base on AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models <h1 align="center">⚒️ Forge: AI-Enhanced Terminal Development Environment</h1> <p align="center">A comprehensive coding agent that integrates AI capabilities with your development environment</p> <p align="center"><code>npm install -g @antinomyhq/forge</code></p> [](https://github.com/antinomyhq/forge/actions) [](https://github.com/antinomyhq/forge/releases) [](https://discord.gg/kRZBPpkgwq) [](https://cla-assistant.io/antinomyhq/forge)  --- <details> <summary><strong>Table&nbsp;of&nbsp;Contents</strong></summary> - [Quickstart](#quickstart) - [Usage Examples](#usage-examples) - [Interactive Mode Examples](#interactive-mode-examples) - [Why Forge?](#why-forge) - [Command-Line Options](#command-line-options) - [Advanced Configuration](#advanced-configuration) - [Provider Configuration](#provider-configuration) - [forge.yaml Configuration Options](#forgeyaml-configuration-options) - [Documentation](#documentation) - [Community](#community) - [Support Us](#support-us) </details> --- ## Quickstart Install globally: ```bash npm install -g @antinomyhq/forge ``` Sign up at [Antinomy.ai](https://app.antinomy.ai/app/) to enable the Forge provider. Then set up your Forge provider key: ```bash # .env FORGE_KEY=ForgeKey ``` Run Forge in interactive mode: ```bash forge ``` That's it! Forge is now ready to assist you with your development tasks. ## Usage Examples Forge can be used in different ways depending on your needs. Here are some common usage patterns: <details> <summary><strong>Code Understanding</strong></summary> ``` > Can you explain how the authentication system works in this codebase? ``` Forge will analyze your project's structure, identify authentication-related files, and provide a detailed explanation of the authentication flow, including the relationships between different components. </details> <details> <summary><strong>Implementing New Features</strong></summary> ``` > I need to add a dark mode toggle to our React application. How should I approach this? ``` Forge will suggest the best approach based on your current codebase, explain the steps needed, and even scaffold the necessary components and styles for you. </details> <details> <summary><strong>Debugging Assistance</strong></summary> ``` > I'm getting this error: "TypeError: Cannot read property 'map' of undefined". What might be causing it? ``` Forge will analyze the error, suggest potential causes based on your code, and propose different solutions to fix the issue. </details> <details> <summary><strong>Code Reviews</strong></summary> ``` > Please review the code in src/components/UserProfile.js and suggest improvements ``` Forge will analyze the code, identify potential issues, and suggest improvements for readability, performance, security, and maintainability. </details> <details> <summary><strong>Learning New Technologies</strong></summary> ``` > I want to integrate GraphQL into this Express application. Can you explain how to get started? ``` Forge will provide a tailored tutorial on integrating GraphQL with Express, using your specific project structure as context. </details> <details> <summary><strong>Database Schema Design</strong></summary> ``` > I need to design a database schema for a blog with users, posts, comments, and categories ``` Forge will suggest an appropriate schema design, including tables/collections, relationships, indexes, and constraints based on your project's existing database technology. </details> <details> <summary><strong>Refactoring Legacy Code</strong></summary> ``` > Help me refactor this class-based component to use React Hooks ``` Forge can help modernize your codebase by walking you through refactoring steps and implementing them with your approval. </details> <details> <summary><strong>Git Operations</strong></summary> ``` > I need to merge branch 'feature/user-profile' into main but there are conflicts ``` Forge can guide you through resolving git conflicts, explaining the differences and suggesting the best way to reconcile them. </details> ## 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** - Your code stays on your machine - **Open-source** - Transparent, extensible, and community-driven Forge helps you code faster, solve complex problems, and learn new technologies without leaving your terminal. ## 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 | | `-c, --command <COMMAND>` | Path to a file containing initial commands to execute | | `-w, --workflow <WORKFLOW>` | Path to a file containing the workflow to execute | | `-e, --event <EVENT>` | Dispatch an event to the workflow | | `--conversation <CONVERSATION>` | Path to a file containing the conversation to execute | | `-r, --restricted` | Enable restricted shell mode for enhanced security | | `--verbose` | Enable verbose output mode | | `-h, --help` | Print help information | | `-V, --version` | Print version | ## Advanced Configuration ### Provider Configuration Forge supports multiple AI providers. Below are setup instructions for each supported provider: <details> <summary><strong>Antinomy.ai (Recommended)</strong></summary> ```bash # .env FORGE_KEY=ForgeKey ``` To use Antinomy's provider with Forge: 1. Visit [https://app.antinomy.ai/](https://app.antinomy.ai/) 2. Login with your existing credentials or create a new account 3. Once logged in, your account will automatically enable the Forge Provider _No changes in `forge.yaml` required_ </details> <details> <summary><strong>OpenRouter</strong></summary> ```bash # .env OPENROUTER_API_KEY=<your_openrouter_api_key> ``` _No changes in `forge.yaml` required_ </details> <details> <summary><strong>OpenAI</strong></summary> ```bash # .env OPENAI_API_KEY=<your_openai_api_key> ``` ```yaml # forge.yaml model: o3-mini-high ``` </details> <details> <summary><strong>Anthropic</strong></summary> ```bash # .env ANTHROPIC_API_KEY=<your_anthropic_api_key> ``` ```yaml # forge.yaml model: claude-3.7-sonnet ``` </details> <details> <summary><strong>Google Vertex AI</strong></summary> ```bash # .env PROJECT_ID=<your_project_id> LOCATION=<your_location> OPENAI_API_KEY=<vertex_ai_key> OPENAI_URL=https://${LOCATION}-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/${LOCATION}/endpoints/openapi ``` ```yaml # forge.yaml model: publishers/anthropic/models/claude-3-7-sonnet ``` </details> <details> <summary><strong>OpenAI-Compatible Providers</strong></summary> ```bash # .env OPENAI_API_KEY=<your_provider_api_key> OPENAI_URL=<your_provider_url> ``` ```yaml # forge.yaml model: <provider-specific-model> ``` </details> <details> <summary><strong>Groq</strong></summary> ```bash # .env OPENAI_API_KEY=<your_groq_api_key> OPENAI_URL=https://api.groq.com/openai/v1 ``` ```yaml # forge.yaml model: deepseek-r1-distill-llama-70b ``` </details> <details> <summary><strong>Amazon Bedrock</strong></summary> To use Amazon Bedrock models with Forge, you'll need to first set up the [Bedrock Access Gateway](https://github.com/aws-samples/bedrock-access-gateway): 1. **Set up Bedrock Access Gateway**: - Follow the deployment steps in the [Bedrock Access Gateway repo](https://github.com/aws-samples/bedrock-access-gateway) - Create your own API key in Secrets Manager - Deploy the CloudFormation stack - Note your API Base URL from the CloudFormation outputs 2. **Create these files in your project directory**: ```bash # .env OPENAI_API_KEY=<your_bedrock_gateway_api_key> OPENAI_URL=<your_bedrock_gateway_base_url> ``` ```yaml # forge.yaml model: anthropic.claude-3-opus ``` </details> ### forge.yaml Configuration Options The `forge.yaml` file supports several advanced configuration options that let you customize Forge's behavior. <details> <summary><strong>Custom Rules</strong></summary> Add your own guidelines that all agents should follow when generating responses. ```yaml # 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. ``` </details> <details> <summary><strong>Commands</strong></summary> Define custom commands as shortcuts for repetitive prompts: ```yaml # forge.yaml commands: - name: "refactor" description: "Refactor selected code" prompt: "Please refactor this code to improve readability and performance" ``` </details> <details> <summary><strong>Model</strong></summary> Specify the default AI model to use for all agents in the workflow. ```yaml # forge.yaml model: "claude-3.7-sonnet" ``` </details> <details> <summary><strong>Max Walker Depth</strong></summary> Control how deeply Forge traverses your project directory structure when gathering context. ```yaml # forge.yaml max_walker_depth: 3 # Limit directory traversal to 3 levels deep ``` </details> <details> <summary><strong>Temperature</strong></summary> Adjust the creativity and randomness in AI responses. Lower values (0.0-0.3) produce more focused, deterministic outputs, while higher values (0.7-2.0) generate more diverse and creative results. ```yaml # forge.yaml temperature: 0.7 # Balanced creativity and focus ``` </details> --- <details> <summary><strong>Model Context Protocol (MCP)</strong></summary> The MCP feature allows AI agents to communicate with external tools and services. This implementation follows Anthropic's [Model Context Protocol](https://docs.anthropic.com/en/docs/claude-code/tutorials#set-up-model-context-protocol-mcp) design. ### MCP Configuration Configure MCP servers using the CLI: ```bash # List all MCP servers forge mcp list # Add a new server forge mcp add # Add a server using JSON format forge mcp add-json # Get server details forge mcp get # Remove a server forge mcp remove ``` Or manually create a `.mcp.json` file with the following structure: ```json { "mcp_servers": { "server_name": { "command": "command_to_execute", "args": ["arg1", "arg2"], "env": {"ENV_VAR": "value"} }, "another_server": { "url": "http://localhost:3000/events" } } } ``` MCP configurations are read from two locations (in order of precedence): 1. Local configuration (project-specific) 2. User configuration (user-specific) ### Example Use Cases MCP can be used for various integrations: - Web browser automation - External API interactions - Tool integration - Custom service connections ### Usage in Multi-Agent Workflows MCP tools can be used as part of multi-agent workflows, allowing specialized agents to interact with external systems as part of a collaborative problem-solving approach. </details> --- ## Documentation For comprehensive documentation on all features and capabilities, please visit the [documentation site](https://github.com/antinomyhq/forge/tree/main/docs). --- ## Community Join our vibrant Discord community to connect with other Forge users and contributors, get help with your projects, share ideas, and provide feedback! [](https://discord.gg/kRZBPpkgwq) --- ## 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 🌱 ", Assign "at most 3 tags" to the expected json: {"id":"13878","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"