LiteRT-LM

LiteRT-LM is Google AI Edge's official open-source inference framework for deploying Large Language Models directly on edge devices. Announced and open-sourced in April 2026, LiteRT-LM brings production-grade LLM inference to Android, iOS, Web bro…

RAG-Anything

RAG-Anything is a comprehensive retrieval-augmented generation (RAG) framework developed by HKUDS Lab that eliminates the fragmentation of modern RAG pipelines. Where most RAG systems only handle plain text, RAG-Anything natively processes diverse…

RLM

RLM is a novel inference library from MIT's OASYS Lab that reframes how language models handle long contexts. Instead of stuffing enormous inputs into a single context window, RLM allows a language model to programmatically examine, decompose, and…

DeerFlow

DeerFlow (Deep Research Flow) is ByteDance's ambitious open-source project that pushes the boundaries of autonomous AI agents. Unlike simple single-turn chatbots or shallow automation tools, DeerFlow is built to tackle complex tasks that span minu…

DORA

DORA (Dataflow-Oriented Robotic Architecture) is an open-source middleware framework built in Rust that tackles one of the most persistent challenges in embodied AI and robotics: the performance ceiling of existing frameworks. With measured benchm…

MiniMind

MiniMind is an educational and practical open-source project that delivers something remarkable: a complete, reproducible pipeline for training a GPT-class language model from absolute zero in approximately 2 hours on a single NVIDIA 3090 GPU, at …

Archon

coleam00

The first open-source harness builder that makes AI-assisted coding deterministic, structured, and reproducible.

awesome-llm-apps

Shubhamsaboo

100+ production-ready AI Agent & RAG app templates you can clone, customize, and ship immediately.

llm-d

llm-d

Production-ready distributed LLM inference stack on Kubernetes. Prefix-cache-aware scheduling, disaggregated serving, and SLO-driven autoscaling.

OpenAI Codex CLI

openai

Lightweight AI coding agent that runs in your terminal. Written in Rust, integrates with ChatGPT plans, and supports local code read/write/execution.

PageIndex

VectifyAI

Vectorless, reasoning-based RAG that uses hierarchical document trees instead of embeddings — 98.7% accuracy on FinanceBench.

Unsloth

unslothai

2x faster LLM fine-tuning with 70% less VRAM via custom Triton kernels. Supports Llama, Qwen, DeepSeek, Gemma, and 500+ models.