Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
Repository Index
132,241 visible repositories in the index
121–144 of 144 · Most stars
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
Generative Representational Instruction Tuning
- embeddings
- grit
- information-retrieval
- instruction-tuning
ns3-gym - The Playground for Reinforcement Learning in Networking Research
- ns3
- gym-environment
- openai-gym
- reinforcement-learning
AI-first Search & Answer Engine for work. Open-source alternative to Glean.
- enterprise-search
- gen-ai
- rag
- typescript
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
SkyChat是一款基于中文GPT-3 api的聊天机器人项目。它可以像chatGPT一样,实现人机聊天、问答、中英文互译、对对联、写古诗等任务。| SkyChat is a Chatbot project based on Chinese GPT3 API. Like chatGPT, it can do human-machine chat, question and answer, and can also complete tasks such as Chinese-English or English-Chinese translation, content continuation, couplets, and Chinese ancient poems writing.
- aigc
- language-model
- natural-language-generation
- natural-language-processing
BioMCP: Biomedical Model Context Protocol
- ai
- bioinformatics
- clinical-trials
- genomics
ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
- alignment
- dpo
- llm
- llm-aligment
RAG based tool for indexing and searching PDF text data using OpenAI API and FAISS (Facebook AI Similarity Search) index, designed for rapid information retrieval and superior search accuracy.
Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]
- chatgpt
- information-retrieval
- large-language-models
- reranking
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
- agent-rl
- entropy-method
- llm-agent
- llm-reasoning
Memento is a Python app that records everything you do on your computer and lets you go back in time, search, and chat with a LLM (Large Language Model) to find back information about what you did.
- llms
- productivity
- pygame
- python
Cell type annotation for single-cell RNA-seq using multi-LLM consensus
- bioinformatics
- cell-type-annotation
- consensus-algorithm
- large-language-models
Latest Advances on Long Chain-of-Thought Reasoning
- agent
- chain-of-thought
- deepseek-r1
- long
Summary of deep learning models for dialog systems (Tiancheng Zhao LTI, CMU)
Dataset and benchmark for RAG on company internal documents.
A collection of multi agent environments based on OpenAI gym.
- gym
- multi-agent
- openai-gym
- reinforcement-learning
Implementation of the Deep Deterministic Policy Gradient (DDPG) using PyTorch
- pytorch
- ddpg
- deep-reinforcement-learning
- openai-gym
Span-level grounding verification for RAG, code, and tool-grounded AI outputs.
- bert
- hallucination-detection
- hallucination-evaluation
- information-extraction
Toolkits for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
- meta-learning
- reinforcement-learning
- rsi
- ai-agents
TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".
- game-ai
- hearthstone
- reinforcement-learning
- rust
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.