Stars
LLM-powered MCP server for building financial deep-research agents, integrating web search, Crawl4AI scraping, and entity extraction into composable analysis flows.
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
AgentEvolver: Towards Efficient Self-Evolving Agent System
FlowLLM: Simplifying LLM-based HTTP/MCP Service Development
The missing star history graph of GitHub repos - https://star-history.com
[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
AgentScope: Agent-Oriented Programming for Building LLM Applications
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
EvaLearn is a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks.
verl: Volcano Engine Reinforcement Learning for LLMs
程序员延寿指南 | A programmer's guide to live longer
Official Repo for Open-Reasoner-Zero
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓
All codes for our ACL2024 accepted paper "DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms"
Retrieval and Retrieval-augmented LLMs
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
An easy-to-use Python framework to generate adversarial jailbreak prompts.
All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
DeepSeek Coder: Let the Code Write Itself
Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]
Reference implementation for DPO (Direct Preference Optimization)