Project category
AI / LLM App tech stacks
LLM apps, agents, RAG, inference engines, and AI orchestration. 17 production examples.
Production AI / LLM App projects
- Desktop & Web AI Agent Workspace AI-agent MindsHub (formerly MindsDB) Splitting the client, API and agent into separately versioned git submodules lets each ship on its own cadence (a signed desktop app, a PyPI server package, an agent package), while one Makefile and one docker-compose.yml still bring the whole stack up together.
- Local LLM Inference Engine & Hardware Profiler Hybrid Magnitude Performance-critical inference sits in a Rust workspace around vendored llama.cpp, while the app, CLI, agent and model management live in a Bun + Effect TypeScript monorepo. The native engine can be pinned and benchmarked on its own while the product layer changes quickly.
- Multi-Agent Interactive AI Classroom Classic OpenMAIC Built as a Next.js app around a set of npm-published packages (slide DSL, generation, renderer, editor, importer, storage). The multi-agent LangGraph pipeline, the slide format and persistence can each be reused or swapped, and heavy video rendering runs in a separate container.
- Local AI Voice Cloning & Speech Studio Hybrid VoiceStudio Heavy model work stays in a Python FastAPI backend with a pluggable, hardware-aware engine registry. Desktop, web, MCP and remote-worker clients all use the same local API, so voice models run on the user's own GPU without a cloud dependency.
- LLM Knowledge Base & RAG Platform Classic WeKnora Retrieval, agents and the API sit in one Go service, and parsing is delegated to a Python gRPC service. Storage backends are pluggable, so the same codebase runs as a lite SQLite binary or a full Kubernetes deployment on existing Postgres, Elasticsearch or vector databases.
- High-Throughput LLM Inference & Serving Engine AI-agent vLLM vLLM solves GPU memory fragmentation in large language model serving, delivering state-of-the-art throughput on commodity and enterprise hardware.
- LLM Application Framework & Agent Orchestrator AI-agent LangChain The current langchain package is a thin agent-building layer on top of LangGraph, with the older chain-based API kept separately as langchain-classic, and every model provider ships as its own versioned package so integrations can release independently of the core library.
- Multi-Model AI Agent & Chat Workspace Hybrid LibreChat A Node/Express API with a Mongoose-modeled MongoDB store handles chat state, while Vite builds the React client separately; optional Docker sidecars for pgvector, Meilisearch, and a Go OpenTelemetry relay keep RAG, search, and observability decoupled from the core API.
- Vector Similarity Search Engine Classic Qdrant Authoring the engine from scratch in Rust provides zero-overhead memory safety, hardware SIMD vectorization, and lock-free concurrency for large-scale similarity search.
- AI Copilot & Assistant SDK AI-agent CopilotKit A shared AG-UI protocol plus a PlatformAdapter-based channel architecture let one agent implementation power web, mobile and chat-platform surfaces from a single Nx/pnpm monorepo instead of building a separate integration per surface.
- Self-Hosted AI Interface & Agent Hub AI-agent Open WebUI A SvelteKit-plus-FastAPI split lets one Docker image serve the UI and API together, while SQLAlchemy over SQLite or PostgreSQL and a swappable vector-store layer let self-hosters scale from a laptop to a multi-worker Redis-backed deployment without changing code.
- AI Memory & Context Engine AI-agent Mem0 Keeping the core library provider-agnostic through optional dependency groups, while the hosted server bundles a fixed set of vector stores, LLM providers, auth, and rate limiting behind its own FastAPI app, lets self-hosters install a minimal footprint without forking the managed-service code path.
- LLM Workflow & Orchestration UI AI-agent Flowise A Turborepo monorepo lets the ReactFlow-based visual editor, the TypeORM-backed API server, and the LangChain.js node library ship and version independently, with an optional BullMQ worker tier for scaling flow execution.
- AI Application Framework Hybrid Taipy Taipy enables Python data scientists to build full-stack web applications and data DAG pipelines using pure Python bindings.
- Local AI Inference Engine AI-agent Ollama Inference performance depends on the accelerator, so the C++ llama.cpp server is built as separate CPU, CUDA, ROCm, and Vulkan variants, with native Go code choosing the right one at runtime, while an independent MLX runner handles Apple Silicon instead of one shared code path.
- LLM Observability AI-agent Langfuse Storage is split by workload: Postgres via Prisma for relational app state, ClickHouse for high-volume trace analytics, and Redis-backed BullMQ for async jobs, while a separate Rust Axum service handles latency-sensitive LLM proxying outside the Node runtime.
- LLM App Builder AI-agent Dify.ai Agent execution and vector retrieval are split into separate, independently scalable services (a Go sandbox runtime, a FastAPI agent orchestrator, and pluggable vector-store providers) so untrusted tool code and swappable retrieval backends stay out of the core Flask API process.
AGENTS.md rules and agent skills for AI / LLM App
fastapi-jev-decision-service/AGENTS.mdFastAPI + Jev Decision Service (Python)Python rules for a Jev decision service: FastAPI, the async typesafe-sdk client, a typed question registry, confidence thresholds, decision logs and replay tests. intermediatefastapi-python-postgres/AGENTS.mdFastAPI + Python + PostgreSQL (Async SQLAlchemy & Pydantic v2)Production guidelines for FastAPI, Pydantic v2 validation, Async SQLAlchemy 2.0 (asyncpg), Alembic migrations, and PostgreSQL/Redis. intermediatejev-browser-agent/AGENTS.mdJev Browser Agent (Playwright + TypeSafe System One)Rules for a browser agent where Jev picks the action and target from an indexed element table, Noul checks goal and stuck, and a small LLM types only text. advancedlanggraph-python-fastapi/AGENTS.mdLangGraph + Python + FastAPI (Agentic AI Workflows)Production architecture for autonomous multi-agent systems, LangGraph cyclic state graphs, Pydantic v2 structured tool calling, and Chroma/Qdrant vector stores. advancednextjs-ai-sdk-jev/AGENTS.mdNext.js + Vercel AI SDK + Jev (System One + LLM)Next.js rules for Jev: typed TypeSafe decisions route, classify and gate on the server, the Vercel AI SDK streams LLM text, and confidence decides what runs. intermediatenode-express-mongodb/AGENTS.mdNode.js + Express + MongoDBProduction guidelines for Express REST APIs, Mongoose schema design, and MongoDB indexing/transaction discipline. intermediate
Questions about AI / LLM App stacks
How many AI / LLM App tech stacks are in the directory?
17 verified production AI / LLM App projects are currently indexed, each with a full architecture breakdown and copy-paste AI scaffolding prompt.
What AGENTS.md rules or agent skills apply to AI / LLM App projects?
FastAPI + Jev Decision Service (Python), FastAPI + Python + PostgreSQL (Async SQLAlchemy & Pydantic v2), Jev Browser Agent (Playwright + TypeSafe System One), LangGraph + Python + FastAPI (Agentic AI Workflows), Next.js + Vercel AI SDK + Jev (System One + LLM), Node.js + Express + MongoDB are battle-tested architecture rules for this category, each with a full AGENTS.md, CLAUDE.md, Cursor .mdc file and a Claude Code SKILL.md.
How do I get a custom stack recommendation for a AI / LLM App project?
Take the STACK IT FAST architecture survey and select "AI / LLM App" as your project type to get a ranked rule recommendation and an instant AI scaffolding prompt tailored to a "AI / LLM App" project.