tool
│   └── registry.py       # Central tool registry
├── gateway/              # Messaging gateway
│   └── platforms/        # Platform adapters (telegram, discord, etc.)
├── cron/                 # Job scheduler
├── tests/                # ~3000 pytest tests
└── website/              # Docusaurus docs site

Config: ~/.zorro/config.yaml (settings), ~/.zorro/.env (API keys).

Adding a Tool (3 files)

1. Create `tools/your_tool.py`:

import json, os
from tools.registry import registry

def check_requirements() -> bool:
    return bool(os.getenv("EXAMPLE_API_KEY"))

def example_tool(param: str, task_id: str = None) -> str:
    return json.dumps({"success": True, "data": "..."})

registry.register(
    name="example_tool",
    toolset="example",
    schema={"name": "example_tool", "description": "...", "parameters": {...}},
    handler=lambda args, **kw: example_tool(
        param=args.get("param", ""), task_id=kw.get("task_id")),
    check_fn=check_requirements,
    requires_env=["EXAMPLE_API_KEY"],
)

2. Add import in model_tools.py → _discover_tools() list.

3. Add to `toolsets.py` → _ZORRO_CORE_TOOLS list.

All handlers must return JSON strings. Use get_zorro_home() for paths, never hardcode ~/.zorro.

Adding a Slash Command

1. Add CommandDef to COMMAND_REGISTRY in zorro_cli/commands.py
2. Add handler in cli.py → process_command()
3. (Optional) Add gateway handler in gateway/run.py

All consumers (help text, autocomplete, Telegram menu, Slack mapping) derive from the central registry automatically.

Agent Loop (High Level)

run_conversation():
  1. Build system prompt
  2. Loop while iterations < max:
     a. Call LLM (OpenAI-format messages + tool schemas)
     b. If tool_calls → dispatch each via handle_function_call() → append results → continue
     c. If text response → return
  3. Context compression triggers automatically near token limit

Testing

python -m pytest tests/ -o 'addopts=' -q   # Full suite
python -m pytest tests/tools/ -q            # Specific area

• Tests auto-redirect ZORRO_HOME to temp dirs — never touch real ~/.zorro/
• Run full suite before pushing any change
• Use -o 'addopts=' to clear any baked-in pytest flags

Commit Conventions

type: concise subject line

Optional body.

Types: fix:, feat:, refactor:, docs:, chore:

Key Rules

• Never break prompt caching — don't change context, tools, or system prompt mid-conversation
• Message role alternation — never two assistant or two user messages in a row
• Use get_zorro_home() from zorro_constants for all paths (profile-safe)
• Config values go in config.yaml, secrets go in .env
• New tools need a check_fn so they only appear when requirements are met