langgenius/dify
Dify is an open-source platform for developing and deploying AI applications using large language models, featuring workflow building, model management, agent capabilities, and observability tools.
Awesome AI Agents › AI Application Development
vstorm-co/full-stack-fastapi-nextjs-llm-template
This project is a command-line and web-based generator that scaffolds a full-stack AI agent application rather than a single library. It is installed from PyPI as fastapi-fullstack through pip, uv or pipx, and a wizard asks configuration questions and writes out a new project; a browser-based configurator is also offered for producing the same result as a downloadable archive. The generated backend is FastAPI with PostgreSQL, Alembic migrations, Celery, JWT and OAuth authentication, an admin panel, and Docker and Kubernetes manifests; a bootstrap make target builds the backend image, starts the stack from a development compose file, waits for PostgreSQL, applies migrations and seeds a default administrator account. The frontend is Next.js 15 with a real-time chat interface fed by WebSocket streaming, and it displays a live plan and task checklist while the agent works. The agent layer is pluggable across five frameworks: PydanticAI, PydanticDeep, LangChain, LangGraph and DeepAgents, with the deepagents option backed by the separate pydantic-deepagents runtime. A retrieval-augmented generation pipeline is included and can be pointed at Milvus, Qdrant, pgvector or ChromaDB. Conversations can be shared directly, exposed through public links, or browsed by an administrator. The README also documents observability, a Django-style command line interface for the generated project, the generated directory layout, configuration options and a comparison section. The template belongs to a wider open-source ecosystem from the same authors covering guardrails for Pydantic AI agents, declarative multi-agent orchestration with token tracking, context compression for long-running agents, and sandboxed execution backed by Docker and Daytona. It targets teams that want a starting point for an agent-backed web product instead of assembling the infrastructure themselves.
https://github.com/vstorm-co/full-stack-fastapi-nextjs-llm-template
Also in AI Application Development
daytonaio/daytona
Daytona is a secure and elastic infrastructure platform designed for safely running AI-generated code with high performance and scalability.
e2b-dev/awesome-ai-agents
A curated and comprehensive list of AI autonomous agents categorized into open-source and closed-source projects, serving as a valuable resource for exploring, building, and contributing to AI agent development.
mlflow/mlflow
MLflow is an open-source platform that manages the full machine learning lifecycle, providing tools for experiment tracking, model packaging, deployment, evaluation, and observability in one integrated solution.
pydantic/pydantic-ai
PydanticAI is a Python agent framework that simplifies building production-grade Generative AI applications by providing type-safe, structured, and model-agnostic integration with multiple LLMs, along with features like dependency injection and real-time debugging.
GoogleCloudPlatform/generative-ai
A comprehensive repository of sample code, notebooks, and resources for developing and managing generative AI workflows on Google Cloud using Gemini models on Vertex AI.
0xPlaygrounds/rig
Rig is a Rust library for building scalable, modular, and ergonomic fullstack agents powered by large language models, supporting multiple LLM providers and vector stores for AI integration.
mnfst/manifest
Manifest is an open-source components library built on shadcn/ui for creating customizable and production-ready UI components to develop ChatGPT and conversational AI applications efficiently.