Stars
A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android
On-device AI across mobile, embedded and edge for PyTorch
⚡ Extremely fast online playground for every programming language.
Fetch an entire site and save it as a text file (to be used with AI models).
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Official inference framework for 1-bit LLMs
Devon: An open-source pair programmer
Embeddable stream processing engine based on Apache DataFusion
Issue API keys for your Supabase app with one line of SQL
Open source alternative to Auth0 / Firebase Auth / AWS Cognito
AdalFlow: The library to build & auto-optimize LLM applications.
Browser extension for AnythingLLM Docker & Desktop application
CloudFormation template that runs a 7 Days to Die server with idle shutdown, start/stop access control and static IP
A modular graph-based Retrieval-Augmented Generation (RAG) system
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Dropbase helps developers build and prototype web apps faster with AI. Dropbase is local-first and self hosted.
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x fast 5461 er random access, vector index, and data versioning. Compatible with Pandas, Du…
create custom test databases that are populated with fake data
A natural language interface for computers
Documentation of AnythingLLM by Mintplex Labs Inc.
🦜🔗 Build context-aware reasoning applications 🦜🔗