{"id":49636444,"url":"https://github.com/kushal1302/ai-software-team","last_synced_at":"2026-05-05T15:02:49.831Z","repository":{"id":355442167,"uuid":"1228101933","full_name":"Kushal1302/ai-software-team","owner":"Kushal1302","description":"Autonomous multi-agent AI software engineering runtime built with LangGraph, TypeScript, Hono, and real-time orchestration visualization.","archived":false,"fork":false,"pushed_at":"2026-05-03T16:27:37.000Z","size":202,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-03T17:36:27.327Z","etag":null,"topics":["agentic-ai","ai-agents","ai-engineering","ai-runtime","autonomous-agents","developer-tools","hono","langchain","langgraph","llm","multi-agent","nextjs","reactflow","sse","streaming","tool-calling","typescript"],"latest_commit_sha":null,"homepage":"https://ai-software-team.vercel.app/","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Kushal1302.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-03T15:44:44.000Z","updated_at":"2026-05-03T16:29:58.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Kushal1302/ai-software-team","commit_stats":null,"previous_names":["kushal1302/ai-software-team"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Kushal1302/ai-software-team","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kushal1302%2Fai-software-team","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kushal1302%2Fai-software-team/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kushal1302%2Fai-software-team/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kushal1302%2Fai-software-team/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Kushal1302","download_url":"https://codeload.github.com/Kushal1302/ai-software-team/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kushal1302%2Fai-software-team/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32654618,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-05T11:29:49.557Z","status":"ssl_error","status_checked_at":"2026-05-05T11:29:48.587Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["agentic-ai","ai-agents","ai-engineering","ai-runtime","autonomous-agents","developer-tools","hono","langchain","langgraph","llm","multi-agent","nextjs","reactflow","sse","streaming","tool-calling","typescript"],"created_at":"2026-05-05T15:02:45.470Z","updated_at":"2026-05-05T15:02:49.826Z","avatar_url":"https://github.com/Kushal1302.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI Software Team \n\nAn autonomous multi-agent AI software engineering runtime built with LangGraph, TypeScript, Hono, ReactFlow, and real-time orchestration visualization.\n\nThis project simulates a real AI engineering organization where specialized agents collaborate to analyze repositories, retrieve code context, modify implementations, validate changes, and stream runtime activity live to the UI.\n\n---\n\n# Features\n\n## Multi-Agent Architecture\n\nSpecialized AI agents collaborate together:\n\n- Intent Classifier\n- Strategic Planner\n- Repository Searcher\n- Task Classifier\n- Backend Engineer\n- Frontend Engineer\n- Reviewer\n- Validator\n- Change Summary Agent\n- Answer Agent\n\n---\n\n## Engineering Memory System\n\nPersistent semantic memory powered by vector embeddings.\n\nThe system learns:\n\n- repository architecture\n- implementation locations\n- framework conventions\n- recurring validation failures\n- engineering patterns\n\nMemory retrieval is semantic and reusable across executions.\n\n---\n\n## Real-Time Runtime Streaming\n\nLive runtime observability using:\n\n- Server-Sent Events (SSE)\n- Event-driven architecture\n- Streaming terminal logs\n- Streaming tool execution\n- Live workflow updates\n\n---\n\n## Dynamic Workflow Visualization\n\nInteractive runtime graph visualization using ReactFlow.\n\nFeatures:\n\n- active agent highlighting\n- real-time execution tracking\n- dynamic graph rendering\n- orchestration visibility\n\n---\n\n## Tool Calling System\n\nAgents can safely use specialized tools:\n\n### Repository Intelligence Tools\n\n- search_code\n- read_file\n- grep/search_text\n\n### Engineering Tools\n\n- patch_file\n- git_diff\n- run_terminal\n\n### Validation Tools\n\n- npm run build\n- npm run typecheck\n- lint/test execution\n\n---\n\n## Human Approval Gates\n\nDangerous operations require human approval.\n\nExamples:\n\n- rm commands\n- git push\n- migrations\n- docker operations\n\nThe runtime pauses until user approval is provided.\n\n---\n\n## LangGraph Orchestration\n\nBuilt on top of LangGraph StateGraph.\n\nFeatures:\n\n- conditional routing\n- autonomous loops\n- checkpointing\n- agent handoffs\n- dynamic execution flows\n\n---\n\n# Architecture\n\n## Runtime Flow\n\n```text\nUser Task\n   ↓\nIntent Classifier\n   ↓\nPlanner\n   ↓\nSearcher\n   ↓\nTask Classifier\n   ↓\nFrontend / Backend Engineer\n   ↓\nReviewer\n   ↓\nValidator\n   ↓\nChange Summary\n```\n\n---\n\n## Graph Architecture\n\n```text\nSTART\n  ↓\nintent-classifier\n  ↓\nplanner\n  ↓\nsearcher\n  ↓\nclassifier\n  ├── backend-engineer\n  └── frontend-engineer\n          ↓\nreviewer\n  ↓\nvalidator\n  ↓\nchange-summary\n  ↓\nEND\n```\n\n---\n\n# Memory Architecture\n\n```text\nExecution\n   ↓\nMemory Extraction\n   ↓\nEmbedding Generation\n   ↓\nVector Storage\n   ↓\nSemantic Retrieval\n   ↓\nMemory Injection\n```\n\nThe system continuously learns from previous executions.\n\n---\n\n# Tech Stack\n\n## Backend\n\n- TypeScript\n- LangGraph\n- LangChain\n- Hono\n- Node.js\n\n## Frontend\n\n- Next.js\n- React\n- Tailwind CSS\n- ReactFlow\n\n## AI / Runtime\n\n- Gemini\n- Tool Calling\n- Event Streaming\n- Multi-Agent Orchestration\n\n## Memory\n\n- ChromaDB\n- Vector Embeddings\n\n---\n\n# Runtime Events\n\nThe runtime streams events in real-time:\n\n```ts\ntype RuntimeEvent =\n  | \"agent\"\n  | \"tool\"\n  | \"terminal\"\n  | \"diff\"\n  | \"approval\"\n  | \"log\";\n```\n\nThese events power:\n\n- live logs\n- graph visualization\n- terminal streaming\n- diff viewer\n- approval modals\n\n---\n\n# Agent Routing\n\nThe system uses conditional routing extensively.\n\nExample:\n\n```ts\n.addConditionalEdges(\n  \"classifier\",\n  taskRouter\n)\n```\n\nRouting decisions are dynamically determined by agent reasoning and runtime state.\n\n---\n\n# Project Structure\n\n```bash\nsrc/\n├── agents/\n├── graph/\n├── tools/\n├── events/\n├── runtime/\n├── memory/\n├── prompts/\n├── server.ts\n└── index.ts\n\nweb/\n├── /app\n├── /components\n├── /lib\n└── /types\n```\n\n---\n\n# Getting Started\n\n## Install Dependencies\n\n```bash\nnpm install\n```\n\n---\n\n## Run ChromaDB\n\n```bash\ndocker run -p 8000:8000 chromadb/chroma\n```\n\n---\n\n## Start Backend\n\n```bash\nnpm run dev\n```\n\n---\n\n## Start Frontend\n\n```bash\ncd web\nnpm install\nnpm run dev\n```\n\n---\n\n# Example Tasks\n\n```text\nAdd auth request logging\n\nFix Prisma validation issue\n\nImplement dark mode toggle\n\nAdd Redis caching layer\n\nRefactor middleware architecture\n```\n\n---\n\n# Goals\n\nThis project explores:\n\n- autonomous software engineering\n- AI orchestration systems\n- multi-agent collaboration\n- repository intelligence\n- durable AI runtimes\n- real-time AI observability\n- semantic engineering memory\n\n---\n\n# Future Improvements\n\n- LangGraph Interrupts\n- Durable Workflow Resumption\n- Playwright Browser Agent\n- AST-safe Code Editing\n- Multi-Repository Intelligence\n- Distributed Worker Runtime\n- Monaco Diff Visualization\n- Kubernetes Runtime Workers\n- Autonomous PR Generation\n\n---\n\n# Key Concepts Explored\n\n- Multi-Agent Systems\n- Tool Calling\n- Semantic Memory\n- Runtime Streaming\n- Event-Driven Architecture\n- Autonomous Loops\n- Human-in-the-loop AI\n- Vector Retrieval\n- Repository Intelligence\n- AI Workflow Orchestration\n\n---\n\n# Disclaimer\n\nThis project is experimental and designed for learning advanced agentic AI system architecture.\n\nAlways review AI-generated code before production usage.\n\n---\n\n# If you like this project\n\nStar the repository and explore autonomous AI engineering systems ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkushal1302%2Fai-software-team","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkushal1302%2Fai-software-team","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkushal1302%2Fai-software-team/lists"}