
AnythingLLM: The all-in-one AI desktop app (MIT, 30k stars)
Combining RAG, multi-model chat, document ingestion, and agent tools in a single Docker container with 30+ LLM providers in one app.
Explore AI engineering, system design, DevOps, and cutting-edge tools reshaping how we build software.
Featured Series
An 18-part engineering deep dive into ChatGPT, Claude, Gemini, Perplexity, DeepSeek, Copilot, Grok, Lovable, Manus, NanoBanana, Leonardo AI, Meta AI, Assembly AI, Canva AI, Veo 3, Sora 2, Kimi, and Kling.
Sorted by newest first

Combining RAG, multi-model chat, document ingestion, and agent tools in a single Docker container with 30+ LLM providers in one app.

Deploying ML models as production APIs with auto-scaling and GPU management — BentoML unifies packaging, serving, and observability in one framework.

Converting complex PDFs, tables, and multi-column layouts into structured Markdown for AI processing — all with a permissive MIT license.

The memory-augmented LLM agent framework — giving LLMs persistent memory with virtual context management and tiered storage.

A memory layer for AI applications providing persistent, self-updating memory for LLMs with entity extraction and retrieval.

The most popular ChatGPT alternative UI — a lightweight, self-hosted chat interface supporting GPT, Claude, Gemini, and local models.

BentoML's LLM serving platform — one-command deployment of any open-source LLM with OpenAI-compatible API.

Adding AI-powered search to your existing Postgres database with no separate infrastructure — a PostgreSQL extension for vector similarity search.

A generative AI knowledge assistant that chats with your documents, images, and databases — your second brain in the cloud.