{"id":25346588,"url":"https://github.com/burnycoder/multiagent-ai-coding","last_synced_at":"2026-05-04T05:35:07.207Z","repository":{"id":276007834,"uuid":"927813169","full_name":"BurnyCoder/multiagent-ai-coding","owner":"BurnyCoder","description":"MultiAgent AI Coding system asking clarifying questions, generating plan, using smolagents AI agents (a code writing agent and code review agent, using LLM providers (o3, Claude, Gemini) by Portkey.ai, Gradio+terminal GUI","archived":false,"fork":false,"pushed_at":"2025-02-11T23:42:36.000Z","size":322,"stargazers_count":1,"open_issues_count":3,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-12T00:28:00.051Z","etag":null,"topics":["agent","agents","ai-agent","ai-agents","large-language-model","large-language-models","llm","llms","multiagent-systems","openrouter","smolagents"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BurnyCoder.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-05T15:32:35.000Z","updated_at":"2025-02-11T23:42:39.000Z","dependencies_parsed_at":"2025-02-12T00:28:01.904Z","dependency_job_id":null,"html_url":"https://github.com/BurnyCoder/multiagent-ai-coding","commit_stats":null,"previous_names":["burnycoder/ai-experiments","burnycoder/multiagent-ai-coding"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BurnyCoder%2Fmultiagent-ai-coding","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BurnyCoder%2Fmultiagent-ai-coding/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BurnyCoder%2Fmultiagent-ai-coding/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BurnyCoder%2Fmultiagent-ai-coding/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BurnyCoder","download_url":"https://codeload.github.com/BurnyCoder/multiagent-ai-coding/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247888567,"owners_count":21013002,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","agents","ai-agent","ai-agents","large-language-model","large-language-models","llm","llms","multiagent-systems","openrouter","smolagents"],"created_at":"2025-02-14T13:39:05.889Z","updated_at":"2026-05-04T05:35:07.157Z","avatar_url":"https://github.com/BurnyCoder.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MultiAgent AI Coding\n\nMultiAgent AI Coding system that first asks clarifying questions about the user's request, generates a detailed implementation plan, then uses specialized AI agents (a code writing agent to implement the solution and a code review agent to validate and improve the code) powered by various LLM providers through Portkey.ai, with support for both terminal and web interfaces.\n\n## Installation\n\n1. Clone the repository:\n```bash\ngit clone \u003crepository-url\u003e\ncd multiagent-ai-coding\n```\n\n2. Create and activate a virtual environment:\n```bash\npython -m venv venv\nsource venv/bin/activate  # On Linux/Mac\n# or\n.\\venv\\Scripts\\activate  # On Windows\n```\n\n3. Install the required dependencies:\n```bash\npip install -r requirements.txt\n```\n\n4. Create a `.env` file and configure the following environment variables. You can use .envtemplate as a template:\n\nAPI keys:\n- `PORTKEY_API_BASE`: Base URL for Portkey API (default: \"https://api.portkey.ai/v1\")\n- `PORTKEY_API_KEY`: Your Portkey API key\n- `PORTKEY_VIRTUAL_KEY_ANTHROPIC`: Virtual key for Anthropic models\n- `PORTKEY_VIRTUAL_KEY_OPENAI`: Virtual key for OpenAI models\n- `PORTKEY_VIRTUAL_KEY_GOOGLE`: Virtual key for Google models\n- `ZEP_API_KEY`: Your Zepp API key\n- `OSMOSIS_API_KEY`: Your Osmosis API key\n\n\nCoding Agent System Prompts:\n- `CODE_WRITING_AGENT_SYSTEM_PROMPT`: System prompt for code writing agent. This should be customized based on your project's needs - for example, whether you want the agent to focus on implementing core functionality quickly or take a more thorough approach with extensive error handling.\n- `CODE_REVIEW_AGENT_SYSTEM_PROMPT`: System prompt for code review agent. The strictness level can be adjusted depending on your goals - from basic functionality verification to comprehensive error detection and optimization suggestions.\n\nCoding Agent Settings:\n- `CODING_AGENT_MODEL`: Model to use for coding (default: \"claude-3-5-sonnet-latest\")\n- `MAX_AGENT_STEPS`: Maximum number of steps for agents (default: 20)\n- `PLANNING_INTERVAL`: Interval at which the agent will run a planning step (default: 3)\n- `USE_O3_PLANNING`: Whether to use planning with O3 model (default: \"true\")\n- `USE_CLARIFYING_QUESTIONS`: Whether to use clarifying questions (default: \"true\")\n- `USE_WEB_SEARCH`: Whether to use web search (default: \"false\")\n- `INCLUDE_CODEBASE_IN_SYSTEM_PROMPT`: Whether to include codebase in system prompt (default: \"true\")\n- `MORE_AUTHORIZED_IMPORTS`: Additional authorized imports (default: \"streamlit,smolagents\")\n\nPath Settings\n- `AI_PLAYGROUND_PATH`: Path for AI playground (default: \"ai_playground/\")\n- `TESTS_PATH`: Path for tests (default: \"tests/tests_multiagent_coding/\")\n\n## Using MultiAgent Coding System\n\n### Setting Up Your Codebase\n\nTo use the MultiAgent Coding System with your own codebase:\n\n1. Create a directory for your project in the `ai_playground` folder:\n```bash\nmkdir ai_playground\n```\n\n2. Place your codebase files in this directory. The MultiAgent Coding System will use this as the working directory for code generation, review, and modifications.\n\n3. When using any of the MultiAgent Coding interfaces, your project in `ai_playground` will be automatically recognized and the agents will work within this context.\n\n## Available Interfaces\n\n### 1. Terminal Interface (memory isn't implemented)\n\nTo run:\n```bash\npython app_terminal.py\n```\n\n### 2. Web Interface (has memory)\nTo run:\n```bash\npython app_gradio.py\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fburnycoder%2Fmultiagent-ai-coding","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fburnycoder%2Fmultiagent-ai-coding","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fburnycoder%2Fmultiagent-ai-coding/lists"}