open-source-ai• 15 min
n8n: A fair-code workflow automation platform (Sustainable License, 52k stars)
A fair-code workflow automation platform connecting 400+ services with AI-powered nodes for intelligent automation.
#n8n#workflow-automation
All Posts
Explore our latest articles and technical deep dives.
open-source-ai• 15 min
Open WebUI: The most popular self-hosted AI chat interface (MIT, 60k stars)
A feature-rich ChatGPT-like UI for Ollama and OpenAI backends with RAG, tools, and multi-user support — the most popular self-hosted AI chat interface.
#open-webui#chat-ui
open-source-ai• 15 min
ChromaDB: The AI-native open-source vector database (Apache 2.0, 17k stars)
The AI-native open-source vector database — built for semantic search, RAG, and embedding storage with a developer-friendly API.
#chromadb#vector-database
open-source-ai• 15 min
LangChain: The most popular LLM application framework (MIT, 100k stars)
The most popular LLM application framework — building RAG pipelines, agent chains, and LLM-powered applications with 700+ integrations.
#langchain#llm-framework
open-source-ai• 15 min
LlamaIndex: The leading data framework for LLM applications (MIT, 38k stars)
The leading data framework for LLM applications — connecting LLMs to your data with advanced indexing, retrieval, and query engines.
#llamaindex#data-framework
open-source-ai• 15 min
Milvus: The most scalable open-source vector database (Apache 2.0, 32k stars)
The most scalable open-source vector database managing trillion-scale vector datasets with GPU-accelerated indexing and hybrid search.
#milvus#vector-database
open-source-ai• 15 min
Qdrant: A high-performance vector search engine (Apache 2.0, 22k stars)
A high-performance vector search engine written in Rust with filtering, quantization, and horizontal scaling for production RAG.
#qdrant#vector-search
open-source-ai• 15 min
Weaviate: An AI-native vector database (BSD-3-Clause, 12k stars)
An AI-native vector database with built-in vectorization modules, hybrid search, and seamless integration with any LLM.
#weaviate#vector-database
open-source-ai• 15 min
ExLlamaV2: The fastest inference engine for quantized Llama/HF models (MIT, 5k stars)
Achieving 140+ tok/s on a single RTX 4090 with 4-bit quantization — the fastest inference engine for quantized Llama/HF models.
#exllamav2#inference