Archon/README.md

Dynamous Remote Coding Agent

Control AI coding assistants (Claude Code, Codex) remotely from a Web UI, Telegram, GitHub, and more. Built for developers who want to code from anywhere with persistent sessions and flexible workflows/systems.

Quick Start: Getting Started • Server Setup • AI Assistant Setup • Platform Setup • Usage Guide

Features

• Web UI: Built-in React dashboard with real-time streaming, tool call visualization, and conversation management — no external platform required
• Multi-Platform Support: Interact via Web UI, Telegram, Slack, Discord, GitHub issues/PRs, and more
• Multiple AI Assistants: Choose between Claude Code or Codex (or both)
• Persistent Sessions: Sessions survive container restarts with full context preservation
• Codebase Management: Clone and work with any GitHub repository
• Flexible Streaming: Real-time or batch message delivery per platform
• Generic Command System: User-defined commands versioned with Git
• Docker Ready: Simple deployment with Docker Compose

Getting Started

The fastest way to set up Archon is through the built-in setup wizard in Claude Code.

Interactive Setup (Recommended)

Step 1: Clone the repo and install dependencies

git clone https://github.com/dynamous-community/remote-coding-agent
cd remote-coding-agent
bun install

Step 2: Open Claude Code in the repo

claude

Step 3: Ask Claude to set up Archon

Set up Archon

The skill walks you through everything interactively: installing the CLI, authenticating, choosing platforms (CLI, GitHub, Telegram, Slack, Discord), configuring credentials, and copying the skill to your target repository.

When it's done, you'll have the archon command available globally and the skill installed in your target repo — open Claude Code there and start using it.

Manual Setup

If you prefer to set things up yourself:

Manual CLI setup steps

1. Install and link the CLI

cd remote-coding-agent
bun install
cd packages/cli && bun link

This creates an archon command available from anywhere on your system.

2. Authenticate with Claude

which claude   # verify Claude Code is installed
claude /login  # authenticate if needed

3. Copy the skill to your target repository

mkdir -p /path/to/your/repository/.claude/skills
cp -r .claude/skills/archon /path/to/your/repository/.claude/skills/archon

4. Run workflows from your target repo

cd /path/to/your/repository
archon workflow list
archon workflow run assist "What does this codebase do?"

Note: Workflow and isolation commands must be run from within a git repository. Running from subdirectories works (resolves to repo root).

Detailed documentation: CLI User Guide

---

Prerequisites

System Requirements:

• Docker & Docker Compose (for server deployment)
• Bun 1.0+ (for local development)

Platform Support:

• macOS: Apple Silicon (M1/M2/M3) and Intel - fully supported
• Linux: x64 and ARM64 - fully supported
• Windows: Requires WSL2 (Windows Subsystem for Linux 2) - see Windows Setup below

Accounts Required:

• GitHub account (for repository cloning via /clone command)
• At least one of: Claude Pro/Max subscription OR Codex account
• Optional: Telegram, Slack, Discord, or GitHub account (the built-in Web UI works without any external platform)

---

Server Quick Start

Option 1: Docker (Not working yet => works when repo goes public)

# 1. Get the files
mkdir remote-agent && cd remote-agent
curl -fsSL https://raw.githubusercontent.com/dynamous-community/remote-coding-agent/main/deploy/docker-compose.yml -o docker-compose.yml
curl -fsSL https://raw.githubusercontent.com/dynamous-community/remote-coding-agent/main/deploy/.env.example -o .env

# 2. Configure (edit .env with your tokens)
nano .env

# 3. Run
docker compose up -d --profile <yourprofile>

# 4. Check it's working
curl http://localhost:3000/health

Option 2: Local Development

# 1. Clone and install
git clone https://github.com/dynamous-community/remote-coding-agent
cd remote-coding-agent
bun install

# 2. Configure
cp .env.example .env
nano .env  # Add your AI assistant tokens (Claude or Codex)

# 3. Start server + Web UI (SQLite auto-detected, no database setup needed)
bun run dev

# 4. Open Web UI
# http://localhost:5173

Optional: Use PostgreSQL instead of SQLite:

docker compose --profile with-db up -d postgres
# Set DATABASE_URL=postgresql://postgres:postgres@localhost:5432/remote_coding_agent in .env

Note: The database schema is created automatically on first container startup via the mounted migration file. No manual psql step is needed for fresh installs.

Option 3: Self-Hosted Production

See Cloud Deployment Guide for deploying to:

• DigitalOcean, Linode, AWS EC2, or any VPS
• With automatic HTTPS via Caddy

Directory Structure

The app uses ~/.archon/ for all managed files:

~/.archon/
├── workspaces/     # Cloned repositories (auto-synced before worktree creation)
├── worktrees/      # Git worktrees for isolation
├── archon.db       # SQLite database (when DATABASE_URL not set)
└── config.yaml     # Optional: global configuration

On Windows: C:\Users\<username>\.archon\ In Docker: /.archon/

See Configuration Guide for customization options.

Important: How commands and workflows are loaded

Commands (.archon/commands/) and workflows (.archon/workflows/) are loaded at runtime from the working directory — not from a fixed location. This means:

• Server (Telegram/Slack/GitHub): The working directory is the workspace clone (~/.archon/workspaces/owner/repo/). Changes to commands or workflows must be committed and pushed to the remote — the workspace syncs from origin before worktree creation, but does not see local uncommitted changes from other clones.
• CLI (archon workflow run): The working directory is wherever you run the command. If you run from your local repo, it reads files directly from disk, including uncommitted changes.

If you edit a workflow locally but don't push, the server won't pick it up. The CLI will, as long as you run it from the same directory.

---

Setup Guide

Get started:

git clone https://github.com/dynamous-community/remote-coding-agent
cd remote-coding-agent
bun install

1. Core Configuration (Required)

Create environment file:

cp .env.example .env

Set these required variables:

Variable	Purpose	How to Get
DATABASE_URL	PostgreSQL connection (optional)	Omit for SQLite (default, zero setup). See database options below
GH_TOKEN	Repository cloning	Generate token with repo scope
GITHUB_TOKEN	Same as GH_TOKEN	Use same token value
PORT	HTTP server port	Default: 3090 (optional)
ARCHON_HOME	(Optional) Override base directory	Default: ~/.archon

GitHub Personal Access Token Setup:

1. Visit GitHub Settings > Personal Access Tokens
2. Click "Generate new token (classic)" → Select scope: repo
3. Copy token (starts with ghp_...) and set both variables:

# .env
GH_TOKEN=ghp_your_token_here
GITHUB_TOKEN=ghp_your_token_here  # Same value

Note: Repository clones are stored in ~/.archon/workspaces/ by default (or /.archon/workspaces/ in Docker). Set ARCHON_HOME to override the base directory.

Database Setup — SQLite is the default (zero setup, recommended for most users):

Option A: SQLite (Default - No Setup Required)

Simply omit the DATABASE_URL variable from your .env file. The app will automatically:

• Create a SQLite database at ~/.archon/archon.db
• Initialize the schema on first run
• Use this database for all operations

Pros:

• Zero configuration required
• No external database needed
• Perfect for single-user CLI usage

Cons:

• Not suitable for multi-container deployments
• No network access (CLI and server can't share database across different hosts)

Option B: Remote PostgreSQL — Advanced (Supabase, Neon)

Set your remote connection string:

DATABASE_URL=postgresql://user:password@host:5432/dbname

For fresh installations, run the combined migration:

psql $DATABASE_URL < migrations/000_combined.sql

This creates 7 tables:

• remote_agent_codebases - Repository metadata
• remote_agent_conversations - Platform conversation tracking
• remote_agent_sessions - AI session management
• remote_agent_isolation_environments - Worktree isolation tracking
• remote_agent_workflow_runs - Workflow execution tracking
• remote_agent_workflow_events - Step-level workflow event log
• remote_agent_messages - Conversation message history

For updates to existing installations, run only the migrations you haven't applied yet:

# Check which migrations you've already run, then apply new ones:
psql $DATABASE_URL < migrations/002_command_templates.sql
psql $DATABASE_URL < migrations/003_add_worktree.sql
psql $DATABASE_URL < migrations/004_worktree_sharing.sql
psql $DATABASE_URL < migrations/006_isolation_environments.sql
psql $DATABASE_URL < migrations/007_drop_legacy_columns.sql
psql $DATABASE_URL < migrations/011_partial_unique_constraint.sql

Option C: Local PostgreSQL — Advanced (via Docker)

Use the with-db profile for automatic PostgreSQL setup:

DATABASE_URL=postgresql://postgres:postgres@postgres:5432/remote_coding_agent

For fresh installations, database schema is created automatically when you start with docker compose --profile with-db. The combined migration runs on first startup.

For updates to existing Docker installations, you need to manually run new migrations:

# Connect to the running postgres container
docker compose exec postgres psql -U postgres -d remote_coding_agent

# Then run the migrations you haven't applied yet
\i /migrations/002_command_templates.sql
\i /migrations/003_add_worktree.sql
\i /migrations/004_worktree_sharing.sql
\i /migrations/006_isolation_environments.sql
\i /migrations/007_drop_legacy_columns.sql
\i /migrations/011_partial_unique_constraint.sql
\q

Or from your host machine (requires psql installed):

psql postgresql://postgres:postgres@localhost:5432/remote_coding_agent < migrations/002_command_templates.sql
psql postgresql://postgres:postgres@localhost:5432/remote_coding_agent < migrations/003_add_worktree.sql
psql postgresql://postgres:postgres@localhost:5432/remote_coding_agent < migrations/004_worktree_sharing.sql
psql postgresql://postgres:postgres@localhost:5432/remote_coding_agent < migrations/006_isolation_environments.sql
psql postgresql://postgres:postgres@localhost:5432/remote_coding_agent < migrations/007_drop_legacy_columns.sql
psql postgresql://postgres:postgres@localhost:5432/remote_coding_agent < migrations/011_partial_unique_constraint.sql

---

2. AI Assistant Setup (Choose At Least One)

You must configure at least one AI assistant. Both can be configured if desired.

🤖 Claude Code

Recommended for Claude Pro/Max subscribers.

Authentication Options:

Claude Code supports three authentication modes via CLAUDE_USE_GLOBAL_AUTH:

1. Global Auth (set to true): Uses credentials from claude /login
2. Explicit Tokens (set to false): Uses tokens from env vars below
3. Auto-Detect (not set): Uses tokens if present in env, otherwise global auth

Option 1: Global Auth (Recommended)

CLAUDE_USE_GLOBAL_AUTH=true

Option 2: OAuth Token

# Install Claude Code CLI first: https://docs.claude.com/claude-code/installation
claude setup-token

# Copy the token starting with sk-ant-oat01-...

CLAUDE_CODE_OAUTH_TOKEN=sk-ant-oat01-xxxxx

Option 3: API Key (Pay-per-use)

1. Visit console.anthropic.com/settings/keys
2. Create a new key (starts with sk-ant-)

CLAUDE_API_KEY=sk-ant-xxxxx

Set as default assistant (optional):

If you want Claude to be the default AI assistant for new conversations without codebase context, set this environment variable:

DEFAULT_AI_ASSISTANT=claude

🤖 Codex

Authenticate with Codex CLI:

# Install Codex CLI first: https://docs.codex.com/installation
codex login

# Follow browser authentication flow

Extract credentials from auth file:

On Linux/Mac:

cat ~/.codex/auth.json

On Windows:

type %USERPROFILE%\.codex\auth.json

Set all four environment variables:

CODEX_ID_TOKEN=eyJhbGc...
CODEX_ACCESS_TOKEN=eyJhbGc...
CODEX_REFRESH_TOKEN=rt_...
CODEX_ACCOUNT_ID=6a6a7ba6-...

Set as default assistant (optional):

If you want Codex to be the default AI assistant for new conversations without codebase context, set this environment variable:

DEFAULT_AI_ASSISTANT=codex

How Assistant Selection Works:

• Assistant type is set per codebase (auto-detected from .codex/ or .claude/ folders)
• Once a conversation starts, the assistant type is locked for that conversation
• DEFAULT_AI_ASSISTANT (optional) is used only for new conversations without codebase context

---

3. Platform Adapter Setup (Optional)

The built-in Web UI works out of the box with no additional configuration. Optionally, configure one or more external platforms for remote access:

🌐 Web UI (Built-in — No Setup Required)

The Web UI is available automatically when you start the server. No tokens or configuration needed.

Development:

bun run dev
# Web UI: http://localhost:5173
# API server: http://localhost:3090

Production:

bun run build    # Build the frontend
bun run start    # Server serves both API and Web UI on port 3090

Features:

• Real-time streaming of AI responses via Server-Sent Events (SSE)
• Tool call visualization with collapsible cards showing inputs/outputs
• Conversation management (create, switch, rename, delete, persist across sessions)
• Project/codebase browsing and management (clone, register, remove)
• Workflow invocation from UI with real-time progress tracking
• Lock indicator showing when the agent is working
• Connected/disconnected status indicator
• Message history persistence across page refreshes

💬 Telegram

Create Telegram Bot:

1. Message @BotFather on Telegram
2. Send /newbot and follow the prompts
3. Copy the bot token (format: 123456789:ABCdefGHIjklMNOpqrsTUVwxyz)

Set environment variable:

TELEGRAM_BOT_TOKEN=123456789:ABCdefGHI...

Configure streaming mode (optional):

TELEGRAM_STREAMING_MODE=stream  # stream (default) | batch

For streaming mode details, see Advanced Configuration.

💼 Slack

Create Slack App with Socket Mode:

See the detailed Slack Setup Guide for step-by-step instructions.

Quick Overview:

1. Create app at api.slack.com/apps
2. Enable Socket Mode and get App Token (xapp-...)
3. Add Bot Token Scopes: app_mentions:read, chat:write, channels:history, im:history, im:write
4. Subscribe to events: app_mention, message.im
5. Install to workspace and get Bot Token (xoxb-...)

Set environment variables:

SLACK_BOT_TOKEN=xoxb-your-bot-token
SLACK_APP_TOKEN=xapp-your-app-token

Optional configuration:

# Restrict to specific users (comma-separated Slack user IDs)
SLACK_ALLOWED_USER_IDS=U1234ABCD,W5678EFGH

# Streaming mode
SLACK_STREAMING_MODE=batch  # batch (default) | stream

Usage:

Interact by @mentioning your bot in channels or DM directly:

@your-bot /clone https://github.com/user/repo
@your-bot /status

Thread replies maintain conversation context, enabling workflows like:

1. Clone repo in main channel
2. Continue work in thread
3. Use /worktree for parallel development

🐙 GitHub Webhooks

Requirements:

• GitHub repository with issues enabled
• GITHUB_TOKEN already set in Core Configuration above
• Public endpoint for webhooks (see ngrok setup below for local development)

Step 1: Generate Webhook Secret

On Linux/Mac:

openssl rand -hex 32

On Windows (PowerShell):

-join ((1..32) | ForEach-Object { '{0:x2}' -f (Get-Random -Maximum 256) })

Save this secret - you'll need it for steps 3 and 4.

Step 2: Expose Local Server (Development Only)

Using ngrok (Free Tier)

# Install ngrok: https://ngrok.com/download
# Or: choco install ngrok (Windows)
# Or: brew install ngrok (Mac)

# Start tunnel
ngrok http 3000

# Copy the HTTPS URL (e.g., https://abc123.ngrok-free.app)
# ⚠️ Free tier URLs change on restart

Keep this terminal open while testing.

Using Cloudflare Tunnel (Persistent URLs)

# Install: https://developers.cloudflare.com/cloudflare-one/connections/connect-apps/install-and-setup/
cloudflared tunnel --url http://localhost:3000

# Get persistent URL from Cloudflare dashboard

Persistent URLs survive restarts.

For production deployments, use your deployed server URL (no tunnel needed).

Step 3: Configure GitHub Webhook

Go to your repository settings:

• Navigate to: https://github.com/owner/repo/settings/hooks
• Click "Add webhook"
• Note: For multiple repositories, you'll need to add the webhook to each one individually

Webhook Configuration:

Field	Value
Payload URL	Local: https://abc123.ngrok-free.app/webhooks/github Production: https://your-domain.com/webhooks/github
Content type	application/json
Secret	Paste the secret from Step 1
SSL verification	Enable SSL verification (recommended)
Events	Select "Let me select individual events": ✓ Issues ✓ Issue comments ✓ Pull requests

Click "Add webhook" and verify it shows a green checkmark after delivery.

Step 4: Set Environment Variables

WEBHOOK_SECRET=your_secret_from_step_1

Important: The WEBHOOK_SECRET must match exactly what you entered in GitHub's webhook configuration.

Step 5: Configure Streaming (Optional)

GITHUB_STREAMING_MODE=batch  # batch (default) | stream

For streaming mode details, see Advanced Configuration.

Usage:

Interact by @mentioning @Archon in issues or PRs:

@Archon can you analyze this bug?
@Archon /command-invoke prime
@Archon review this implementation

First mention behavior:

• Automatically clones the repository to /.archon/workspaces/
• Detects and loads commands from .archon/commands/ if present
• Injects full issue/PR context for the AI assistant

Subsequent mentions:

• Resumes existing conversation
• Maintains full context across comments

---

Adding Additional Repositories

Once your server is running, add more repos by creating a webhook with the same secret:

# Get your existing webhook secret
WEBHOOK_SECRET=$(grep WEBHOOK_SECRET .env | cut -d= -f2)

# Add webhook to new repo (replace OWNER/REPO)
gh api repos/OWNER/REPO/hooks --method POST \
  -f "config[url]=https://YOUR_DOMAIN/webhooks/github" \
  -f "config[content_type]=json" \
  -f "config[secret]=$WEBHOOK_SECRET" \
  -f "events[]=issues" \
  -f "events[]=issue_comment" \
  -f "events[]=pull_request" \
  -f "events[]=pull_request_review_comment"

Or via GitHub UI: Repo Settings → Webhooks → Add webhook

• Payload URL: Your server URL + /webhooks/github
• Content type: application/json
• Secret: Same WEBHOOK_SECRET from your .env
• Events: Issues, Issue comments, Pull requests, Pull request review comments

Important: The webhook secret must be identical across all repos.

💬 Discord

Create Discord Bot:

1. Visit Discord Developer Portal
2. Click "New Application" → Enter a name → Click "Create"
3. Go to the "Bot" tab in the left sidebar
4. Click "Add Bot" → Confirm

Get Bot Token:

1. Under the Bot tab, click "Reset Token"
2. Copy the token (starts with a long alphanumeric string)
3. Save it securely - you won't be able to see it again

Enable Message Content Intent (Required):

1. Scroll down to "Privileged Gateway Intents"
2. Enable "Message Content Intent" (required for the bot to read messages)
3. Save changes

Invite Bot to Your Server:

1. Go to "OAuth2" → "URL Generator" in the left sidebar
2. Under "Scopes", select:
   • ✓ bot
3. Under "Bot Permissions", select:
   • ✓ Send Messages
   • ✓ Read Message History
   • ✓ Create Public Threads (optional, for thread support)
   • ✓ Send Messages in Threads (optional, for thread support)
4. Copy the generated URL at the bottom
5. Paste it in your browser and select your server
6. Click "Authorize"

Note: You need "Manage Server" permission to add bots.

Set environment variable:

DISCORD_BOT_TOKEN=your_bot_token_here

Configure user whitelist (optional):

To restrict bot access to specific users, enable Developer Mode in Discord:

1. User Settings → Advanced → Enable "Developer Mode"
2. Right-click on users → "Copy User ID"
3. Add to environment:

DISCORD_ALLOWED_USER_IDS=123456789012345678,987654321098765432

Configure streaming mode (optional):

DISCORD_STREAMING_MODE=batch  # batch (default) | stream

For streaming mode details, see Advanced Configuration.

Usage:

The bot responds to:

• Direct Messages: Just send messages directly
• Server Channels: @mention the bot (e.g., @YourBotName help me with this code)
• Threads: Bot maintains context in thread conversations

---

4. Start the Application

Choose how to start the application based on your setup:

Option A: Local Development (Recommended — SQLite, No Docker)

Run directly with Bun. SQLite is the default — no database setup needed:

bun install  # First time only
bun run dev  # Starts server + Web UI with hot reload
# Web UI: http://localhost:5173
# API: http://localhost:3090

Option B: With Remote PostgreSQL (Supabase, Neon, etc.)

Starts only the app container (requires DATABASE_URL set to remote database in .env):

# Start app container
docker compose --profile external-db up -d --build

# View logs
docker compose logs -f app

Option C: With Local PostgreSQL (Docker)

Starts both the app and PostgreSQL containers:

# Start containers
docker compose --profile with-db up -d --build

# Wait for startup (watch logs)
docker compose logs -f app-with-db

# Database tables are created automatically via init script

Stop the application:

docker compose --profile external-db down  # If using Option A
docker compose --profile with-db down      # If using Option B

---

Usage

Available Commands

Once your platform adapter is running, you can use these commands. Type /help to see this list.

Codebase Commands (Per-Project)

Command	Description
/command-set <name> <path> [text]	Register a command from file
/load-commands <folder>	Bulk load commands (recursive)
/command-invoke <name> [args]	Execute a codebase command
/commands	List registered commands

Note: Commands use relative paths (e.g., .archon/commands/plan.md)

Codebase Management

Command	Description
/clone <repo-url>	Clone repository
/repos	List repositories (numbered)
/repo <#|name> [pull]	Switch repo (auto-loads commands)
/repo-remove <#|name>	Remove repo and codebase record
/getcwd	Show working directory
/setcwd <path>	Set working directory

Tip: Use /repo for quick switching between cloned repos, /setcwd for manual paths.

Worktrees (Isolation)

Command	Description
/worktree create <branch>	Create isolated worktree
/worktree list	Show worktrees for this repo
/worktree remove [--force]	Remove current worktree
/worktree cleanup merged|stale	Clean up worktrees
/worktree orphans	Show all worktrees from git

Workflows

Command	Description
/workflow list	Show available workflows
/workflow reload	Reload workflow definitions
/workflow status	Show running workflow details
/workflow cancel	Cancel running workflow

Note: Workflows are YAML files in .archon/workflows/

Session Management

Command	Description
/status	Show conversation state
/reset	Clear session completely
/reset-context	Reset AI context, keep worktree
/help	Show all commands

Setup

Command	Description
/init	Create .archon structure in current repo

Example Workflow (Telegram)

Clone a Repository

You: /clone https://github.com/user/my-project

Bot: Repository cloned successfully!

     Repository: my-project
     ✓ App defaults available at runtime

     Session reset - starting fresh on next message.

     You can now start asking questions about the code.

Note: Default commands and workflows are loaded at runtime and merged with repo-specific ones. Repo commands/workflows override app defaults by name. To disable defaults, set defaults.loadDefaultCommands: false or defaults.loadDefaultWorkflows: false in the repo's .archon/config.yaml.

Ask Questions Directly

You: What's the structure of this repo?

Bot: [Claude analyzes and responds...]

Create Custom Commands (Optional)

You: /init

Bot: Created .archon structure:
       .archon/
       ├── config.yaml
       └── commands/
           └── example.md

     Use /load-commands .archon/commands to register commands.

You can then create your own commands in .archon/commands/ and load them with /load-commands.

Check Status

You: /status

Bot: Platform: telegram
     AI Assistant: claude

     Codebase: my-project
     Repository: https://github.com/user/my-project

     Repository: my-project @ main

     Worktrees: 0/10

Work in Isolation with Worktrees

You: /worktree create feature-auth

Bot: Worktree created!

     Branch: feature-auth
     Path: feature-auth/

     This conversation now works in isolation.
     Run dependency install if needed (e.g., bun install).

Reset Session

You: /reset

Bot: Session cleared. Starting fresh on next message.

     Codebase configuration preserved.

Example Workflow (GitHub)

Create an issue or comment on an existing issue/PR:

@your-bot-name can you help me understand the authentication flow?

Bot responds with analysis. Continue the conversation:

@your-bot-name can you create a sequence diagram for this?

Bot maintains context and provides the diagram.

---

Advanced Configuration

Streaming Modes Explained

Stream Mode

Messages are sent in real-time as the AI generates responses.

Configuration:

TELEGRAM_STREAMING_MODE=stream
GITHUB_STREAMING_MODE=stream

Pros:

• Real-time feedback and progress indication
• More interactive and engaging
• See AI reasoning as it works

Cons:

• More API calls to platform
• May hit rate limits with very long responses
• Creates many messages/comments

Best for: Interactive chat platforms (Telegram)

Batch Mode

Only the final summary message is sent after AI completes processing.

Configuration:

TELEGRAM_STREAMING_MODE=batch
GITHUB_STREAMING_MODE=batch

Pros:

• Single coherent message/comment
• Fewer API calls
• No spam or clutter

Cons:

• No progress indication during processing
• Longer wait for first response
• Can't see intermediate steps

Best for: Issue trackers and async platforms (GitHub)

Concurrency Settings

Control how many conversations the system processes simultaneously:

MAX_CONCURRENT_CONVERSATIONS=10  # Default: 10

How it works:

• Conversations are processed with a lock manager
• If max concurrent limit reached, new messages are queued
• Prevents resource exhaustion and API rate limits
• Each conversation maintains its own independent context

Check current load:

curl http://localhost:3000/health/concurrency

Response:

{
  "status": "ok",
  "active": 3,
  "queued": 0,
  "maxConcurrent": 10
}

Tuning guidance:

• Low resources: Set to 3-5
• Standard: Default 10 works well
• High resources: Can increase to 20-30 (monitor API limits)

Health Check Endpoints

The application exposes health check endpoints for monitoring:

Basic Health Check:

curl http://localhost:3090/health

Returns: {"status":"ok"}

Database Connectivity:

curl http://localhost:3090/health/db

Returns: {"status":"ok","database":"connected"}

Concurrency Status:

curl http://localhost:3090/health/concurrency

Returns: {"status":"ok","active":0,"queued":0,"maxConcurrent":10}

Use cases:

• Docker healthcheck configuration
• Load balancer health checks
• Monitoring and alerting systems (Prometheus, Datadog, etc.)
• CI/CD deployment verification

Custom Command System

Create your own commands by adding markdown files to your codebase:

1. Create command file:

mkdir -p .archon/commands
cat > .archon/commands/analyze.md << 'EOF'
You are an expert code analyzer.

Analyze the following aspect of the codebase: $1

Provide:
1. Current implementation analysis
2. Potential issues or improvements
3. Best practices recommendations

Focus area: $ARGUMENTS
EOF

2. Load commands:

/load-commands .archon/commands

3. Invoke your command:

/command-invoke analyze "security vulnerabilities"

Variable substitution:

• $1, $2, $3, etc. - Positional arguments
• $ARGUMENTS - All arguments as a single string
• $PLAN - Previous plan from session metadata
• $IMPLEMENTATION_SUMMARY - Previous execution summary
• $BASE_BRANCH - Base branch from config or auto-detected from repo

Commands are version-controlled with your codebase, not stored in the database.

Workflows (Multi-Step Automation)

Workflows are YAML files that define multi-step AI processes. They can be step-based (sequential commands) or loop-based (autonomous iteration).

Location: .archon/workflows/

Example step-based workflow (.archon/workflows/fix-github-issue.yaml):

name: fix-github-issue
description: |
  Use when: User wants to FIX or RESOLVE a GitHub issue.
  Does: Investigates root cause -> creates plan -> makes code changes -> creates PR.  

model: sonnet  # Optional: provider inherited from .archon/config.yaml

steps:
  - command: investigate-issue

  - command: implement-issue
    clearContext: true

Example loop-based workflow (autonomous iteration):

name: ralph-loop
description: Execute plan until all validations pass

model: sonnet  # Optional: provider inherited from .archon/config.yaml

loop:
  until: "All validations pass"
  max_iterations: 10
  fresh_context: true

prompt: |
  Continue implementing the plan. Run validation after each change.
  Signal completion with: "All validations pass"  

How workflows are invoked:

• AI routes to workflows automatically based on user intent
• If no workflow matches, falls back to archon-assist with a "Routing unclear" notice; if archon-assist is not available, the raw routing response is returned instead
• Workflows use commands defined in .archon/commands/
• Only one workflow can run per conversation at a time

Managing workflows:

/workflow list    # Show available workflows
/workflow reload  # Reload definitions after editing
/workflow cancel  # Cancel a running workflow

---

Architecture

System Overview

┌─────────────────────────────────────────────────────────┐
│  Platform Adapters (Web UI, Telegram, Slack, Discord,  │
│                    GitHub)                               │
└──────────────────────────┬──────────────────────────────┘
                           │
                           ▼
┌─────────────────────────────────────────────────────────┐
│                     Orchestrator                        │
│          (Message Routing & Context Management)         │
└─────────────┬───────────────────────────┬───────────────┘
              │                           │
      ┌───────┴────────┐          ┌───────┴────────┐
      │                │          │                │
      ▼                ▼          ▼                ▼
┌───────────┐  ┌────────────┐  ┌──────────────────────────┐
│  Command  │  │  Workflow  │  │    AI Assistant Clients  │
│  Handler  │  │  Executor  │  │      (Claude / Codex)    │
│  (Slash)  │  │  (YAML)    │  │                          │
└───────────┘  └────────────┘  └──────────────────────────┘
      │              │                      │
      └──────────────┴──────────────────────┘
                           │
                           ▼
┌─────────────────────────────────────────────────────────┐
│              SQLite / PostgreSQL (7 Tables)             │
│   Codebases • Conversations • Sessions • Workflow Runs  │
│    Isolation Environments • Messages • Workflow Events  │
└─────────────────────────────────────────────────────────┘

Key Design Patterns

• Web UI: React dashboard with SSE streaming, served by the backend in production
• Adapter Pattern: Platform-agnostic via IPlatformAdapter interface
• Strategy Pattern: Swappable AI assistants via IAssistantClient interface
• Session Persistence: AI context survives restarts via database storage
• Generic Commands: User-defined markdown commands versioned with Git
• Workflow Engine: YAML-based multi-step automation with step and loop modes
• Worktree Isolation: Git worktrees enable parallel work per conversation, auto-synced with origin before creation
• Concurrency Control: Lock manager prevents race conditions

Database Schema

7 tables with `remote_agent_` prefix

1. remote_agent_codebases - Repository metadata

   • Commands stored as JSONB: {command_name: {path, description}}
   • AI assistant type per codebase
   • Default working directory

2. remote_agent_conversations - Platform conversation tracking

   • Platform type + conversation ID (unique constraint)
   • Linked to codebase via foreign key
   • AI assistant type locked at creation

3. remote_agent_sessions - AI session management

   • Active session flag (one per conversation)
   • Session ID for resume capability
   • Metadata JSONB for command context

4. remote_agent_isolation_environments - Worktree isolation

   • Tracks git worktrees per issue/PR
   • Enables worktree sharing between linked issues and PRs

5. remote_agent_workflow_runs - Workflow execution tracking

   • Tracks active workflows per conversation
   • Prevents concurrent workflow execution
   • Stores workflow state, step progress, and parent conversation linkage

6. remote_agent_workflow_events - Step-level workflow event log

   • Records step transitions, artifacts, and errors per workflow run
   • Lean UI-relevant events (verbose logs stored in JSONL files)
   • Enables workflow run detail views and debugging

7. remote_agent_messages - Conversation message history

   • Persists user and assistant messages with timestamps
   • Stores tool call metadata (name, input, duration) in JSONB
   • Enables message history in Web UI across page refreshes

---

Troubleshooting

Bot Not Responding

Check if application is running:

docker compose ps
# Should show 'app' or 'app-with-db' with state 'Up'

Check application logs:

docker compose logs -f app          # If using --profile external-db
docker compose logs -f app-with-db  # If using --profile with-db

Verify bot token:

# In your .env file
cat .env | grep TELEGRAM_BOT_TOKEN

Test with health check:

curl http://localhost:3090/health
# Expected: {"status":"ok"}

Database Connection Errors

Check database health:

curl http://localhost:3090/health/db
# Expected: {"status":"ok","database":"connected"}

For local PostgreSQL (with-db profile):

# Check if postgres container is running
docker compose ps postgres

# Check postgres logs
docker compose logs -f postgres

# Test direct connection
docker compose exec postgres psql -U postgres -c "SELECT 1"

For remote PostgreSQL:

# Verify DATABASE_URL
echo $DATABASE_URL

# Test connection directly
psql $DATABASE_URL -c "SELECT 1"

Verify tables exist:

# For local postgres
docker compose exec postgres psql -U postgres -d remote_coding_agent -c "\dt"

# Should show: remote_agent_codebases, remote_agent_conversations, remote_agent_sessions,
# remote_agent_isolation_environments, remote_agent_workflow_runs, remote_agent_workflow_events,
# remote_agent_messages

Clone Command Fails

Verify GitHub token:

cat .env | grep GH_TOKEN
# Should have both GH_TOKEN and GITHUB_TOKEN set

Test token validity:

# Test GitHub API access
curl -H "Authorization: token $GH_TOKEN" https://api.github.com/user

Check workspace permissions:

# Use the service name matching your profile
docker compose exec app ls -la /.archon/workspaces          # --profile external-db
docker compose exec app-with-db ls -la /.archon/workspaces  # --profile with-db

Try manual clone:

docker compose exec app git clone https://github.com/user/repo /.archon/workspaces/test-repo
# Or app-with-db if using --profile with-db

GitHub Webhook Not Triggering

Verify webhook delivery:

1. Go to your webhook settings in GitHub
2. Click on the webhook
3. Check "Recent Deliveries" tab
4. Look for successful deliveries (green checkmark)

Check webhook secret:

cat .env | grep WEBHOOK_SECRET
# Must match exactly what you entered in GitHub

Verify ngrok is running (local dev):

# Check ngrok status
curl http://localhost:4040/api/tunnels
# Or visit http://localhost:4040 in browser

Check application logs for webhook processing:

docker compose logs -f app | grep GitHub          # --profile external-db
docker compose logs -f app-with-db | grep GitHub  # --profile with-db

TypeScript Compilation Errors

Clean and rebuild:

# Stop containers (use the profile you started with)
docker compose --profile external-db down  # or --profile with-db

# Clean build
rm -rf dist node_modules
bun install
bun run build

# Restart (use the profile you need)
docker compose --profile external-db up -d --build  # or --profile with-db

Check for type errors:

bun run type-check

Container Won't Start

Check logs for specific errors:

docker compose logs app          # If using --profile external-db
docker compose logs app-with-db  # If using --profile with-db

Verify environment variables:

# Check if .env is properly formatted (include your profile)
docker compose --profile external-db config  # or --profile with-db

Rebuild without cache:

docker compose --profile external-db build --no-cache  # or --profile with-db
docker compose --profile external-db up -d             # or --profile with-db

Check port conflicts:

# See if port 3090 is already in use
# Linux/Mac:
lsof -i :3090

# Windows:
netstat -ano | findstr :3090

---

Windows (WSL2 Setup)

Archon CLI requires WSL2 (Windows Subsystem for Linux 2) on Windows. Native Windows binaries are not currently supported.

Why WSL2?

The Archon CLI relies on Unix-specific features and tools:

• Git worktree operations with symlinks
• Shell scripting for AI agent execution
• File system operations that differ between Windows and Unix

WSL2 provides a full Linux environment that runs seamlessly on Windows.

Quick WSL2 Setup

1. Install WSL2 (requires Windows 10 version 2004+ or Windows 11):

   wsl --install
   

   This installs Ubuntu by default. Restart your computer when prompted.

2. Set up Ubuntu: Open "Ubuntu" from the Start menu and create a username/password.

3. Install Bun in WSL2:

   curl -fsSL https://bun.sh/install | bash
   source ~/.bashrc
   

4. Clone and install Archon:

   git clone https://github.com/dynamous-community/remote-coding-agent
   cd remote-coding-agent
   bun install
   

5. Make CLI globally available:

   cd packages/cli
   bun link
   

6. Verify installation:

   archon version
   

Working with Windows Files

WSL2 can access your Windows files at /mnt/c/ (for C: drive):

archon workflow run assist --cwd /mnt/c/Users/YourName/Projects/my-repo "What does this code do?"

For best performance, keep projects inside the WSL2 file system (~/projects/) rather than /mnt/c/.

Tips

• VS Code Integration: Install "Remote - WSL" extension to edit WSL2 files from VS Code
• Terminal: Windows Terminal provides excellent WSL2 support
• Git: Use Git inside WSL2 for consistent behavior with Archon