🔥 The Web Data API for AI - Power AI agents with clean web data

We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference…

Papers, repository and other data about anime or manga research. Please let me know if you have information that the list does not include.

🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.

💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

CL-bench: A Benchmark for Context Learning

Elevate your AI research writing, no more tedious polishing ✨

verl: Volcano Engine Reinforcement Learning for LLMs

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

Recursive Language Models for unbounded context processing. Process 100k+ tokens with any LLM by storing context as variables instead of prompts.

Light Image Video Generation Inference Framework

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

repo for paper https://arxiv.org/abs/2504.13837

Contexts Optical Compression

A simple yet powerful agent framework that delivers with open-source models

The best ChatGPT that $100 can buy.

Agent S: an open agentic framework that uses computers like a human

Train your Agent model via our easy and efficient framework

The absolute trainer to light up AI agents.

A Neural Symbolic Model for Space Physics

Text-audio foundation model from Boson AI

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

学术双语简历模板，涵盖教育背景、论文发表、项目经历、竞赛经历和个人陈述等关键部分，可适用于申请研究生项目、学术职位或相关行业岗位。

Offline, privacy-first grammar checker. Fast, open-source, Rust-powered

🐧 Linux 上完整的 Clash / Mihomo (Clash Meta) 管理工具