⚒️ Forge: AI-Enhanced Terminal Development Environment

A comprehensive coding agent that integrates AI capabilities with your development environment

curl -fsSL https://forgecode.dev/cli | sh

Quickstart

To get started with Forge, run the command below:

curl -fsSL https://forgecode.dev/cli | sh

On first run, Forge will guide you through setting up your AI provider credentials using the interactive login flow. Alternatively, you can configure providers beforehand:

# Configure your provider credentials interactively
forge provider login
Then start Forge
forge

Usage Examples

Forge can be used in different ways depending on your needs. Here are some common usage patterns:

> Can you explain how the authentication system works in this codebase?

> I need to add a dark mode toggle to our React application. How should I approach this?

> I'm getting this error: "TypeError: Cannot read property 'map' of undefined". What might be causing it?

> Please review the code in src/components/UserProfile.js and suggest improvements

> I want to integrate GraphQL into this Express application. Can you explain how to get started?

> I need to design a database schema for a blog with users, posts, comments, and categories

> Help me refactor this class-based component to use React Hooks

> I need to merge branch 'feature/user-profile' into main but there are conflicts

Why Forge?

Forge is designed for developers who want to enhance their workflow with AI assistance while maintaining full control over their development environment.

• Zero configuration - Just add your API key and you're ready to go
• Seamless integration - Works right in your terminal, where you already work
• Multi-provider support - Use OpenAI, Anthropic, or other LLM providers
• Secure by design - Restricted shell mode limits file system access and prevents unintended changes
• Open-source - Transparent, extensible, and community-driven

How Forge Works: Three Modes

Forge has three distinct ways to use it. Understanding this distinction upfront will save you confusion.

Interactive Mode (TUI)

Running forge with no arguments starts the interactive terminal UI, a persistent session where you type prompts and the AI responds in a conversational loop. This is the primary way to do multi-step work.

forge                              # Start a new interactive session
forge conversation resume <id>     # Resume a specific saved conversation in interactive mode
forge --conversation-id <id>       # Same: resume conversation by ID
forge --agent <agent-id>           # Start interactive session with a specific agent
forge -C /path/to/project          # Start in a specific directory
forge --sandbox experiment-name    # Create an isolated git worktree + branch, then start there

Once inside interactive mode, type your prompt and press Enter. Forge reads files, writes patches, runs commands, and maintains context across the whole session.

One-Shot CLI Mode

Pass -p (or --prompt) to run a single prompt and exit. Forge does the work and returns to your shell. Useful for scripts, piping output, or quick tasks.

forge -p "Explain the purpose of src/main.rs"
forge -p "Add error handling to the parse() function in lib.rs"
echo "What does this do?" | forge    # Pipe input as the prompt
forge commit                         # Generate an AI commit message and commit (exits when done)
forge commit --preview               # Generate commit message, print it, then exit
forge suggest "find large log files" # Translate natural language to a shell command, then exit

Note: forge conversation resume <id> opens the interactive TUI. It does not just print a message and exit. If you run it and see the cursor waiting, you are inside the interactive session. Type your prompt or press Ctrl+C to exit.

ZSH Plugin Mode (: prefix)

Install the ZSH plugin once with forge setup, then use : commands directly at your shell prompt without ever typing forge. This is the fastest mode for day-to-day development: send prompts, switch conversations, commit, and suggest commands without leaving your shell.

: refactor the auth module      # Send a prompt to the active agent
:commit                         # AI-powered git commit
:suggest "find large log files" # Translate description → shell command in your buffer
:conversation                   # Browse saved conversations with interactive picker

See the full ZSH Plugin reference below for all commands and aliases.

ZSH Plugin: The : Prefix System

When you install the ZSH plugin (forge setup), you get a : prefix command system at your shell prompt. This is the fastest way to use Forge during normal development; you never leave your shell.

How it works: Lines starting with : are intercepted before the shell sees them and routed to Forge. Everything else runs normally.

: <prompt>         # Send a prompt to the active agent
:sage <prompt>     # Send a prompt to a specific agent by name (sage, muse, forge, or any custom agent)
:agent <name>      # Switch the active agent; opens interactive picker if no name given

Agents

Forge ships with three built-in agents, each with a different role:

| Agent | Alias | Purpose | Modifies files? | |---|---|---|---| | forge | (default) | Implementation: builds features, fixes bugs, and runs tests | Yes | | sage | :ask | Research: maps architecture, traces data flow, and reads code | No | | muse | :plan | Planning: analyzes structure and writes implementation plans to plans/ | No |

Sending Prompts

: refactor the auth module to use the new middleware
:sage how does the caching layer work?    # sage = read-only research agent
:muse design a deployment strategy        # muse = planning agent (writes to plans/)
:ask how does X work?                     # alias for :sage
:plan create a migration plan             # alias for :muse

The agent context persists. Typing :sage alone (no prompt text) switches the active agent to sage for all subsequent : <prompt> commands.

Attaching Files

Type @ in a prompt, then press Tab to fuzzy-search and select files. The path is inserted as @[filename] and attached as context to the AI.

: review this code @[src/auth.rs] @[tests/auth_test.rs]

Conversation Management

Forge saves every conversation. You can switch between them like switching directories.

:new                      # Start a fresh conversation (saves current for :conversation -)
:new <initial prompt>     # Start a new conversation and immediately send a prompt
:conversation             # Open interactive picker: browse and switch conversations with preview
:conversation <id>        # Switch directly to a conversation by ID
:conversation -           # Toggle between current and previous conversation (like cd -)
:clone                    # Branch the current conversation (try a different direction)
:clone <id>               # Clone a specific conversation by ID
:rename <name>            # Rename the current conversation
:conversation-rename      # Rename a conversation via interactive picker
:retry                    # Retry the last prompt (useful if the AI misunderstood)
:copy                     # Copy the last AI response to clipboard as markdown
:dump                     # Export conversation as JSON
:dump html                # Export conversation as formatted HTML
:compact                  # Manually compact context to free up token budget

Git Integration

:commit                   # AI reads your diff, writes a commit message, and commits immediately
:commit <context>         # Same, but pass extra context: :commit fix typo in readme
:commit-preview           # AI generates the message and puts "git commit -m '...'" in your buffer
                          # so you can review/edit the message before pressing Enter

Shell Command Tools

:suggest <description>    # Translate natural language to a shell command and put it in your buffer
:edit                     # Open $EDITOR to compose a complex multi-line prompt, then send it

Session & Configuration

Some commands change settings for the current session only. Others persist to your config file (~/forge/.forge.toml). The distinction matters:

# Session-only (reset when you close the terminal; not saved to config)
:model <model-id>              # Change model for this session only
:reasoning-effort <level>      # Set reasoning effort: none/minimal/low/medium/high/xhigh/max
:agent <id>                    # Switch active agent for this session
Persistent (saved to config file)
:config-model <model-id>       # Set default model globally  (alias: :cm)
:config-provider               # Switch provider globally    (alias: :provider, :p)
:config-reasoning-effort <lvl> # Set default reasoning effort globally (alias: :cre)
:config-commit-model <id>      # Set model used for :commit  (alias: :ccm)
:config-suggest-model <id>     # Set model used for :suggest (alias: :csm)
:config-reload                 # Reset session overrides back to global config (alias: :cr)
View & edit config
:info                          # Show current session info (model, agent, conversation ID)
:config                        # Display effective resolved configuration in TOML format
:config-edit                   # Open config file in $EDITOR (alias: :ce)
:tools                         # List available tools for the current agent
:skill                         # List available skills

Skills

Skills are reusable workflows the AI can invoke as tools. Forge ships three built-in skills:

• create-skill: scaffold a new custom skill
• execute-plan: execute a plan file from plans/
• github-pr-description: generate a PR description from your diff

Custom skills live in SKILL.md files with YAML front-matter. Precedence (highest first):

| Location | Path | Scope | |---|---|---| | Project-local | .forge/skills/<name>/SKILL.md | This project only | | Global | ~/forge/skills/<name>/SKILL.md | All projects | | Built-in | Embedded in binary | Always available |

Project-local skills override global ones, which override built-in ones. To scaffold a new skill, ask: : create a new skill.

Customizing Agent Behavior

AGENTS.md: Create this file in your project root (or ~/forge/AGENTS.md globally) to give all agents persistent instructions such as coding conventions, commit message style, and things to avoid. Forge reads it automatically at the start of every conversation.

Custom agents: Place a .md file with YAML front-matter in .forge/agents/ (project) or ~/forge/agents/ (global) to define additional agents with their own models, tools, and system prompts. Project-local agents override global ones. The built-in agent files in crates/forge_repo/src/agents/ are good examples of the format.

Custom commands: Place YAML files in .forge/commands/ (project) or ~/forge/commands/ (global) to define shortcut commands available via :commandname. Commands can also be defined inline in forge.yaml under the commands: key.

Semantic Search (Workspace)

:sync                     # Index your codebase for semantic search
:workspace-init           # Initialize workspace for indexing
:workspace-status         # Show indexing status
:workspace-info           # Show workspace details

After running :sync, the AI can search your codebase by meaning rather than exact text matches. Indexing sends file content to the workspace server, which defaults to https://api.forgecode.dev. Set FORGEWORKSPACESERVER_URL to override this if self-hosting.

Quick Reference: All : Commands

| Command | Alias | What it does | |---|---|---| | : <prompt> | | Send prompt to active agent | | :new | :n | Start new conversation | | :conversation | :c | Browse/switch conversations (interactive picker) | | :conversation - | | Toggle to previous conversation | | :clone | | Branch current conversation | | :rename <name> | :rn | Rename current conversation | | :conversation-rename | | Rename conversation (interactive picker) | | :retry | :r | Retry last prompt | | :copy | | Copy last response to clipboard | | :dump | :d | Export conversation as JSON | | :compact | | Compact context | | :commit | | AI commit (immediate) | | :commit-preview | | AI commit (review first) | | :suggest <desc> | :s | Translate natural language to command | | :edit | :ed | Compose prompt in $EDITOR | | :sage <prompt> | :ask | Q&A / code understanding agent | | :muse <prompt> | :plan | Planning agent | | :agent <name> | :a | Switch active agent (interactive picker if no name given) | | :model <id> | :m | Set model for this session only | | :config-model <id> | :cm | Set default model (persistent) | | :reasoning-effort <lvl> | :re | Set reasoning effort for session | | :config-reload | :cr | Reset session overrides to global config | | :info | :i | Show session info | | :sync | :workspace-sync | Index codebase for semantic search | | :tools | :t | List available tools | | :skill | | List available skills | | :login | :provider-login | Login to a provider | | :logout | | Logout from a provider | | :keyboard-shortcuts | :kb | Show keyboard shortcuts | | :doctor | | Run shell environment diagnostics |

Command-Line Options

Here's a quick reference of Forge's command-line options:

| Option | Description | | ----------------------------------- | ------------------------------------------------------------------------ | | -p, --prompt <PROMPT> | Direct prompt to process without entering interactive mode | | -e, --event <EVENT> | Dispatch an event to the workflow in JSON format | | --conversation <CONVERSATION> | Path to a JSON file containing the conversation to execute | | --conversation-id <ID> | Resume or continue an existing conversation by ID | | --agent <AGENT> | Agent ID to use for this session | | -C, --directory <DIR> | Change to this directory before starting | | --sandbox <NAME> | Create an isolated git worktree + branch for safe experimentation | | --verbose | Enable verbose logging output | | -h, --help | Print help information | | -V, --version | Print version |

Subcommands

# Conversations
forge conversation list                  # List all saved conversations
forge conversation resume <id>           # Resume a conversation in interactive mode
forge conversation new                   # Create a new conversation ID (prints it)
forge conversation dump <id>             # Export conversation as JSON
forge conversation compact <id>          # Compact conversation context
forge conversation retry <id>            # Retry last message
forge conversation clone <id>            # Clone a conversation
forge conversation rename <id> <name>    # Rename a conversation
forge conversation delete <id>           # Delete a conversation permanently
forge conversation info <id>             # Show conversation details
forge conversation stats <id>            # Show token usage statistics
forge conversation show <id>             # Show last assistant message
Commits
forge commit                             # Generate AI commit message and commit
forge commit --preview                   # Generate commit message only (prints it)
forge commit fix the auth bug            # Pass extra context for the commit message
Shell command suggestion
forge suggest "list files by size"       # Translate description to a shell command
Providers
forge provider login                     # Add or update provider credentials (interactive)
forge provider logout                    # Remove provider credentials
forge list provider                      # List supported providers
Models & agents
forge list model                         # List available models
forge list agent                         # List available agents
Workspace / semantic search
forge workspace sync                     # Index current directory for semantic search
forge workspace init                     # Initialize workspace
forge workspace status                   # Show indexing status
forge workspace query <text>             # Query the semantic index
MCP servers
forge mcp list                           # List configured MCP servers
forge mcp import                         # Add a server from JSON
forge mcp show                           # Show server configuration
forge mcp remove                         # Remove a server
forge mcp reload                         # Reload all servers and rebuild caches
Other
forge info                               # Show config, active model, environment
forge list tool --agent <id>             # List tools for a specific agent
forge doctor                             # Run shell environment diagnostics
forge update                             # Update forge to the latest version
forge setup                              # Install ZSH plugin (updates .zshrc)

Advanced Configuration

Provider Configuration

Forge supports multiple AI providers. The recommended way to configure providers is using the interactive login command:

forge provider login

This will:

• Show you a list of available providers
• Guide you through entering the required credentials

Managing Provider Credentials

# Login to a provider (add or update credentials)
forge provider login
Remove provider credentials
forge provider logout
List supported providers
forge provider list

Deprecated: Environment Variables

⚠️ DEPRECATED: Using .env files for provider configuration is deprecated and will be removed in a future version. Please use forge provider login instead.

For backward compatibility, Forge still supports environment variables. On first run, any credentials found in environment variables will be automatically migrated to file-based storage.

# .env
OPENROUTERAPIKEY=<youropenrouterapi_key>

# .env
REQUESTYAPIKEY=<yourrequestyapi_key>

# .env
XAIAPIKEY=<yourxaiapi_key>

# .env
ZAIAPIKEY=<yourzaiapi_key>
Or for coding plan subscription
ZAICODINGAPIKEY=<yourzaicodingapi_key>

# .env
CEREBRASAPIKEY=<yourcerebrasapi_key>

# .env
NEURALWATTAPIKEY=<yourneuralwattapi_key>

# .env
ORCAROUTERAPIKEY=<yourorcarouterapi_key>

# .env
METAAPIKEY=<yourmetamodelapikey>

# forge.yaml
model: muse-spark-1.1

# .env
IOINTELLIGENCEAPIKEY=<youriointelligenceapi_key>

# forge.yaml
model: meta-llama/Llama-3.3-70B-Instruct

# .env
OPENAIAPIKEY=<youropenaiapi_key>

# forge.yaml
model: o3-mini-high

# .env
ANTHROPICAPIKEY=<youranthropicapi_key>

# forge.yaml
model: claude-3.7-sonnet

gcloud auth login
   gcloud config set project YOURPROJECTID

gcloud auth print-access-token

forge provider login
   # Select Google Vertex AI and enter your credentials

# .env
PROJECTID=<yourproject_id>
LOCATION=<your_location>
VERTEXAIAUTHTOKEN=<yourauth_token>

# forge.yaml
model: google/gemini-2.5-pro

# .env
OPENAIAPIKEY=<yourproviderapi_key>
OPENAIURL=<yourprovider_url>

# forge.yaml
model: <provider-specific-model>

# .env
OPENAIAPIKEY=<yourgroqapi_key>
OPENAI_URL=https://api.groq.com/openai/v1

# forge.yaml
model: deepseek-r1-distill-llama-70b

forge provider login
   # Select OpenAI-compatible provider and enter your Bedrock Gateway details

# .env
OPENAIAPIKEY=<yourbedrockgatewayapikey>
OPENAIURL=<yourbedrockgatewaybase_url>

# forge.yaml
model: anthropic.claude-3-opus

# .env
FORGEAPIKEY=<yourforgeapi_key>

# forge.yaml
model: claude-3.7-sonnet

forge.yaml Configuration Options

Environment Variables

Forge supports several environment variables for advanced configuration and fine-tuning. These can be set in your .env file or system environment.

# .env
FORGERETRYINITIALBACKOFFMS=1000    # Initial backoff time in milliseconds (default: 1000)
FORGERETRYBACKOFF_FACTOR=2           # Multiplier for backoff time (default: 2)
FORGERETRYMAX_ATTEMPTS=3             # Maximum retry attempts (default: 3)
FORGESUPPRESSRETRY_ERRORS=false      # Suppress retry error messages (default: false)
FORGERETRYSTATUS_CODES=429,500,502   # HTTP status codes to retry (default: 429,500,502,503,504)

# .env
FORGEHTTPCONNECT_TIMEOUT=30              # Connection timeout in seconds (default: 30)
FORGEHTTPREAD_TIMEOUT=900                # Read timeout in seconds (default: 900)
FORGEHTTPPOOLIDLETIMEOUT=90            # Pool idle timeout in seconds (default: 90)
FORGEHTTPPOOLMAXIDLEPERHOST=5        # Max idle connections per host (default: 5)
FORGEHTTPMAX_REDIRECTS=10                # Maximum redirects to follow (default: 10)
FORGEHTTPUSE_HICKORY=false               # Use Hickory DNS resolver (default: false)
FORGEHTTPTLS_BACKEND=default             # TLS backend: "default" or "rustls" (default: "default")
FORGEHTTPMINTLSVERSION=1.2             # Minimum TLS version: "1.0", "1.1", "1.2", "1.3"
FORGEHTTPMAXTLSVERSION=1.3             # Maximum TLS version: "1.0", "1.1", "1.2", "1.3"
FORGEHTTPADAPTIVE_WINDOW=true            # Enable HTTP/2 adaptive window (default: true)
FORGEHTTPKEEPALIVEINTERVAL=60          # Keep-alive interval in seconds (default: 60, use "none"/"disabled" to disable)
FORGEHTTPKEEPALIVETIMEOUT=10           # Keep-alive timeout in seconds (default: 10)
FORGEHTTPKEEPALIVEWHILE_IDLE=true      # Keep-alive while idle (default: true)
FORGEHTTPACCEPTINVALIDCERTS=false      # Accept invalid certificates (default: false) - USE WITH CAUTION
FORGEHTTPROOTCERTPATHS=/path/to/cert1.pem,/path/to/cert2.crt  # Paths to root certificate files (PEM, CRT, CER format), multiple paths separated by commas

# .env
FORGEAPIURL=https://api.forgecode.dev  # Custom Forge API URL (default: https://api.forgecode.dev)
FORGEWORKSPACESERVER_URL=http://localhost:8080  # URL for the indexing server (default: https://api.forgecode.dev/)

# .env
FORGETOOLTIMEOUT=300         # Maximum execution time in seconds for a tool before it is terminated to prevent hanging the session. (default: 300)
FORGEMAXIMAGESIZE=10485760  # Maximum image file size in bytes for readimage operations (default: 10485760 - 10 MB)
FORGEDUMPAUTO_OPEN=false     # Automatically open dump files in browser (default: false)
FORGEDEBUGREQUESTS=/path/to/debug/requests.json  # Write debug HTTP request files to specified path (supports absolute and relative paths)

# .env
FORGE_BIN=forge                    # Command to use for forge operations (default: "forge")

# .env
FORGECURRENCYSYMBOL="$"         # Currency symbol for cost display in ZSH theme (default: "$")
FORGECURRENCYCONVERSION_RATE=1.0  # Conversion rate for currency display (default: 1.0)
NERD_FONT=1                       # Enable Nerd Font icons in ZSH theme (default: auto-detected, set to "1" or "true" to enable, "0" or "false" to disable)
USENERDFONT=1                   # Alternative variable for enabling Nerd Font icons (same behavior as NERD_FONT)

# .env
FORGE_CONFIG=/custom/config/dir        # Base directory for all Forge config files (default: ~/.forge)
FORGEMAXSEARCHRESULTBYTES=10240   # Maximum bytes for search results (default: 10240 - 10 KB)
FORGEHISTORYFILE=/path/to/history    # Custom path for Forge history file (default: uses system default location)
FORGE_BANNER="Your custom banner text" # Custom banner text to display on startup (default: Forge ASCII art)
FORGEMAXCONVERSATIONS=100            # Maximum number of conversations to show in list (default: 100)
FORGEMAXLINE_LENGTH=2000             # Maximum characters per line for file read operations (default: 2000)
FORGESTDOUTMAXLINELENGTH=2000      # Maximum characters per line for shell output (default: 2000)
SHELL=/bin/zsh                         # Shell to use for command execution (Unix/Linux/macOS)
COMSPEC=cmd.exe                        # Command processor to use (Windows)

# .env
FORGESEMSEARCH_LIMIT=200            # Maximum number of results to return from initial vector search (default: 200)
FORGESEMSEARCHTOPK=20             # Top-k parameter for relevance filtering during semantic search (default: 20)

# .env
FORGE_LOG=forge=info                  # Log filter level (default: forge=debug when tracking disabled, forge=info when tracking enabled)

# .env
FORGE_TRACKER=false                   # Disable tracking enrichment metadata (default: true)

The forge.yaml file supports several advanced configuration options that let you customize Forge's behavior.

# forge.yaml
custom_rules: |
  1. Always add comprehensive error handling to any code you write.
  2. Include unit tests for all new functions.
  3. Follow our team's naming convention: camelCase for variables, PascalCase for classes.

# forge.yaml
commands:
  - name: "refactor"
    description: "Refactor selected code"
    prompt: "Please refactor this code to improve readability and performance"

# forge.yaml
model: "claude-3.7-sonnet"

# forge.yaml
maxwalkerdepth: 3 # Limit directory traversal to 3 levels deep

# forge.yaml
temperature: 0.7 # Balanced creativity and focus

# forge.yaml
maxtoolfailureperturn: 3 # Allow up to 3 failures per tool before forcing completion

# forge.yaml
maxrequestsper_turn: 50 # Allow up to 50 requests per turn

# List all MCP servers
forge mcp list
Import a server from JSON
forge mcp import
Show server configuration details
forge mcp show
Remove a server
forge mcp remove
Reload servers and rebuild caches
forge mcp reload

{
  "mcpServers": {
    "server_name": {
      "command": "commandtoexecute",
      "args": ["arg1", "arg2"],
      "env": { "ENV_VAR": "value" }
    },
    "another_server": {
      "url": "http://localhost:3000/events"
    }
  }
}

Documentation

For comprehensive documentation on all features and capabilities, please visit the documentation site.

Installation

# YOLO
curl -fsSL https://forgecode.dev/cli | sh
Package managers
nix run github:tailcallhq/forgecode # for latest dev branch

Community

Join our vibrant Discord community to connect with other Forge users and contributors, get help with your projects, share ideas, and provide feedback!

Support Us

Your support drives Forge's continued evolution! By starring our GitHub repository, you:

• Help others discover this powerful tool 🔍
• Motivate our development team 💪
• Enable us to prioritize new features 🛠️
• Strengthen our open-source community 🌱