Stars
High-Performance Engine for Multi-Vector Search
A vector index built on TurboQuant, written in Rust with Python bindings
Codes and data for paper: GrepSeek: Training Search Agents for Direct Corpus Interaction
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent (ACL 2026 Main)
GenRec: Generative Recommender Systems with RQ-VAE semantic IDs, Transformer-based retrieval, and LLM integration. Built on PyTorch with distributed training support.
Implementations for "Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation"
Data and code for ACL 2026 Paper "Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems"
[ACL 2026 main] DGPO: Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
The code implementation for our KDD 2026 paper "How Well Does Generative Recommendation Generalize?"
GRID: Generative Recommendation with Semantic IDs
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
An Open Foundation Model and Benchmark to Accelerate Generative Recommendation
This is the source code for Efficient Sequential Recommendation for Long Term User Interest Via Personalization.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Repo for paper "Agentic-R: Learning to Retrieve for Agentic Search" (ACL 2026 Findings)
A curated list of papers and resources based on the survey "Agentic Reasoning for Large Language Models"
A repository of OpenDecoder framework: Open Large Language Model Decoding to Incorporate Document Quality in RAG (WWW 2026)
(ICLR'26 + Netflix) Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
[NeurIPS 2025] RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
This repository helps you evaluate your models on the FreshStack benchmark!
A blazing fast inference solution for text embeddings models
Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.
Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-head Decoding
LATTICE turns retrieval into an LLM-driven navigation problem over a semantic scaffold
Official repository for "Conflict-Aware Soft Prompting for Retrieval-Augmented Generation" (EMNLP 2025)
This is the official code for the EMNLP findings 2025 paper "Enhancing Time Awareness in Generative Recommendation".