Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.
- ai-coding-agent
- ai-tools
- anthropic-claude
- claude-code
132,241 visible repositories in the index
73–96 of 143 · Most stars
Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.
PDEBench: An Extensive Benchmark for Scientific Machine Learning
A generalized information-seeking agent system with Large Language Models (LLMs).
[ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
Reinforcement Learning via Self-Distillation (SDPO)
[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
LLM-based ontological extraction tools, including SPIRES
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
A version of verl to support diverse tool use [TMLR 2026]
Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.
Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and slow)
Deep reinforcement learning GPU libraries for NVIDIA Jetson TX1/TX2 with PyTorch, OpenAI Gym, and Gazebo robotics simulator.
FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
🧠 Motorhead is a memory and information retrieval server for LLMs.
Late Interaction Models Training & Retrieval
AI molecular design tool for de novo design, scaffold hopping, R-group replacement, linker design and molecule optimization.
cuVS - a library for vector search and clustering on the GPU
Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.
[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training