14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
- ai-agent-tools
- context-compression
- context-pruning
- context-window-optimization
100,822 visible repositories in the index
145–168 of 299 · Most stars
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
Minimal reproduction of OneRec
Supercharged experience for multiple models such as ChatGPT, DALL-E and Stable Diffusion.
Nomic Developer API SDK
Netease Youdao's open-source embedding and reranker models for RAG products.
Unified, efficient, and easy-to-use inference infrastructure for edge AI || 面向端侧 AI 的统一、高效、易用的推理基础设施
WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
Synthetic data curation for post-training and structured data extraction
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
Chat2API enables zero-cost access to leading AI models by leveraging official web UIs. It supports providers such as DeepSeek, GLM, Kimi, MiniMax, Qwen, and Z.ai, and seamlessly integrates with tools like openlcaw, Cline, and Roo-Code.
Optimized Agentic and LLM Bulk Processing Over Your Data
Private and secure AI tools for everyone's productivity.
A very simple GRPO implement for reproducing r1-like LLM thinking.
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration
High-performance retrieval engine for unstructured data
Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.
KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델 (KoAlpaca: An open-source language model to understand Korean instructions)
Get up and running with GLM-5.3-flash, DeepSeek, Gemma and other open source frontier models.
The open document intelligence platform for builders and hackers - DMS for the agentic world