Stars
Open-source AI agent for web automation and scraping.
Markdown text to a novel in ePub and PDF.
Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Codex, OpenClaw, Hermes, and more
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
Knowledge Graph-Guided Retrieval Augmented Generation, NAACL 2025
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…
Implementation of ICML-2025 paper "Peripheral Memory for LLMs: Integration of Sequential Memory Banks with Adaptive Querying".
The code for NeurIPS 2025 paper "A-Mem: Agentic Memory for LLM Agents"
A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!
A Collection of BM25 Algorithms in Python
[EMNLP 2024] CompAct: Compressing Retrieved Documents Actively for Question Answering
mlciv / ai-deadlines
Forked from paperswithcode/ai-deadlines⏰ AI conference deadline countdowns
Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch
The official repository for "Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation", Shengyao Zhuang, Houxing Ren, Linjun Shou, Jian Pei, Ming Gong, …
A huggingface transformers implementation of "Transformer Memory as a Differentiable Search Index"
[ICCV 2025] PVChat: Personalized Video Chat with One-Shot Learning
repo for paper https://arxiv.org/abs/2504.13837
State-of-the-art 2D and 3D Face Analysis Project
Kimi K2 is the large language model series developed by Moonshot AI team
BoT-SORT: Robust Associations Multi-Pedestrian Tracking
Simple Online Realtime Tracking with a Deep Association Metric
Detection, tracking and re-identification of people in a surveillance video to make a list of people that appeared in the video. If people leave the frame and re-appear later in the video, the mode…
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
A high-throughput and memory-efficient inference and serving engine for LLMs
[CVPR 2025] EgoLife: Towards Egocentric Life Assistant