Explore live open-source projects and AI models.

A curated collection of awesome AI Agents and LLM Apps built with multiple tech stacks, showcasing real-world implementations using OpenAI, Gemini, local models, and various AI frameworks.

Portable multi-agent AI developer setup for Claude Code + Ollama. Role-based local LLM orchestration via Bash — plan, code, review, commit. Zero Dependency. Works with any language stack.

Free Local-first Full-Stack AI App Builder & Automation — Build, Test & Deploy with LLMs - Antigravity, Lovable, Bolt opensource Alternative ✨ 🌟 Star if you like it!

Self-hosted voice-assistant stack for the M5Stack StackChan desktop robot — local ASR/TTS, pluggable LLM brain, kid-mode default, no cloud required.

Full-stack vibe coding platform with model freedom. Any LLM, local or cloud, zero lock-in.

Local LLM stack with open-source components and documented the installation and configuration steps.

Full stack observability for local AI agent development. Provides a llm-proxy to use as LLM provider base URL, logs traces to opik.

Local RAG + offline LLM demo with Streamlit chat UI, FAISS vector DB, and LoRA tuning/merge utilities — fully powered by Ollama models running locally. Tech Stack: Python 3.11+ · Streamlit · FAISS · Ollama (local LLM + embeddings) · nomic-embed-text · qwen2.5-instruct · PDF ingestion + chunking ... Read more

ClaraN — Privacy-first, fully local AI workspace with Ollama LLM chat, tool calling, agent builder, Stable Diffusion, and embedded n8n-style automation. Backend in Rust. Just your stack, your machines.

A Docker Compose setup for running a local AI and LLM environment with multiple services including AnythingLLM, Flowise, Open WebUI, n8n, and Qdrant.