65,264 visible repositories in the index
1–24 of 32 · Most stars
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Gel supercharges Postgres with a modern data model, graph queries, Auth & AI solutions, and much more.
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
A new kind of Progress Bar, with real-time throughput, ETA, and very cool animations!
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Align Anything: Training All-modality Model with Feedback
Fast Python Collaborative Filtering for Implicit Feedback Datasets
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.
Barman - Backup and Recovery Manager for PostgreSQL
Tookie is a advanced OSINT information gathering tool that finds social media accounts based on inputs.
Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
pickleDB is an in memory key-value store using Python's orjson module for persistence. It can also use SQLite instead of orjson if needed.
Code for the USENIX 2017 paper: kAFL: Hardware-Assisted Feedback Fuzzing for OS Kernels
Studio-grade sound effects for agents: search Pixabay, Freesound, Mixkit and Kenney, ranked by human feedback
Open-source embodied agent framework: execution, feedback, and continual improvement
TranslatedCurated agent skills for social media: Xiaohongshu (RedNote), Douyin, WeChat, X, YouTube, TikTok and LinkedIn. Also covers self-media operations, including WeChat Official Accounts, WeChat Channels and Bilibili: topic selection, writing, images, publishing and data. Usable by agents such as 千问 (Qianwen, "Thousand Questions"), 豆包 (Doubao, "bun"), 龙虾 (Longxia, "lobster") OpenClaw, WorkBuddy, Claude Code and Codex.
The goal of pandas-log is to provide feedback about basic pandas operations. It provides simple wrapper functions for the most common functions that add additional logs
Open Source Threat Intelligence Platform
LLM for Drug Editing, ICLR 2024
An auditable, reversible, evaluable local agent runtime that turns feedback into skills — and ships them only when evidence and tests say so.
TypeDB Bio: Biomedical Knowledge Graph