This is your work, valued
rebiber. A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
★ 3kLLM-Blender. [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
★ 987lstm_sentence_classifier. LSTM-based Models for Sentence Classification in PyTorch
★ 78awesome-commonsense. [Work in progress] A reading list for machine commonsense reasoning
★ 34OpenCSR. Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)
★ 32CDMA-NER. Python
★ 28ParaGEN. Neural Paraphrase Generation based on OpenNMT-py
★ 12shanbayAddWords. A python program to add words in batch For Shanbay.com
★ 12easy-align. A tutorial for aligning language models
★ 6EE208-Intro2EE. Python
★ 5dictNER. a simple dictionary-based method to show the difficulty of a NER dataset
★ 5RossetaSeg. A HMM-based Chinese word segmentation system in Python
★ 4CS222-Homework. Homework of CS222 Algorithm Design @ SJTU
★ 3entity-recognition-datasets. A collection of corpora for named entity recognition (NER) and entity recognition tasks. These annotated datasets cover a variety of languages, domains and entity types.
★ 3sequence_tagging. Sequence Tagging and Named Entity Recognition with Tensorflow (LSTM + CRF)
★ 3Awesome-LLM-Synthetic-Data. A reading list on LLM based Synthetic Data Generation 🔥
★ 3petals. 🌸 Run 100B+ language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
★ 2parse_seq2seq. A tensorflow implementation of neural sequence-to-sequence parser for converting natural language queries to logical form.
★ 1spaCy. 💫 Industrial-strength Natural Language Processing (NLP) with Python and Cython
★ 1MusicSpotlight. A search engine for great music
★ 1pytorch_lstmcrf. Pytorch implementation of LSTM-CRF for named entity recognition
★ 1rank_outputs. Python
★ 1CSrankings. A web app for ranking computer science departments according to their research output in selective venues.
★ 1knowledge-graph-embeddings. Implementations of Embedding-based methods for Knowledge Base Completion tasks
★ 1aclpubcheck. Tools for checking ACL paper submissions
★ 1BERT-related-papers. BERT-related papers
★ 1rcnn-relation-extraction. Tensorflow Implementation of Recurrent Convolutional Neural Network for Relation Extraction
★ 1TextAttack. A Python framework for building adversarial attacks on NLP models
★ 1autolab. A benchmark for evaluating AI agents on frontier ultra long-horizon auto research tasks.
★ 152ARC-AGI-3-Agents. Python
★ 172type4me. MacOS语音输入法,实时识别、大模型文本优化、全本地存储
★ 1.3knanoclaw. A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
★ 30kvscode-dark-islands. VSCode theme based off the easemate IDE and Jetbrains islands theme
★ 8.6knofx. Your AI trading terminal assistant for US stocks, commodities, forex, and crypto.
★ 13kOpenCut. The open-source CapCut alternative
★ 62kvaluecell. ValueCell is a community-driven, multi-agent platform for financial applications.
★ 11kn8n. Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
★ 196kxiaohongshu-mcp. MCP for xiaohongshu.com
★ 15kLoCoBench. Python
★ 46IMO25. An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.
★ 936dyad. Local, open-source AI app builder for power users ✨ v0 / Lovable / Replit / Bolt alternative 🌟 Star if you like it!
★ 21knanobrowser. Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
★ 13kubuntu-dind. A docker image based in ubuntu to run docker containers inside docker containers
★ 272claude-code-router. Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
★ 36kclaude-code-proxy. Claude Code to OpenAI API Proxy
★ 2.7kMCP-Universe. MCP-Universe is a comprehensive framework designed for RL training, benchmarking, and developing AI agents for general tool-use.
★ 593KernelBench. KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
★ 1.1kopencode. The open source coding agent.
★ 185kgemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.
★ 106kcomputer_use_ootb. Out-of-the-box (OOTB) GUI Agent for Windows and macOS
★ 2kOpen-Interface. Control Any Computer Using LLMs.
★ 2.7kopen-computer-use. AI computer use powered by open source LLMs and E2B Desktop Sandbox
★ 2.1kROLL. An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
★ 3.3kcline. Autonomous coding agent as an SDK, IDE extension, or CLI assistant.
★ 65kterminal-bench. A benchmark for LLMs on complicated tasks in the terminal
★ 2.4kSWE-smith. [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
★ 696swt-bench. [NeurIPS 2024] Evaluation harness for SWT-Bench, a benchmark for evaluating LLM repository-level test-generation
★ 85verifiers. Our library for RL environments + evals
★ 4.3kDebugBench. The repository for paper "DebugBench: "Evaluating Debugging Capability of Large Language Models".
★ 87DI-engine. OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
★ 3.6kmulti-swe-bench. Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
★ 350agno. Build, run, and manage your own agent platform.
★ 41kthinking-in-space. Official repo and evaluation implementation of VSI-Bench
★ 731repomix. 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
★ 27kAgentless. Agentless🐱: an agentless approach to automatically solve software development problems
★ 2.1kr2e. [ICML '24] R2E: Turn any GitHub Repository into a Programming Agent Environment
★ 148textgames. Python
★ 9BEHAVIOR-1K. BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx
★ 1.6kRepoST. Code for "[COLM'25] RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing"
★ 24uv. An extremely fast Python package and project manager, written in Rust.
★ 87kxgrammar. Fast, Flexible and Portable Structured Generation
★ 1.8kSWE-bench. SWE-bench: Can Language Models Resolve Real-world Github Issues?
★ 5.4kFlashMLA. FlashMLA: Efficient Multi-head Latent Attention Kernels
★ 13kcontinue. open-source coding agent
★ 35kDeepSeek-R1.
★ 92kOpenHands. 🙌 OpenHands: AI-Driven Development
★ 80kcosta-utils. Python
★ 10opencompass. OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
★ 7.2kopeninterpreter. A lightweight coding agent for open models like Deepseek, Kimi, and Qwen
★ 64kllm-decontaminator. Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"
★ 323LAPA. [ICLR 2025] LAPA: Latent Action Pretraining from Videos
★ 556lingua. Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
★ 4.8kCitationMap. A simple pip-installable Python tool to generate your HTML citation world map from your Google Scholar ID.
★ 7201xgpt. world modeling challenge for humanoid robots
★ 561LLM-Engines. Python
★ 50chatbox. Powerful AI Client
★ 41kDOnlineJudge. An online judge developed using ReactJS as frontend and Django REST API framework as backend.
★ 6judge0. Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.
★ 4.3keasy-align. A tutorial for aligning language models
★ 6DistillKit. An Open Source Toolkit For LLM Distillation
★ 977LLM-Shearing. [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
★ 640EasyLM. Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
★ 2.5kfasthtml. The fastest way to create an HTML app
★ 7kminRLHF. A (somewhat) minimal library for finetuning language models with PPO on human feedback.
★ 91Speech. A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
★ 18kMoA. Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models
★ 2.9kGoodBadGreedy. The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism
★ 31LLM101n. LLM101n: Let's build a Storyteller
★ 37knanoChatGPT. nanogpt turned into a chat model
★ 82nanoRLHF. Train a tiny LLaMA model from scratch to repeat your words using Reinforcement Learning from Human Feedback (RLHF)
★ 18ZeroEval. A simple unified framework for evaluating LLMs
★ 272WildVision-Arena. https://huggingface.co/spaces/WildVision/vision-arena
★ 11nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.
★ 61kawesome-mechanistic-interpretability-lm-papers.
★ 257RAGatouille. Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
★ 3.9kbm25s. Fast BM25 search in Python, powered by Numpy and Numba
★ 1.7kLLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
★ 99koh-my-cv. An in-browser, local-first Markdown resume builder.
★ 1kmagpie. [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!
★ 869SWE-agent. SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
★ 20kwildvision-bench.github.io.
★ 1scrape-open-llm-leaderboard. Scrape and export data from the Open LLM Leaderboard.
★ 48ChatTTS. A generative speech model for daily dialogue.
★ 40kWildBench. Benchmarking LLMs with Challenging Tasks from Real Users
★ 255MAP-NEO. Python
★ 985geminiplayground. Gemini Playground provides a Python interface and a user interface to interact with the Gemini models family
★ 39SafeDecoding. Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
★ 154outlines. Structured Outputs
★ 14kdevika. Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.
★ 20kETO. Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)
★ 167bore. 🕳 bore is a simple CLI tool for making tunnels to localhost
★ 11kMediaCrawler. 小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 | 评论爬虫、微博帖子 | 评论爬虫、百度贴吧帖子 | 百度贴吧评论回复爬虫 | 知乎问答文章|评论爬虫
★ 56kOpen-Sora. Open-Sora: Democratizing Efficient Video Production for All
★ 29kmixtral. Mixtral finetuning
★ 19OpenCodeInterpreter. OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.
★ 1.7kTrustLLM. [ICML 2024] TrustLLM: Trustworthiness in Large Language Models
★ 628RefGPT. Python
★ 98OpenRLHF. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
★ 9.8kprompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
★ 165kMultilingualSIFT. MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning
★ 97SPIN. The official implementation of Self-Play Fine-Tuning (SPIN)
★ 1.2kDeepSeek-Math. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
★ 3.4kShareGPT_investigation. The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions (EMNLP 2023))
★ 13chatgpt-failures. Failure archive for ChatGPT and similar models
★ 595MMBench. Official Repo of "MMBench: Is Your Multi-modal Model an All-around Player?"
★ 305llm_steer. Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
★ 280overleaf_cool_fonts. how to do cool fonts in overleaf
★ 1InfoBench. Python
★ 61AgentBoard. An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]
★ 425Yi. A series of large language models trained from scratch by developers @01-ai
★ 7.8kself-rewarding-lm-pytorch. Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
★ 1.4kfree-for-dev. A list of SaaS, PaaS and IaaS offerings that have free tiers of interest to devops and infradev
★ 129kUnifiedFeedback. Python
★ 3SeeAct. [ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
★ 851camel. 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
★ 17kbagel. A bagel, with everything.
★ 326AlignTDS. Analyzing LLM Alignment via Token distribution shift
★ 17episodic-memory. Python
★ 139CommonGen-Eval. Evaluating LLMs with CommonGen-Lite
★ 95axolotl. Go ahead and axolotl questions
★ 12kunified-io-2. Python
★ 650ToolEyes. [COLING 2025] ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
★ 74vectordb. A Python vector database you just need - no more, no less.
★ 650AgentLLM. AgentLLM is a PoC for browser-native autonomous agents
★ 469lorax. Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
★ 3.8kMedusa. Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
★ 2.8kcodebox-api. 👾📦 CodeBoxAPI is the simplest sandboxing infrastructure for your LLM Apps and Services.
★ 364swiftsage.github.io. JavaScript
★ 2URIAL. Python
★ 316WeChatMsg.
★ 42kjust-eval. A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.
★ 90faith-and-fate. Python
★ 39LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
★ 25kcursor.
★ 33kLlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
★ 73kPASTA. PASTA: Post-hoc Attention Steering for LLMs
★ 142lumos. Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"
★ 478langsuite. Official Repo of LangSuitE
★ 84GPT-4V-Act. AI agent using GPT-4V(ision) capable of using a mouse/keyboard to interact with web UI
★ 1.1kmujoco. Multi-Joint dynamics with Contact. A general purpose physics simulator.
★ 14kopen_x_embodiment. Jupyter Notebook
★ 1.9klanguage-table. Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.
★ 360papermage. library supporting NLP and CV research on scientific papers
★ 800OpenMoE. A family of open-sourced Mixture-of-Experts (MoE) Large Language Models
★ 1.7kRLPHF. Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
★ 120AuditNLG. AuditNLG: Auditing Generative AI Language Modeling for Trustworthiness
★ 103dspy. DSPy: The framework for programming—not prompting—language models
★ 36kpdf-to-txt-python. Simple pdf to text with python using PDFtk and PyPDF2
★ 20s2orc. S2ORC: The Semantic Scholar Open Research Corpus: https://www.aclweb.org/anthology/2020.acl-main.447/
★ 1.1kpromptflow. Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
★ 11kVoyager. An Open-Ended Embodied Agent with Large Language Models
★ 7kmmc4. MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.
★ 953web-browsing-llama. Python
★ 7VITS-fast-fine-tuning. This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion
★ 5kicae. The repo for In-context Autoencoder
★ 172detoxify. Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.
★ 1.3kFActScore. A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"
★ 448world-models. Extracting spatial and temporal world models from LLMs
★ 262litellm. Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
★ 53kstreaming-llm. [ICLR 2024] Efficient Streaming Language Models with Attention Sinks
★ 7.2kllm-pddl. SAS
★ 456text-generation-inference. Large Language Model Text Generation Inference
★ 11kSuspicion-Agent. The implementation of "Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4"
★ 165Xwin-LM. Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
★ 1kMAmmoTH. Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" [ICLR 2024]
★ 383selfreferential-logical-puzzles. either solve or create a type of logical puzzle made up by a list of questions referring only to their own list of answers
★ 4Miniworld. Simple and easily configurable 3D FPS-game-like environments for reinforcement learning
★ 772openrl. Unified Reinforcement Learning Framework
★ 838Mind2Web. [NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web" -- the first LLM-based web agent and benchmark for generalist web agents
★ 1kreflexion-framework. A simple, modular, non-brittle framework for implementing text-based Reflexion agents.
★ 10PettingZoo. A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
★ 3.5knlp-gym. NLPGym - A toolkit to develop RL agents to solve NLP tasks.
★ 202leetcode-hard-gym. A hard gym for programming
★ 168Gymnasium. A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
★ 12kintercode. [NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898
★ 252AgentBench. A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
★ 3.6kneurologic_fast. a faster version of neurologic
★ 2Linly. Chinese-LLaMA 1&2、Chinese-Falcon 基础模型;ChatFlow中文对话模型;中文OpenLLaMA模型;NLP预训练/指令微调数据集
★ 3kLLaMA2-Accessory. An Open-source Toolkit for LLM Development
★ 2.8kGentopia. Build Hierarchical Autonomous Agents through Config. Collaborative Growth of Specialized Agents.
★ 328webarena. Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"
★ 1.5klorahub. [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
★ 671AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
★ 185kCTranslate2. Fast inference engine for Transformer models
★ 4.6kcomposer. Supercharge Your Model Training
★ 5.5ksymbolic-knowledge-distillation. Python
★ 143comet-atomic-2020. Python
★ 260LLM-Gen. A simple generate script utils using fastchat conv template for generation of Large Language Models
★ 21peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
★ 21kopen-instruct. AllenAI's post-training codebase
★ 3.8kchain-of-thought-hub. Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
★ 2.8kalpaca_eval. An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
★ 2kvisprog. Official code for VisProg (CVPR 2023 Best Paper!)
★ 774baize-chatbot. Let ChatGPT teach your own chatbot in hours with a single GPU!
★ 3.2kLLM-Blender. [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
★ 987LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
★ 5.9kaclpubcheck. Tools for checking ACL paper submissions
★ 1kinstance_attributions_NLP. Python
★ 16