Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics
- agent-rl
- agentic-ai
- llm-agents
- reinforcement-learning
142,273 visible repositories in the index
457–480 of 1,943 · Most stars
Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics
Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"
A Unified Library for Parameter-Efficient and Modular Transfer Learning
中文langchain项目|小必应,Q.Talk,强聊,QiangTalk
Convert HTML to Markdown-formatted text.
Concatenate a directory full of files into a single prompt for use with LLMs
The repository host gives no description.
Claude Code to OpenAI API Proxy
An Open-source Toolkit for LLM Development
OpenAI Privacy Filter
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等
dLLM: Simple Diffusion Language Modeling
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
从零构建大模型:从预训练到RLHF的完整实践
streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.
A benchmark for LLMs on complicated tasks in the terminal
A benchmark for evaluating LLMs on Chinese traditional fortune telling — Bazi (八字) and Ziwei Doushu (紫微斗数).
CodeGeeX4-ALL-9B, a versatile model for all AI software development scenarios, including code completion, code interpreter, web search, function calling, repository-level Q&A and much more.
Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.