taishi-i/awesome-ChatGPT-repositories / skills/awesome-chatgpt-search
awesome-chatgpt-search
UnverifiedSearch 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.0 KB |
| agents/openai.yaml | config | 210 B |
| data/repos-awesome-lists.json | config | 35.1 KB |
| data/repos-browser-extensions-a.json | config | 38.7 KB |
| data/repos-browser-extensions-b.json | config | 50.7 KB |
| data/repos-chatbots-a.json | config | 57.9 KB |
| data/repos-chatbots-b.json | config | 72.5 KB |
| data/repos-clis-a.json | config | 40.7 KB |
| data/repos-clis-b.json | config | 51.0 KB |
| data/repos-langchain.json | config | 60.6 KB |
| data/repos-nlp-a.json | config | 60.2 KB |
| data/repos-nlp-b.json | config | 73.9 KB |
| data/repos-openai-a.json | config | 43.8 KB |
| data/repos-openai-b.json | config | 49.7 KB |
| data/repos-others-a.json | config | 55.8 KB |
| data/repos-others-b.json | config | 66.7 KB |
| data/repos-prompts.json | config | 65.1 KB |
| data/repos-reimplementations.json | config | 12.6 KB |
| data/repos-tutorials.json | config | 7.5 KB |
| data/repos-unity.json | config | 5.1 KB |
data/repos-nlp-a.json
View on GitHub[
{"u":"https://github.com/microsoft/biogpt","n":"BioGPT","d":"microsoft research has released biogpt, a large language model trained on biomedical research literature. the model achieves better-than-human performance on answering questions from the biomedical...","c":"NLP","sc":4.5,"l":"Python","st":4500,"ns":7.3},
{"u":"https://github.com/varunshenoy/graphgpt","n":"GraphGPT","d":"Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️♂️","c":"NLP","sc":5.0,"l":"JavaScript","t":"gpt-3,knowledge-graph","st":4400,"ns":7.3},
{"u":"https://github.com/theappletucker/backend-gpt","n":"backend-GPT","d":"6/ \"gpt is all you need for the backend\" : use an llm to help you write a backendwired: llm is the backendinspiring project from a recent scale hackathon. the llm backend takes state as json blob a...","c":"NLP","sc":4.5,"l":"JavaScript","st":2900,"ns":6.9},
{"u":"https://github.com/tatsu-lab/stanford_alpaca","n":"stanford_alpaca","d":"Code and documentation to train Stanford's Alpaca models, and generate the data.","c":"NLP","sc":6.0,"l":"Python","t":"deep-learning,instruction-following,language-model","st":30000,"ns":9.0},
{"u":"https://github.com/antimatter15/alpaca.cpp","n":"alpaca.cpp","d":"Locally run an Instruction-Tuned Chat-Style LLM","c":"NLP","sc":3.0,"l":"C","st":10000,"ns":8.0},
{"u":"https://github.com/openai/openai-python","n":"openai-python","d":"The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language.","c":"NLP","sc":5.0,"l":"Python","t":"openai,python","st":31000,"ns":9.0},
{"u":"https://github.com/fminference/flexgen","n":"FlexGen","d":"Running large language models on a single GPU for throughput-oriented scenarios.","c":"NLP","sc":7.0,"l":"Python","t":"deep-learning,gpt-3,high-throughput,large-language-models,machine-learning,offloading,opt","st":9400,"ns":7.9},
{"u":"https://github.com/blinkdl/rwkv-lm","n":"RWKV-LM","d":"RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,...","c":"NLP","sc":8.0,"l":"Python","t":"attention-mechanism,chatgpt,deep-learning,gpt,gpt-2,gpt-3,language-model,linear-attention,lstm,pytorch,rnn,rwkv,transformer,transformers","st":15000,"ns":8.4},
{"u":"https://github.com/shyamsn97/mario-gpt","n":"mario-gpt","d":"Generating Mario Levels with GPT2. Code for the paper \"MarioGPT: Open-Ended Text2Level Generation through Large Language Models\" https://arxiv.org/abs/2302.05981","c":"NLP","sc":5.0,"l":"Python","st":1100,"ns":6.1},
{"u":"https://github.com/jameshwade/gpttools","n":"gpttools","d":"gpttools extends gptstudio for package development to help you document code, write tests, or even explain code","c":"NLP","sc":6.5,"l":"R","t":"chatgpt,nlp,openai,package-development,rstats,rstudio-addin","st":299,"ns":5.0},
{"u":"https://github.com/yihong0618/bilingual_book_maker","n":"bilingual_book_maker","d":"Create bilingual e-books using AI translation.","c":"NLP","sc":3.0,"l":"Python","st":9300,"ns":7.9},
{"u":"https://github.com/jesselau76/pdf-epub-gpt-translator","n":"pdf-epub-GPT-translator","d":"learn python + flask","c":"NLP","sc":1.5,"st":1700,"ns":6.5},
{"u":"https://github.com/greshake/llm-security","n":"llm-security","d":"New ways of breaking app-integrated LLMs","c":"NLP","sc":3.0,"l":"Python","st":2100,"ns":6.6},
{"u":"https://github.com/thudm/glm-130b","n":"GLM-130B","d":"GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)","c":"NLP","sc":4.0,"l":"Python","st":7700,"ns":7.8},
{"u":"https://github.com/kanhari/gpt-commit-summarizer","n":"gpt-commit-summarizer","d":"gpt based tool that writes the commit message for you","c":"NLP","sc":4.0,"l":"JavaScript","st":563,"ns":5.5},
{"u":"https://github.com/openai/gpt-3","n":"gpt-3","d":"GPT-3: Language Models are Few-Shot Learners","c":"NLP","sc":1.5,"st":16000,"ns":8.4},
{"u":"https://github.com/trzy/chatarkit","n":"ChatARKit","d":"Using ChatGPT to create AR experiences with natural language.","c":"NLP","sc":4.0,"l":"C","st":441,"ns":5.3},
{"u":"https://github.com/carperai/trlx","n":"trlx","d":"A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)","c":"NLP","sc":6.0,"l":"Python","t":"machine-learning,pytorch,reinforcement-learning","st":4700,"ns":7.3},
{"u":"https://github.com/thudm/chatglm-6b","n":"ChatGLM-6B","d":"ChatGLM-6B:开源双语对话语言模型 | An Open Bilingual Dialogue Language Model","c":"NLP","sc":4.0,"l":"Python","st":41000,"ns":9.2},
{"u":"https://github.com/mckaywrigley/ai-code-translator","n":"ai-code-translator","d":"Use AI to translate code from one language to another.","c":"NLP","sc":3.5,"l":"TypeScript","st":4200,"ns":7.2},
{"u":"https://github.com/tanreinama/gptsan","n":"GPTSAN","d":"General-purpose Swich transformer based Japanese language model","c":"NLP","sc":4.0,"l":"Python","st":118,"ns":4.2},
{"u":"https://github.com/instruction-tuning-with-gpt-4/gpt-4-llm","n":"GPT-4-LLM","d":"nice summary of our \"instruction tuning with gpt-4!\" @omarsar0 generated instruction-following & feedback data is released, leading to superior self-instruct llms. stay tuned while we are push...","c":"NLP","sc":4.0,"st":4300,"ns":7.3},
{"u":"https://github.com/openai/gpt-2","n":"gpt-2","d":"Code for the paper \"Language Models are Unsupervised Multitask Learners\"","c":"NLP","sc":4.5,"l":"Python","t":"paper","st":25000,"ns":8.8},
{"u":"https://github.com/forrestchang/gptlang","n":"gptlang","d":"A new programming language implemented by GPT-4.","c":"NLP","sc":2.5,"l":"Python","st":347,"ns":5.1},
{"u":"https://github.com/google/big-bench","n":"BIG-bench","d":"Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models","c":"NLP","sc":4.0,"l":"Python","st":3200,"ns":7.0},
{"u":"https://github.com/tysam-code/hlb-gpt","n":"hlb-gpt","d":"Minimalistic, fast, and experimentation-friendly researcher's toolbench for GPT-like models in ~<365 lines of code. Reaches <3.8 validation loss on wikitext-103 on a single A100 in ~138 seconds.","c":"NLP","sc":5.0,"l":"Python","st":356,"ns":5.1},
{"u":"https://github.com/guillaume-be/rust-bert","n":"rust-bert","d":"Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)","c":"NLP","sc":7.0,"l":"Rust","t":"bart,bert,deep-learning,electra,gpt,gpt-2,language-generation,machine-learning,ner,nlp,question-answering,roberta,rust,rust-lang,sentiment-analysis,transformer,translation","st":3100,"ns":7.0},
{"u":"https://github.com/jiggy-ai/hn_summary","n":"hn_summary","d":"Summarizes top stories from Hacker News using a large language model and post them to a Telegram channel.","c":"NLP","sc":7.0,"l":"Python","t":"gpt,gpt-3,gpt-3-prompts,gpt3,hacker-news,hackernews,llm,news,telegram-bot","st":247,"ns":4.8},
{"u":"https://github.com/traghav/auto-redteam","n":"auto-redteam","d":"Redteaming LLMs using other LLMs","c":"NLP","sc":2.5,"l":"Jupyter Notebook","st":256,"ns":4.8},
{"u":"https://github.com/madaan/cocogen","n":"CoCoGen","d":"there are nlp tasks in which codex performs better than gpt-3 and t5,if you convert the nl problem into pseudo-python!: appear in #emnlp2022)work led by @aman_madaan , with @shuyanzhxyc yiming yan...","c":"NLP","sc":4.5,"l":"TeX","st":86,"ns":3.9},
{"u":"https://github.com/huggingface/transformers","n":"transformers","d":"🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.","c":"NLP","sc":7.0,"l":"Python","t":"bert,deep-learning,flax,hacktoberfest,jax,language-model,language-models,machine-learning,model-hub,natural-language-processing,nlp,nlp-library,pretrained-models,python,pytorch,pytorch-transformers,seq2seq,speech-recognition,tensorflow,transformer","st":160000,"ns":10.0},
{"u":"https://github.com/yizhongw/self-instruct","n":"self-instruct","d":"Aligning pretrained language models with instruction data generated by themselves.","c":"NLP","sc":6.0,"l":"Python","t":"general-purpose-model,instruction-tuning,language-model","st":4600,"ns":7.3},
{"u":"https://github.com/mmz-001/knowledge_gpt","n":"knowledge_gpt","d":"Accurate answers and instant citations for your documents.","c":"NLP","sc":4.0,"l":"Python","st":1600,"ns":6.4},
{"u":"https://github.com/lhao499/lqae","n":"lqae","d":"Language Quantized AutoEncoders","c":"NLP","sc":5.5,"l":"Python","t":"autoencoders,bert,large-language-models,multimodal,roberta,vq,vqvae","st":114,"ns":4.1},
{"u":"https://github.com/observedobserver/chatgpt-i18n","n":"chatgpt-i18n","d":"Translate your locale json files with AI assistance.","c":"NLP","sc":7.0,"l":"TypeScript","t":"ai,chatgpt,chatgpt-i18n,frontend,gpt,i18n,i18n-ai","st":813,"ns":5.8},
{"u":"https://github.com/tatsu-lab/stanford_alpaca#fine-tuning","n":"stanford_alpaca","d":"Code and documentation to train Stanford's Alpaca models, and generate the data.","c":"NLP","sc":6.0,"l":"Python","t":"deep-learning,instruction-following,language-model","st":30000,"ns":9.0},
{"u":"https://github.com/rupeshs/alpaca.cpp","n":"alpaca.cpp","d":"Locally run an Instruction-Tuned Chat-Style LLM (Android/Linux/Windows/Mac)","c":"NLP","sc":4.0,"l":"C","st":262,"ns":4.8},
{"u":"https://github.com/r-three/fib","n":"fib","d":"are bloom, opt-175b, t0, and gpt-neox \"factually consistent\"? new preprint! we introduce fib - the factual inconsistency benchmark - and evaluate 23 llms. work done with @anisham197 @byryuer @mohit...","c":"NLP","sc":5.0,"l":"Python","st":26,"ns":2.9},
{"u":"https://github.com/bigscience-workshop/petals","n":"petals","d":"🌸 Run 100B+ language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading","c":"NLP","sc":7.0,"l":"Python","t":"bloom,deep-learning,distributed-systems,language-models,large-language-models,machine-learning,neural-networks,pipeline-parallelism,pytorch,tensor-parallelism,volunteer-computing","st":10000,"ns":8.0},
{"u":"https://github.com/lucasmccabe/emailgpt","n":"emailGPT","d":"a quick and easy interface to generate emails with ChatGPT","c":"NLP","sc":7.0,"l":"Python","t":"chatgpt,gpt,nlp,openai,productivity,streamlit"},
{"u":"https://github.com/uezo/gpt3-contextual","n":"gpt3-contextual","d":"Contextual chat with GPT-3 model of OpenAI API","c":"NLP","sc":3.0,"l":"Python","st":25,"ns":2.8},
{"u":"https://github.com/naptha/tesseract.js","n":"tesseract.js","d":"Pure Javascript OCR for more than 100 Languages 📖🎉🖥","c":"NLP","sc":6.0,"l":"JavaScript","t":"deep-learning,javascript,ocr,tesseract,webassembly","st":38000,"ns":9.2},
{"u":"https://github.com/lightaime/camel","n":"camel","d":"CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society","c":"NLP","sc":7.0,"l":"Python","t":"ai-societies,artificial-intelligence,communicative-ai,cooperative-ai,deep-learning,large-language-models,multi-agent-systems,natural-language-processing","st":17000,"ns":8.5},
{"u":"https://github.com/arokem/pubmed-gpt","n":"pubmed-gpt","d":"Use gpt to summarize abstracts for a pubmed query","c":"NLP","sc":3.0,"l":"Python","st":40,"ns":3.2},
{"u":"https://github.com/manyoso/haltt4llm","n":"haltt4llm","d":"This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real...","c":"NLP","sc":5.0,"l":"Python","st":224,"ns":4.7},
{"u":"https://github.com/huggingface/olm-datasets","n":"olm-datasets","d":"Pipeline for pulling and processing online language model pretraining data from the web","c":"NLP","sc":4.0,"l":"Python","st":179,"ns":4.5},
{"u":"https://github.com/ofirpress/self-ask","n":"self-ask","d":"Code and data for \"Measuring and Narrowing the Compositionality Gap in Language Models\"","c":"NLP","sc":3.5,"l":"Jupyter Notebook","st":326,"ns":5.0},
{"u":"https://github.com/johnnay/llm-lobbyist","n":"llm-lobbyist","d":"Code for the paper: \"Large Language Models as Corporate Lobbyists\" (2023).","c":"NLP","sc":3.5,"l":"Jupyter Notebook","st":173,"ns":4.5},
{"u":"https://github.com/nielsrogge/transformers-tutorials","n":"Transformers-Tutorials","d":"This repository contains demos I made with the Transformers library by HuggingFace.","c":"NLP","sc":7.0,"l":"Jupyter Notebook","t":"bert,gpt-2,layoutlm,pytorch,transformers,vision-transformer","st":12000,"ns":8.2},
{"u":"https://github.com/jquesnelle/sat-reading","n":"sat-reading","d":"new blog: language models vs. the sat reading test! they score ~90%, and flan-t5 does as well as gpt-3.5! finetuning even better!all the deets: available here, including a new huggingface dataset ...","c":"NLP","sc":4.5,"l":"Python","st":19,"ns":2.6},
{"u":"https://github.com/gnehs/subtitle-translator","n":"subtitle-translator","d":"Translate subtitle using ChatGPT","c":"NLP","sc":3.0,"l":"JavaScript","st":374,"ns":5.1},
{"u":"https://github.com/tenetlang/tenetlang","n":"tenetlang","d":"A GPT-Designed Language Built for Humans","c":"NLP","sc":3.0,"l":"Python","st":187,"ns":4.5},
{"u":"https://github.com/jesselau76/ebook-gpt-translator","n":"ebook-GPT-translator","d":"Enjoy reading with your favorite style.","c":"NLP","sc":6.0,"l":"Python","t":"docx,epub,mobi,pdf,python,translation,translator","st":1700,"ns":6.5},
{"u":"https://github.com/jesselau76/srt-gpt-translator","n":"srt-gpt-translator","d":"Subtitle translator","c":"NLP","sc":5.0,"l":"Python","t":"gpt,srt,subtitle,translator","st":145,"ns":4.3},
{"u":"https://github.com/ibestvina/datasloth","n":"datasloth","d":"Natural language Pandas queries and data generation powered by GPT-3","c":"NLP","sc":5.0,"l":"Python","t":"gpt-3,pandas","st":200,"ns":4.6},
{"u":"https://github.com/lvwerra/trl","n":"trl","d":"Train transformer language models with reinforcement learning.","c":"NLP","sc":4.0,"l":"Python","st":18000,"ns":8.5},
{"u":"https://github.com/stanfordnlp/dsp","n":"dsp","d":"𝗗𝗦𝗣: Demonstrate-Search-Predict. A framework for composing retrieval and language models for knowledge-intensive NLP.","c":"NLP","sc":4.0,"l":"Jupyter Notebook","st":34000,"ns":9.1},
{"u":"https://github.com/whu-zqh/chatgpt-vs.-bert","n":"ChatGPT-vs.-BERT","d":"🎁[ChatGPT4NLU] A Comparative Study on ChatGPT and Fine-tuned BERT","c":"NLP","sc":5.5,"l":"Python","t":"bert,chain-of-thought,chatgpt,in-context-learning,natural-language-understanding","st":191,"ns":4.6},
{"u":"https://github.com/stevebauman/github-summarizer","n":"github-summarizer","d":"A PHP GitHub summarizer using Chat GPT.","c":"NLP","sc":3.0,"l":"PHP","st":45,"ns":3.3},
{"u":"https://github.com/liujch1998/siri-chatgpt","n":"siri-chatgpt","d":"now you can transform siri into the real #chatgpt! simply download this shortcut (link in repo ⬇️) to your iphone, edit its script in the shortcuts app (i.e. paste your api key into the text box), ...","c":"NLP","sc":3.5,"st":8,"ns":1.9},
{"u":"https://github.com/microsoft/unilm","n":"unilm","d":"Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities","c":"NLP","sc":7.0,"l":"Python","t":"beit,beit-3,deepnet,document-ai,document-foundation-model,foundation-models,kosmos,kosmos-1,layoutlm,layoutxlm,llm,minilm,mllm,multimodal,multimodal-pre-trained-model,nlp,pre-trained-model,trocr,unilm,xlm-e","st":22000,"ns":8.7},
{"u":"https://github.com/ganymedenil/document.ai","n":"document.ai","d":"基于向量数据库与GPT3.5的通用本地知识库方案(A universal local knowledge base solution based on vector database and GPT3.5)","c":"NLP","sc":4.0,"l":"Python","st":3700,"ns":7.1},
{"u":"https://github.com/salesforce/lavis","n":"LAVIS","d":"LAVIS - A One-stop Library for Language-Vision Intelligence","c":"NLP","sc":7.0,"l":"Python","t":"deep-learning,deep-learning-library,image-captioning,multimodal-datasets,multimodal-deep-learning,salesforce,vision-and-language,vision-framework,vision-language-pretraining,vision-language-transformer,visual-question-anwsering","st":11000,"ns":8.1},
{"u":"https://github.com/machinewrapped/gpt-subtrans","n":"gpt-subtrans","d":"Project using OpenAI/ChatGPT to translate subtitle files","c":"NLP","sc":3.5,"l":"Python","st":593,"ns":5.5},
{"u":"https://github.com/transmissions11/flux","n":"flux","d":"LLM Power Tool","c":"NLP","sc":3.0,"l":"TypeScript","st":887,"ns":5.9},
{"u":"https://github.com/panterapolnocy/lsl-snippets","n":"LSL-snippets","d":"Small scripts written (or modified) by me, in Linden Scripting Language (LSL), for Second Life.","c":"NLP","sc":4.0,"l":"LSL","st":17,"ns":2.5},
{"u":"https://github.com/whitead/paper-qa","n":"paper-qa","d":"LLM Chain for answering questions from documents with citations","c":"NLP","sc":6.0,"l":"Python","t":"chatgpt,nlp,question-answering"},
{"u":"https://github.com/microsoft/semantic-kernel","n":"semantic-kernel","d":"Integrate cutting-edge LLM technology quickly and easily into your apps","c":"NLP","sc":6.0,"l":"C#","t":"ai,artificial-intelligence,llm,openai,sdk","st":28000,"ns":8.9},
{"u":"https://github.com/jbrukh/gpt-jargon","n":"gpt-jargon","d":"Jargon is a natural language programming language specified and executed by LLMs like GPT-4.","c":"NLP","sc":3.0,"st":239,"ns":4.8},
{"u":"https://github.com/cognosisai/platform","n":"platform","d":"@erikschluntz when i initially played with gpt-3 agents in the summer of last year (you can see an example here: whereby you can give a gpt-3 agent with access to a javascript repl a goal to accom...","c":"NLP","sc":8.0,"l":"TypeScript","t":"ai,docker,elasticsearch,gpt-3,javascript,llm,typescript","st":174,"ns":4.5},
{"u":"https://github.com/shreyar/guardrails","n":"guardrails","d":"Adding guardrails to large language models.","c":"NLP","sc":5.0,"l":"Python","t":"ai,foundation-model,gpt-3,llm,openai","st":6800,"ns":7.7},
{"u":"https://github.com/brandonrobertz/chatgpt-document-extraction","n":"chatgpt-document-extraction","d":"A proof of concept tool for using ChatGPT to transform messy text documents into structured JSON","c":"NLP","sc":3.5,"l":"Python","st":122,"ns":4.2},
{"u":"https://github.com/dosco/minds","n":"minds","d":"MindsJS - Build AI powered workflows easily","c":"NLP","sc":6.0,"l":"TypeScript","t":"ai,cohere,gpt-3,javascript,llm,nodejs,openai,typescript,workflows","st":2600,"ns":6.8},
{"u":"https://github.com/aggregate-intellect/practical-llms","n":"practical-llms","d":"#aiscllmworkshopa quick way to go from zero to dangerous (like, be able to confidently bullshit like chatgpt, but also quickly ramp up on how to go from idea to product with the latest & greate...","c":"NLP","sc":4.0,"st":174,"ns":4.5},
{"u":"https://github.com/stanfordbdhg/healthgpt","n":"HealthGPT","d":"Query your Apple Health data with natural language 💬 🩺","c":"NLP","sc":5.5,"l":"Swift","t":"apple-health,healthkit,ios,openai,swift","st":1900,"ns":6.6},
{"u":"https://github.com/greydgl/pentestgpt","n":"PentestGPT","d":"A GPT-empowered penetration testing tool","c":"NLP","sc":5.0,"l":"HTML","t":"large-language-models,llm,penetration-testing,python","st":13000,"ns":8.2},
{"u":"https://github.com/h2oai/h2ogpt","n":"h2ogpt","d":"Come join the movement to make the world's best open source GPT led by H2O.ai","c":"NLP","sc":5.0,"l":"Python","t":"chatgpt,llm","st":12000,"ns":8.2},
{"u":"https://github.com/freedomintelligence/llmzoo","n":"LLMZoo","d":"⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡","c":"NLP","sc":4.0,"l":"Python","st":2900,"ns":6.9},
{"u":"https://github.com/oneil512/insight","n":"INSIGHT","d":"INSIGHT is an autonomous AI that can do medical research!","c":"NLP","sc":7.0,"l":"Python","t":"agent,ai,chatgpt,gpt,llm,medical,ml,python","st":416,"ns":5.2},
{"u":"https://github.com/h2oai/h2o-llmstudio","n":"h2o-llmstudio","d":"H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs","c":"NLP","sc":4.0,"l":"Python","st":5000,"ns":7.4},
{"u":"https://github.com/hxu296/nlp-resume-parser","n":"nlp-resume-parser","d":"NLP-powered, GPT-3 enabled Resume Parser from PDF to JSON.","c":"NLP","sc":6.5,"l":"Python","t":"gpt-3,nlp,nlp-parsing,open-ai,parser,resume,resume-parer","st":276,"ns":4.9},
{"u":"https://github.com/pashpashpash/vault-ai","n":"vault-ai","d":"OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, etc) using a simple React frontend.","c":"NLP","sc":8.0,"l":"JavaScript","t":"ai,artificial-intelligence,chatgpt,generative,go,golang,knowledge-base,long-term-memory,machine-learning,openai,openai-api,pdf-support,pinecone,question-answering,react,reactjs,vector-search","st":3400,"ns":7.1},
{"u":"https://github.com/ohmplatform/freedomgpt","n":"FreedomGPT","d":"This codebase is for a React and Electron-based app that executes the FreedomGPT LLM locally (offline and private) on Mac and Windows using a chat-based interface (based on Alpaca Lora)","c":"NLP","sc":7.0,"l":"TypeScript","t":"electron,gpt,llm,react","st":2700,"ns":6.9},
{"u":"https://github.com/xtekky/chatgpt-clone","n":"chatgpt-clone","d":"ChatGPT interface with better UI","c":"NLP","sc":6.0,"l":"Python","t":"chatgpt,chatgpt-api,chatgpt-app,chatgpt-clone,gpt-4,gpt-4-api,gpt-interface,gpt3,gpt4,gpt4-api,gpt4all,interface,language,language-model,site,ui","st":3500,"ns":7.1},
{"u":"https://github.com/whoiskatrin/chart-gpt","n":"chart-gpt","d":"AI tool to build charts based on text input","c":"NLP","sc":3.0,"l":"TypeScript","st":3600,"ns":7.1},
{"u":"https://github.com/lightaime/camel#data-hosted-on-hugging-face","n":"camel","d":"🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society","c":"NLP","sc":7.0,"l":"Python","t":"ai-societies,artificial-intelligence,communicative-ai,cooperative-ai,deep-learning,large-language-models,multi-agent-systems,natural-language-processing","st":17000,"ns":8.5},
{"u":"https://github.com/agiresearch/openagi","n":"OpenAGI","d":"OpenAGI: When Legal Master of Laws Meets Domain Experts","c":"NLP","sc":5.5,"l":"Jupyter Notebook","t":"agi,llm,opensource","st":2300,"ns":6.7},
{"u":"https://github.com/jackbackes/happycommit","n":"happycommit","d":"HappyCommit is a delightful tool that harnesses the power of OpenAI's GPT-3.5 Turbo language model to generate meaningful and descriptive Git commit messages for you.","c":"NLP","sc":4.5,"l":"Rust","st":15,"ns":2.4},
{"u":"https://github.com/jconorgrogan/jamesgpt","n":"JamesGPT","d":"Jailbreak for ChatGPT: Predict the future, opine on politics and controversial topics, and assess what is true. May help us understand more about LLM Bias","c":"NLP","sc":3.5,"st":395,"ns":5.2},
{"u":"https://github.com/kaixindelele/chatpaper","n":"ChatPaper","d":"Use ChatGPT to summarize the arXiv papers. 全流程加速科研,利用chatgpt进行论文总结+润色+审稿+审稿回复","c":"NLP","sc":3.5,"l":"Python","st":19000,"ns":8.6},
{"u":"https://github.com/srush/minichain","n":"minichain","d":"Sequence-to-sequence model with LSTM encoder/decoders and attention","c":"NLP","sc":3.5,"l":"Lua","st":1200,"ns":6.2},
{"u":"https://github.com/irgolic/autopr","n":"AutoPR","d":"Fix issues with AI-generated pull requests, powered by ChatGPT","c":"NLP","sc":6.5,"l":"Python","t":"action,actions,ai,chatgpt,github-action,github-actions,gpt,gpt-3,gpt-4,llm,openai","st":1400,"ns":6.3},
{"u":"https://github.com/imartinez/privategpt","n":"privateGPT","d":"Interact privately with your documents using the power of GPT, 100% privately, no data leaks","c":"NLP","sc":3.5,"l":"Python","st":57000,"ns":9.5},
{"u":"https://github.com/filip-michalsky/salesgpt","n":"SalesGPT","d":"Context-aware AI Sales Agent to automate sales outreach.","c":"NLP","sc":3.5,"l":"Jupyter Notebook","st":2600,"ns":6.8},
{"u":"https://github.com/openai/automated-interpretability","n":"automated-interpretability","d":"LLMs Can Explain Neurons in Other LLMsExplain GPT-2 neuron’s behavior by showing GPT-4 (token, activation) pairsSimulate neuron's activations based on explanation w/ GPT-4Score explanation based on...","c":"NLP","sc":4.5,"l":"Python","st":1100,"ns":6.1},
{"u":"https://github.com/evalplus/evalplus","n":"evalplus","d":"EvalPlus for rigourous evaluation of LLM-synthesized code","c":"NLP","sc":6.5,"l":"Python","t":"benchmark,chatgpt,gpt-4,large-language-models,program-synthesis,testing","st":1700,"ns":6.5},
{"u":"https://github.com/nyanp/chat2plot","n":"chat2plot","d":"chat to visualization with LLM","c":"NLP","sc":2.5,"l":"Python","st":280,"ns":4.9},
{"u":"https://github.com/gmpetrov/databerry","n":"databerry","d":"The no-code platform for building custom LLM Agents","c":"NLP","sc":6.5,"l":"TypeScript","t":"ai,chatgpt,chatgpt-plugins,llm,no-code,openai,qdrant,semantic-search,typescript","st":2900,"ns":6.9},
{"u":"https://github.com/microsoft/guidance","n":"guidance","d":"A guidance language for controlling large language models.","c":"NLP","sc":3.5,"l":"Jupyter Notebook","st":21000,"ns":8.6},
{"u":"https://github.com/jaredkirby/smartpilot","n":"SmartPilot","d":"A Python program leveraging OpenAI's language models to generate, analyze, and select the best answer to a given question.","c":"NLP","sc":4.5,"l":"Python","st":46,"ns":3.3},
{"u":"https://github.com/smol-ai/developer","n":"developer","d":"with 100k context windows on the way, it's now feasible for every dev to have their own smol developer","c":"NLP","sc":3.5,"l":"Python","st":12000,"ns":8.2},
{"u":"https://github.com/kagisearch/pyllms","n":"pyllms","d":"Minimal Python library to connect to LLMs (OpenAI, Anthropic, AI21, Cohere, Aleph Alpha, HuggingfaceHub, Google PaLM2, with a built-in model performance benchmark.","c":"NLP","sc":4.5,"l":"Python","st":819,"ns":5.8},
{"u":"https://github.com/ray-project/llm-numbers","n":"llm-numbers","d":"Numbers every LLM developer should know","c":"NLP","sc":1.5,"st":4300,"ns":7.3},
{"u":"https://github.com/rucaibox/structgpt","n":"StructGPT","d":"The code and data for \"StructGPT: A general framework for Large Language Model to Reason on Structured Data\"","c":"NLP","sc":3.5,"l":"Python","st":417,"ns":5.2},
{"u":"https://github.com/iryna-kondr/scikit-llm","n":"scikit-llm","d":"Seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks.","c":"NLP","sc":6.5,"l":"Python","t":"chatgpt,deep-learning,llm,machine-learning,scikit-learn,transformers","st":3500,"ns":7.1},
{"u":"https://github.com/zeno-ml/zeno-build","n":"zeno-build","d":"Build, evaluate, analyze, and understand LLM-based apps","c":"NLP","sc":3.5,"l":"Python","st":491,"ns":5.4},
{"u":"https://github.com/imartinez/privategpt?utm_source=tldrnewsletter","n":"privateGPT","d":"Interact privately with your documents using the power of GPT, 100% privately, no data leaks","c":"NLP","sc":3.5,"l":"Python","st":57000,"ns":9.5},
{"u":"https://github.com/appointat/chat-with-document-s-using-chatgpt-api-and-text-embedding","n":"Chat-with-Document-s-using-ChatGPT-API-and-Text-Embedding","d":"Chat with Document(s) using ChatGPT API and Text Embedding","c":"NLP","sc":3.5,"l":"Python","st":145,"ns":4.3},
{"u":"https://github.com/artidoro/qlora","n":"qlora","d":"QLoRA: Efficient Finetuning of Quantized LLMs","c":"NLP","sc":2.5,"l":"Jupyter Notebook","st":11000,"ns":8.1},
{"u":"https://github.com/e-johnstonn/briefgpt","n":"BriefGPT","d":"Locally hosted tool that connects documents to LLMs for summarization and querying, with a simple GUI.","c":"NLP","sc":3.5,"l":"Python","st":796,"ns":5.8},
{"u":"https://github.com/mbzuai-oryx/xraygpt","n":"XrayGPT","d":"XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models.","c":"NLP","sc":3.5,"l":"Python","st":532,"ns":5.5},
{"u":"https://github.com/minedojo/voyager","n":"Voyager","d":"An Open-Ended Embodied Agent with Large Language Models","c":"NLP","sc":5.5,"l":"Python","t":"embodied-learning,large-language-models,minecraft,open-ended-learning","st":6900,"ns":7.7},
{"u":"https://github.com/shishirpatil/gorilla","n":"gorilla","d":"Gorilla: A store for APIs for LLMs.","c":"NLP","sc":4.5,"l":"Python","t":"anthropic-claude,api,gpt-4,llm","st":13000,"ns":8.2},
{"u":"https://github.com/paralleldrive/sudolang-llm-support","n":"sudolang-llm-support","d":"SudoLang LLM Support for VSCode","c":"NLP","sc":1.5,"st":1300,"ns":6.2},
{"u":"https://github.com/azure-samples/azure-search-openai-demo","n":"azure-search-openai-demo","d":"A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A exper...","c":"NLP","sc":7.5,"l":"Python","t":"azd-templates,azure,azurecognitivesearch,azureopenai,chatgpt,openai","st":7700,"ns":7.8},
{"u":"https://github.com/emmethalm/infinitegpt","n":"infiniteGPT","d":"InfiniteGPT is a Python script that lets you input an unlimited size text into the OpenAI API. No more tedious copy & pasting. Long live multithreading!","c":"NLP","sc":4.5,"l":"Python","st":737,"ns":5.7},
{"u":"https://github.com/openbmb/toolbench","n":"ToolBench","d":"An open platform for training, serving, and evaluating large language model for tool learning.","c":"NLP","sc":3.5,"l":"Python","st":5600,"ns":7.5},
{"u":"https://github.com/promtengineer/localgpt","n":"localGPT","d":"Chat with your documents on your local device using GPT models. No data leaves your device and 100% private. ","c":"NLP","sc":3.5,"l":"Python","st":22000,"ns":8.7},
{"u":"https://github.com/azure-samples/azure-search-openai-demo-csharp","n":"azure-search-openai-demo-csharp","d":"A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experi...","c":"NLP","sc":7.5,"l":"C#","t":"azd-templates,azure,chatgpt,csharp,dotnet,openai","st":833,"ns":5.8},
{"u":"https://github.com/simonw/llm","n":"llm","d":"Access large language models from the command-line","c":"NLP","sc":2.5,"l":"Python","st":12000,"ns":8.2},
{"u":"https://github.com/panqiwei/autogptq","n":"AutoGPTQ","d":"An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.","c":"NLP","sc":6.5,"l":"Python","t":"deep-learning,inference,large-language-models,llms,nlp,pytorch,quantization,transformer,transformers","st":5100,"ns":7.4},
{"u":"https://github.com/zkx06111/algo","n":"ALGO","d":"🚀Introducing ALGO, a code synthesis framework guided by LLM-generated oracles. Integrated with ALGO, Codex is 8x better and ChatGPT 1.3x better at contest-level problems. Plus, ALGO verifies your s...","c":"NLP","sc":4.5,"l":"Python","st":36,"ns":3.1},
{"u":"https://github.com/i-eval/faireval","n":"FairEval","d":"Large Language Models are not Fair Evaluators- A bias in the evaluation of adopting LLMs, e.g., GPT-4, as a referee to score- Successfully mitigates the bias, resulting in closer alignment with hum...","c":"NLP","sc":4.5,"l":"Python","st":144,"ns":4.3},
{"u":"https://github.com/eiaserinnys/pdf2md","n":"pdf2md","d":"This project, pdf2md, transforms academic paper PDF files into digestible text files. By analyzing the layout of the PDF file, the application restructures paragraphs and translates desired content...","c":"NLP","sc":5.5,"l":"Python","t":"pdf-converter,translation","st":80,"ns":3.8},
{"u":"https://github.com/monarch-initiative/ontogpt","n":"ontogpt","d":"GPT-based ontological extraction tools, including SPIRES","c":"NLP","sc":6.5,"l":"Jupyter Notebook","t":"ai,chat-gpt,gpt-3,language-models,large-language-models,linkml,monarchinitiative,nlp,oaklib,obofoundry,relation-extraction","st":873,"ns":5.9},
{"u":"https://github.com/selefra/selefra","n":"selefra","d":"The open-source policy-as-code software that provides analysis for Multi-Cloud and SaaS environments, you can get insight with natural language (powered by OpenAI).","c":"NLP","sc":7.5,"l":"Go","t":"aws,azure,chatgpt,cloud,cspm,devops,finops,gcp,golang,google,infrastructure-as-code,kubernetes,openai,policy-as-code,terraform","st":544,"ns":5.5},
{"u":"https://github.com/deepset-ai/haystack","n":"haystack","d":":mag: Haystack is an open source NLP framework to interact with your data using Transformer models and LLMs (GPT-4, ChatGPT and alike). Haystack offers production-ready tools to quickly build compl...","c":"NLP","sc":7.5,"l":"Python","t":"ai,bert,chatgpt,elasticsearch,generative-ai,gpt-3,information-retrieval,language-model,large-language-models,machine-learning,natural-language-processing,nlp,python,pytorch,question-answering,semantic-search,squad,summarization,transfer-learning,transformers","st":25000,"ns":8.8},
{"u":"https://github.com/nlpxucan/wizardlm","n":"WizardLM","d":"Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder","c":"NLP","sc":3.5,"l":"Python","st":9500,"ns":8.0},
{"u":"https://github.com/katanaml/sparrow","n":"sparrow","d":"Data extraction from documents with ML","c":"NLP","sc":4.5,"l":"Jupyter Notebook","t":"computer-vision,huggingface-transformers,machinelearning,nlp-machine-learning","st":5200,"ns":7.4},
{"u":"https://github.com/lamini-ai/lamini","n":"lamini","d":"Today:🎉Hosted data generator for training LLMs like ChatGPT 🎉An open-source LLM, trained on the generated data with the Lamini engine 👉Early access waitlist to full training, incl. enterprise VPC e...","c":"NLP","sc":4.5,"l":"Python","st":2500,"ns":6.8},
{"u":"https://github.com/sharonzhou/long_stable_diffusion","n":"long_stable_diffusion","d":"Long-form text-to-images generation, using a pipeline of deep generative models (GPT-3 and Stable Diffusion)","c":"NLP","sc":3.5,"l":"Python","st":689,"ns":5.7},
{"u":"https://github.com/0xpayne/gpt-migrate","n":"gpt-migrate","d":"Easily migrate your codebase from one framework or language to another.","c":"NLP","sc":3.5,"l":"Python","st":7000,"ns":7.7},
{"u":"https://github.com/imoneoi/openchat","n":"openchat","d":"OpenChat: Less is More for Open-source Models","c":"NLP","sc":4.5,"l":"Jupyter Notebook","t":"large-language-models,open-source,transformers","st":5500,"ns":7.5},
{"u":"https://github.com/thudm/webglm","n":"WebGLM","d":"WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)","c":"NLP","sc":5.5,"l":"Python","t":"chatgpt,llm,rlhf,webglm","st":1600,"ns":6.4},
{"u":"https://github.com/geekan/metagpt","n":"MetaGPT","d":"The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo | 多智能体元编程框架:给定老板需求,输出产品文档、架构设计、任务列表、代码","c":"NLP","sc":6.5,"l":"Python","t":"agent,gpt,llm,metagpt","st":68000,"ns":9.7},
{"u":"https://github.com/raghavan/pdfgptindexer","n":"PdfGptIndexer","d":"An efficient tool for indexing and searching PDF text data using OpenAI's GPT-2 model and FAISS (Facebook AI Similarity Search) index, designed for rapid information retrieval and superior search a...","c":"NLP","sc":4.5,"l":"Python","st":677,"ns":5.7},
{"u":"https://github.com/transformeroptimus/superagi","n":"SuperAGI","d":"<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.","c":"NLP","sc":7.5,"l":"Python","t":"agents,agi,ai,artificial-general-intelligence,artificial-intelligence,autonomous-agents,gpt-4,llm,llmops,nextjs,openai,pinecone,python,superagi","st":18000,"ns":8.5},
{"u":"https://github.com/bentoml/openllm","n":"OpenLLM","d":"Operating LLMs in production","c":"NLP","sc":5.5,"l":"Python","t":"ai,chatglm,deployment,developer-tools,dolly,easy-to-use,falcon,fine-tuning,llm,llm-serving,llmops,lmops,machine-learning,model-inference,stablelm,t5-model","st":12000,"ns":8.2},
{"u":"https://github.com/franxyao/gpt-bargaining","n":"GPT-Bargaining","d":"Code for Arxiv 2023: Improving Language Model Negociation with Self-Play and In-Context Learning from AI Feedback","c":"NLP","sc":3.5,"l":"Jupyter Notebook","st":208,"ns":4.6},
{"u":"https://github.com/divergentai/dreamgpt","n":"dreamGPT","d":"Leverage hallucinations from Large Language Models (LLMs) for novelty-driven explorations.","c":"NLP","sc":6.5,"l":"Python","t":"agents,artificial-intelligence,automation,generative-model,ideas,llm,llms,machinelearning,ml","st":589,"ns":5.5},
{"u":"https://github.com/litch/lnchat","n":"lnchat","d":"So I built a thing - LNChat. You hook this app up to your node and then you can ask it plaintext questions like, \"what is my newest channel\", \"show me a channel summary\". ChatGPT bridges the gap. ...","c":"NLP","sc":4.5,"l":"Python","st":3,"ns":1.2},
{"u":"https://github.com/cgisky1980/ai00_rwkv_server","n":"ai00_rwkv_server","d":"A localized open-source AI server that is better than ChatGPT.","c":"NLP","sc":6.5,"l":"CSS","t":"ai,chatgpt,chatgpt-api,chatgpt4,chatgpt4free,llm,openai,openai-api,rwkv","st":612,"ns":5.6},
{"u":"https://github.com/jeinlee1991/chinese-llm-benchmark","n":"chinese-llm-benchmark","d":"Chinese Large Model Capability Evaluation Ranking: Covers open source large models such as Baidu Wenxin Yiyuan, ChatGPT, Ali Tongyi Qianwen, Xunfei Xinghuo, Belle/ChatGLM6B, etc., with multidimensi...","c":"NLP","sc":3.5,"st":6000,"ns":7.6},
{"u":"https://github.com/sunnweiwei/rankgpt","n":"RankGPT","d":"Is ChatGPT Good at Search? LLMs as Re-Ranking Agent","c":"NLP","sc":5.5,"l":"Python","t":"chatgpt,information-retrieval,large-language-models,reranking","st":665,"ns":5.6},
{"u":"https://github.com/qiuhuachuan/smile","n":"smile","d":"SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support","c":"NLP","sc":3.5,"l":"Python","st":528,"ns":5.4},
{"u":"https://github.com/bigbigwatermalon/c3sql","n":"C3SQL","d":"The code for the paper C3: Zero-shot Text-to-SQL with ChatGPT","c":"NLP","sc":3.5,"l":"Python","st":167,"ns":4.5},
{"u":"https://github.com/fmxexpress/codedroidai","n":"CodeDroidAI","d":"Generate code and forms with AI for Delphi Object Pascal and C++Builder using LLMs like ChatGPT and Vicuna-13b.","c":"NLP","sc":6.5,"l":"Pascal","t":"ai,artificial-intelligence,chatgpt-api,cpp-builder,delphi,delphi2007,gpt-3,gpt-4,replicate,unicode,vicuna-13b","st":88,"ns":3.9},
{"u":"https://github.com/kdalanon/chatgpt-autohotkey-utility","n":"ChatGPT-AutoHotkey-Utility","d":"An AutoHotkey script that uses ChatGPT API to process text.","c":"NLP","sc":3.5,"l":"AutoHotkey","st":88,"ns":3.9},
{"u":"https://github.com/yegor256/jekyll-chatgpt-translate","n":"jekyll-chatgpt-translate","d":"Automated translating of Jekyll pages via ChatGPT: all you need is just an OpenAI API key","c":"NLP","sc":6.5,"l":"Ruby","t":"chatgpt,chatgpt-app,internationalization,jekyll,jekyll-plugin,translation","st":19,"ns":2.6},
{"u":"https://github.com/lewangdev/autotranslate","n":"autotranslate","d":"Videos Transcription and Translation with Faster Whisper and ChatGPT","c":"NLP","sc":3.5,"l":"Jupyter Notebook","st":240,"ns":4.8},
{"u":"https://github.com/sveltor/nextlint","n":"nextlint","d":"A rich text editor, notion like Editor, build with svelte + tiptap. Enhance writing experiences with ChatGPT","c":"NLP","sc":6.5,"l":"TypeScript","t":"editor,gpt,nextlint,openai,svelte,tiptap,wysiwyg","st":204,"ns":4.6},
{"u":"https://github.com/boburmirzo/chatgpt-api-python-sales","n":"chatgpt-api-python-sales","d":"Find real-time sales with AI-powered Python API using ChatGPT and LLM (Large Language Model) App. ","c":"NLP","sc":6.5,"l":"Python","t":"ai,api,chatgpt,large-language-models,python,real-time","st":90,"ns":3.9},
{"u":"https://github.com/nekoparapa/ainiee-chatgpt","n":"AiNiee-chatgpt","d":"一款基于【mtool】或【Translator++】,chatgpt自动批量翻译工具,主要是用来翻译各种RPG游戏。","c":"NLP","sc":3.5,"l":"Python","st":5600,"ns":7.5},
{"u":"https://github.com/beidongjiedeguang/openai-forward","n":"openai-forward","d":"🚀 A forwarding service designed specifically for large language models · Deploy your personal AI agent with just one click · LLM Proxy · OpenAI API Reverse Proxy","c":"NLP","sc":7.5,"l":"Python","t":"chatgpt-proxy,fastapi,llm-proxy,openai-api,openai-proxy,python,rate-limit","st":987,"ns":6.0},
{"u":"https://github.com/nashex/gpt4-playground","n":"gpt4-playground","d":"Clone of OpenAI's ChatGPT and Playground environments to enable experimenting with API keys.","c":"NLP","sc":6.5,"l":"TypeScript","t":"gpt4,gpt4-api,nextjs,nlp,openai,playground","st":382,"ns":5.2},
{"u":"https://github.com/flows-network/github-pr-summary","n":"github-pr-summary","d":"Use ChatGPT to summarize & review GitHub Pull Requests","c":"NLP","sc":5.5,"l":"Rust","t":"chatgpt,codereview,github,gpt4","st":229,"ns":4.7},
{"u":"https://github.com/nicolodiamante/sirigpt","n":"SiriGPT","d":"Unleash the power of SiriGPT: the intersection of ChatGPT’s intelligence, DALL·E's creativity, and Whisper's precise audio transcription for your Apple devices with support of 20 languages.","c":"NLP","sc":6.5,"t":"ai-powered,apple-shortcuts,appleshortcuts,chatgpt,chatgpt-api,dalle2,dallegenerator,generative-ai,generative-images,gpt-3-5-turbo,gpt-4,openai,openai-api,openai-api-chatbot,openai-chatgpt,openai-dall-e,openai-whisper,siri,sirigpt,whisper-ai","st":163,"ns":4.4},
{"u":"https://github.com/chieapp/chie","n":"chie","d":"An extensive desktop app for ChatGPT and other LLMs.","c":"NLP","sc":5.5,"l":"TypeScript","t":"chatgpt,desktop-app,llm,openai","st":180,"ns":4.5},
{"u":"https://github.com/zmh-program/chatnio","n":"chatnio","d":"📚 document of Zh-Website project (using vitepress)","c":"NLP","sc":2.5,"t":"docs,zh-website","st":9100,"ns":7.9},
{"u":"https://github.com/liyucheng09/selective_context","n":"Selective_Context","d":"Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.","c":"NLP","sc":5.5,"l":"Python","t":"chatgpt,llms,nlp","st":418,"ns":5.2},
{"u":"https://github.com/azure/gpt-rag","n":"GPT-RAG","d":"Sharing the learning along the way we been gathering to enable Azure OpenAI at scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cogni...","c":"NLP","sc":6.5,"l":"Bicep","t":"azure,gpt-3,gpt-4,openai","st":1100,"ns":6.1},
{"u":"https://github.com/threecolorfr/llmfordialogdatagenerate","n":"LLMforDialogDataGenerate","d":" Generate dialog data from documents using LLM like ChatGLM2 or ChatGPT;利用ChatGLM2,ChatGPT等大模型根据文档生成对话数据集","c":"NLP","sc":3.5,"l":"Python","st":163,"ns":4.4},
{"u":"https://github.com/linyuxuanlin/auto-i18n","n":"Auto-i18n","d":"使用 ChatGPT 自动将 Markdown 文件批量翻译为多语言 | Auto translate Markdown files to multi languages using ChatGPT","c":"NLP","sc":5.5,"l":"Python","t":"blog,chatgpt,chatgpt-api,python,website","st":374,"ns":5.1},
{"u":"https://github.com/azure-samples/chat-with-your-data-solution-accelerator","n":"chat-with-your-data-solution-accelerator","d":"A Solution Accelerator for the RAG pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This inclu...","c":"NLP","sc":4.5,"l":"Python","st":1200,"ns":6.2},
{"u":"https://github.com/yinan-c/rss-gpt","n":"RSS-GPT","d":"Using ChatGPT to summarize your personalized RSS feeds","c":"NLP","sc":3.5,"l":"Python","st":356,"ns":5.1},
{"u":"https://github.com/songquanpeng/one-api","n":"one-api","d":"OpenAI 接口管理 & 分发系统,支持 Azure、Anthropic Claude、Google PaLM 2、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元,可用于二次分发管理 key,仅单可执行文件,已打包好 Docker 镜像,一键部署,开箱即用. OpenAI key management & redistribution system...","c":"NLP","sc":7.5,"l":"Go","t":"api,api-gateway,azure-openai-api,chatgpt,claude,ernie-bot,gpt,openai,openai-api,proxy","st":33000,"ns":9.0},
{"u":"https://github.com/baichuan-inc/baichuan2","n":"Baichuan2","d":"A series of large language models developed by Baichuan Intelligent Technology","c":"NLP","sc":6.5,"l":"Python","t":"artificial-intelligence,benchmark,ceval,chatgpt,chinese,gpt,gpt-4,huggingface,large-language-models,llama2,mmlu,natural-language-processing","st":4100,"ns":7.2},
{"u":"https://github.com/marqo-ai/marqo","n":"marqo","d":"Vector search for humans. Also available on cloud - cloud.marqo.ai","c":"NLP","sc":6.5,"l":"Python","t":"chatgpt,clip,deep-learning,gpt,hacktoberfest,hnsw,information-retrieval,knn,large-language-models,machine-learning,machinelearning,multi-modal,natural-language-processing,search-engine,semantic-search,tensor-search,transformers,vector-search,vision-language,visual-search","st":5000,"ns":7.4},
{"u":"https://github.com/khoj-ai/khoj","n":"khoj","d":"An AI copilot for your second brain. Search and chat with your personal knowledge base, online or offline","c":"NLP","sc":6.5,"l":"Python","t":"ai,chat,chatgpt,emacs,llm,markdown,obsidian-md,org-mode,personal-assistant,productivity,semantic-search,sentence-transformer","st":34000,"ns":9.1},
{"u":"https://github.com/luodian/otter","n":"Otter","d":"🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.","c":"NLP","sc":7.5,"l":"Python","t":"apple-vision-pro,artificial-inteligence,chatgpt,deep-learning,egocentric-vision,embodied,embodied-ai,foundation-models,gpt-4,instruction-tuning,large-scale-models,machine-learning,multi-modality,visual-language-learning","st":3400,"ns":7.1},
{"u":"https://github.com/josstorer/rwkv-runner","n":"RWKV-Runner","d":"A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for c...","c":"NLP","sc":7.5,"l":"TypeScript","t":"api,api-client,chatgpt,llm,rwkv,tool,wails","st":6300,"ns":7.6},
{"u":"https://github.com/esbatmop/mnbvc","n":"MNBVC","d":"MNBVC (Massive Never-ending BT Vast Chinese corpus) is a large-scale Chinese language corpus. It consists of 40T data, which is comparable to the training data of chatGPT. The MNBVC dataset not onl...","c":"NLP","sc":6.5,"t":"chinese,chinese-language,chinese-nlp,chinese-simplified,corpus-data,nlp,nlp-machine-learning","st":4200,"ns":7.2},
{"u":"https://github.com/tisfeng/easydict","n":"Easydict","d":"一个简洁优雅的词典翻译 macOS App。开箱即用,支持离线 OCR 识别,支持有道词典,🍎 苹果系统词典,🍎 苹果系统翻译,ChatGPT,DeepL,Google,Bing,百度和火山翻译。A concise and elegant Dictionary and Translator macOS App for looking up words and translating text. ","c":"NLP","sc":7.5,"l":"Objective-C","t":"app,baidu,bing,deepl,dictionary,google,macos,ocr,shortcuts,translate,translator,volcano,youdao","st":13000,"ns":8.2},
{"u":"https://github.com/next-gpt/next-gpt","n":"NExT-GPT","d":"Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model","c":"NLP","sc":6.5,"l":"Python","t":"chatgpt,foundation-models,gpt-4,instruction-tuning,large-language-models,llm,multi-modal-chatgpt,multimodal,visual-language-learning","st":3600,"ns":7.1},
{"u":"https://github.com/tavernai/tavernai","n":"TavernAI","d":"Atmospheric adventure chat for AI language models (KoboldAI, NovelAI, Pygmalion, OpenAI chatgpt, gpt-4)","c":"NLP","sc":6.5,"l":"JavaScript","t":"ai,chat,chatgpt,gpt-4,koboldai,novelai,pygmalion","st":2700,"ns":6.9},
{"u":"https://github.com/eth-sri/lmql","n":"lmql","d":"A language for constraint-guided and efficient LLM programming.","c":"NLP","sc":5.5,"l":"Python","t":"chatgpt,gpt-3,huggingface,language-model,programming-language","st":4200,"ns":7.2},
{"u":"https://github.com/farama-foundation/chatarena","n":"chatarena","d":"ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.","c":"NLP","sc":7.5,"l":"Python","t":"ai,artificial-intelligence,chatgpt,gpt-4,large-language-models,multi-agent,multi-agent-reinforcement-learning,multi-agent-simulation,natural-language-processing,python","st":1500,"ns":6.4},
{"u":"https://github.com/moataz-elmesmary/data-science-roadmap","n":"Data-Science-Roadmap","d":"Data Science Roadmap from A to Z","c":"NLP","sc":4.5,"t":"big-data,chatgpt,cheatsheet,cv-template,data-analysis,data-engineering,data-science,data-visualization,deep-learning,interview-questions,linear-algebra,llms,machine-learning,mathematics,neural-network,nlp,probability,python,sql,statistics","st":4200,"ns":7.2},
{"u":"https://github.com/confident-ai/deepeval","n":"deepeval","d":"The Evaluation Framework for LLMs","c":"NLP","sc":5.5,"l":"Python","t":"chatgpt,evaluate-models,evaluate-news-article-with-nlp,evaluation,evaluation-framework,evaluation-metrics,large,llm,llmops","st":15000,"ns":8.4},
{"u":"https://github.com/xorbitsai/inference","n":"inference","d":"Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with ...","c":"NLP","sc":7.5,"l":"Python","t":"artificial-intelligence,chatglm,chatglm2,deployment,flan-t5,ggml,inference,llama2,llm,machine-learning,openai-api,pytorch,whisper,wizardlm","st":9300,"ns":7.9},
{"u":"https://github.com/lupantech/chameleon-llm","n":"chameleon-llm","d":"Codes for \"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models\".","c":"NLP","sc":7.0,"l":"Jupyter Notebook","t":"ai,chatgpt,gpt-4,llm,openai,python,tool","st":1100,"ns":6.1},
{"u":"https://github.com/freedomintelligence/huatuogpt","n":"HuatuoGPT","d":"HuatuoGPT, Towards Taming Language Models To Be a Doctor. (An Open Medical GPT)","c":"NLP","sc":4.0,"l":"Python","st":1300,"ns":6.2},
{"u":"https://github.com/eosphoros-ai/db-gpt-hub","n":"DB-GPT-Hub","d":"A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL","c":"NLP","sc":8.0,"l":"Python","t":"database,datasets,fine-tuning,gpt,llm,nl2sql,sql,text-to-sql,text2sql","st":2000,"ns":6.6},
{"u":"https://github.com/mylxsw/aidea-server","n":"aidea-server","d":"AIdea is a versatile app that supports GPT and domestic large language models such as Tongyi Qianwen and Wenxin Yiyuan. It also supports Stable Diffusion Wenshengtu, Tushengtu, SDXL1.0, super-resol...","c":"NLP","sc":6.5,"l":"Go","t":"ai,chatgpt,gpt,llm,stable-diffusion","st":1700,"ns":6.5},
{"u":"https://github.com/bbycroft/llm-viz","n":"llm-viz","d":"3D Visualization of an GPT-style LLM","c":"NLP","sc":2.5,"l":"TypeScript","st":5400,"ns":7.5},
{"u":"https://github.com/mnotgod96/appagent","n":"AppAgent","d":"AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.","c":"NLP","sc":8.0,"l":"Python","t":"agent,chatgpt,generative-ai,gpt4,gpt4v,llm","st":6700,"ns":7.7},
{"u":"https://github.com/thudm/agentbench","n":"AgentBench","d":"A Comprehensive Benchmark to Evaluate LLMs as Agents","c":"NLP","sc":5.5,"l":"Python","t":"chatgpt,gpt-4,llm,llm-agent","st":3400,"ns":7.1},
{"u":"https://github.com/neumtry/neumai","n":"NeumAI","d":"Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.","c":"NLP","sc":7.0,"l":"Python","t":"ai,chatgpt,data,data-engineering,database,embeddings,etl,llm,llmops,mlops,ops,pipeline,python,rag,retrieval,vector-database,vectors","st":868,"ns":5.9},
{"u":"https://github.com/rasbt/llms-from-scratch","n":"LLMs-from-scratch","d":"Implementing a ChatGPT-like LLM from scratch, step by step","c":"NLP","sc":6.5,"l":"Jupyter Notebook","t":"chatgpt,gpt,large-language-models,llm,python,pytorch","st":92000,"ns":9.9},
{"u":"https://github.com/neelnanda-io/transformerlens","n":"TransformerLens","d":"A library for mechanistic interpretability of GPT-style language models","c":"NLP","sc":4.0,"l":"Python","st":3400,"ns":7.1},
{"u":"https://github.com/kwaikeg/kwaiagents","n":"KwaiAgents","d":"A generalized information-seeking agent system with Large Language Models (LLMs).","c":"NLP","sc":6.5,"l":"Python","t":"agi,autogpt,autonomous-agents,chatgpt,gpt,large-language-models,localllm","st":1200,"ns":6.2},
{"u":"https://github.com/openmotionlab/motiongpt","n":"MotionGPT","d":"[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs","c":"NLP","sc":7.0,"l":"Python","t":"3d-generation,chatgpt,gpt,language-model,motion,motion-generation,motiongpt,multi-modal,text-driven,text-to-motion","st":1900,"ns":6.6},
{"u":"https://github.com/goldfishh/chatgpt-tool-hub","n":"chatgpt-tool-hub","d":"An open-source chatgpt tool ecosystem where you can combine tools with chatgpt and use natural language to do anything.","c":"NLP","sc":4.0,"l":"Python","st":1300,"ns":6.2},
{"u":"https://github.com/rucaibox/llmsurvey","n":"LLMSurvey","d":"The official GitHub page for the survey paper \"A Survey of Large Language Models\".","c":"NLP","sc":6.5,"l":"Python","t":"chain-of-thought,chatgpt,in-context-learning,instruction-tuning,large-language-models,llm,llms,natural-language-processing,pre-trained-language-models,pre-training,rlhf","st":12000,"ns":8.2},
{"u":"https://github.com/evanhu1/talk2arxiv","n":"talk2arxiv","d":"Talk to any ArXiv paper using ChatGPT","c":"NLP","sc":6.0,"l":"TypeScript","t":"arxiv,gpt,llm,open-source,rag,research","st":529,"ns":5.4},
{"u":"https://github.com/fjrdomingues/autopilot","n":"autopilot","d":"Code Autopilot, a tool that uses GPT to read a codebase, create context and solve tasks.","c":"NLP","sc":5.5,"l":"JavaScript","t":"ai,code-assistant,gpt,gpt-4","st":613,"ns":5.6},
{"u":"https://github.com/kenyony/openai-forward","n":"openai-forward","d":"🚀 大语言模型高效转发服务 · An efficient forwarding service designed for LLMs. · OpenAI API Reverse Proxy","c":"NLP","sc":7.0,"l":"Python","t":"llm,openai,openai-api,openai-proxy,proxy,python,rate-limit","st":987,"ns":6.0},
{"u":"https://github.com/nvidia/fastertransformer","n":"FasterTransformer","d":"Transformer related optimization, including BERT, GPT","c":"NLP","sc":6.0,"l":"C++","t":"bert,gpt,pytorch,transformer","st":6400,"ns":7.6},
{"u":"https://github.com/polyrabbit/hacker-news-digest","n":"hacker-news-digest","d":":newspaper: Let ChatGPT Summarize Hacker News for You","c":"NLP","sc":7.0,"l":"Python","t":"chatgpt,chatgpt-api,crawler,data-extraction,extract-summaries,hacker-news,hacker-news-digest,hacker-news-reader,machine-learning,news-aggregator,openai,openai-api,python,rss,spider","st":753,"ns":5.8},
{"u":"https://github.com/lancemoe/openai-translator","n":"openai-translator","d":"A translator that uses OpanAI.","c":"NLP","sc":6.0,"l":"TypeScript","t":"chatgpt,daisyui,openai,pwa,react,tailwindcss,translator,translator-app,vite","st":406,"ns":5.2},
{"u":"https://github.com/xianshang33/llm-paper-daily","n":"llm-paper-daily","d":"Daily updated LLM papers. 每日更新 LLM 相关的论文,欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个","c":"NLP","sc":4.5,"t":"agent,chatgpt,large-language-models,llm,rag","st":1200,"ns":6.2},
{"u":"https://github.com/retkowsky/azure-openai-demos","n":"Azure-OpenAI-demos","d":"Azure Open AI (demos, documentation, accelerators).","c":"NLP","sc":6.5,"l":"Jupyter Notebook","t":"azure,azure-cognitive-services,azure-openai,chatgpt,dall-e,embeddings,langchain-python,llm,openai","st":750,"ns":5.8},
{"u":"https://github.com/skywalkerdarren/chatweb","n":"chatWeb","d":"ChatWeb can crawl web pages, read PDF, DOCX, TXT, and extract the main content, then answer your questions based on the content, or summarize the key points.","c":"NLP","sc":7.5,"l":"Python","t":"ai,chatgpt,crawler,docx,embedding,faiss,gpt,gpt-35-turbo,news-extractor,newspaper,openai,pdf,pgvector,postgresql,vector-database","st":912,"ns":5.9},
{"u":"https://github.com/video-db/streamrag","n":"StreamRAG","d":"Video Search and Streaming Agent 🕵️♂️","c":"NLP","sc":6.0,"l":"Python","t":"agent,chatgpt,llm,rag,search,search-engine,video,video-processing,video-streaming","st":504,"ns":5.4},
{"u":"https://github.com/gptscript-ai/gptscript","n":"gptscript","d":"Natural Language Programming","c":"NLP","sc":3.0,"l":"Go","st":3300,"ns":7.0},
{"u":"https://github.com/muennighoff/sgpt","n":"sgpt","d":"SGPT: GPT Sentence Embeddings for Semantic Search","c":"NLP","sc":6.0,"l":"Jupyter Notebook","t":"gpt,information-retrieval,language-model,large-language-models,neural-search,retrieval,semantic-search,sentence-embeddings,sgpt,text-embedding","st":874,"ns":5.9},
{"u":"https://github.com/visual-openllm/visual-openllm","n":"visual-openllm","d":"something like visual-chatgpt, the open-source version of Wenxin Yiyuan","c":"NLP","sc":3.5,"l":"Python","st":1200,"ns":6.2},
{"u":"https://github.com/gpt-fathom/gpt-fathom","n":"GPT-Fathom","d":"GPT-Fathom is an open-source and reproducible LLM evaluation suite, benchmarking 10+ leading open-source and closed-source LLMs as well as OpenAI's earlier models on 20+ curated benchmarks under al...","c":"NLP","sc":5.0,"l":"Python","st":343,"ns":5.1},
{"u":"https://github.com/opencodeinterpreter/opencodeinterpreter","n":"OpenCodeInterpreter","d":"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. ...","c":"NLP","sc":5.0,"l":"Python","st":1700,"ns":6.5},
{"u":"https://github.com/wewehao/flutter_chatgpt","n":"flutter_chatgpt","d":"Flutter ChatGPT APP. The chatgpt chat app implemented by flutter supports custom modes and contextual continuous dialogue. In addition, it supports admob advertisement configuration, accessing open...","c":"NLP","sc":7.0,"l":"Dart","t":"android,chatgpt,firebase,flutter,ios","st":462,"ns":5.3},
{"u":"https://github.com/ai00-x/ai00_server","n":"ai00_server","d":"A localized open-source AI server that is better than ChatGPT.","c":"NLP","sc":7.0,"l":"Rust","t":"ai,chatgpt,chatgpt-api,chatgpt4,chatgpt4free,llm,openai,openai-api,rwkv","st":612,"ns":5.6},
{"u":"https://github.com/robustnlp/cipherchat","n":"CipherChat","d":"A framework to evaluate the generalization capability of safety alignment for LLMs","c":"NLP","sc":7.0,"l":"Python","t":"alignment,chatgpt,gpt-4-0613,jailbreak,large-language-models,llm,security","st":629,"ns":5.6},
{"u":"https://github.com/batsresearch/bonito","n":"bonito","d":"A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.","c":"NLP","sc":7.0,"l":"Python","t":"domain-adaptation,gpt,llm,synthetic-data,synthetic-dataset-generation,task-adaptation,zero-shot-learning","st":824,"ns":5.8},
{"u":"https://github.com/ruoccofabrizio/azure-open-ai-embeddings-qna","n":"azure-open-ai-embeddings-qna","d":"A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves...","c":"NLP","sc":6.0,"l":"Python","t":"azureopenai","st":849,"ns":5.9},
{"u":"https://github.com/openinterpreter/open-interpreter","n":"open-interpreter","d":"A natural language interface for computers","c":"NLP","sc":6.0,"l":"Python","t":"chatgpt,gpt-4,interpreter,javascript,nodejs,python","st":63000,"ns":9.6},
{"u":"https://github.com/thu-keg/evaluationpapers4chatgpt","n":"EvaluationPapers4ChatGPT","d":"Resource, Evaluation and Detection Papers for ChatGPT","c":"NLP","sc":5.0,"t":"chatgpt,detection,evaluation,large-language-models,resource","st":455,"ns":5.3},
{"u":"https://github.com/zylon-ai/private-gpt","n":"private-gpt","d":"Interact with your documents using the power of GPT, 100% privately, no data leaks","c":"NLP","sc":4.0,"l":"Python","st":57000,"ns":9.5},
{"u":"https://github.com/open-compass/vlmevalkit","n":"VLMEvalKit","d":"Open-source evaluation toolkit of large vision-language models (LVLMs), support GPT-4v, Gemini, QwenVLPlus, 30+ HF models, 15+ benchmarks","c":"NLP","sc":7.5,"l":"Python","t":"benchmark,chatgpt,clip,computer-vision,evaluation,gpt,gpt-4v,gpt4,large-language-models,llava,llm,minigpt4,mplug-owl,multi-modal,openai,openai-api,pytorch,qwen,vit,vqa","st":4100,"ns":7.2},
{"u":"https://github.com/kseseu/llmpapers","n":"LLMPapers","d":"Papers & Works for large languange models (ChatGPT, GPT-3, Codex etc.).","c":"NLP","sc":5.5,"l":"TeX","t":"chatgpt,codex,gpt-3,large-language-models","st":314,"ns":5.0},
{"u":"https://github.com/stoerr/aigenpipeline","n":"AIGenPipeline","d":"AI based code generation pipeline: command line tool and framework for systematic code generation using AI in a build process","c":"NLP","sc":8.0,"l":"Java","t":"ai,chatgpt,code-generation,code-generator,llm,openai,software-development","st":5,"ns":1.6},
{"u":"https://github.com/neurocult/agency","n":"agency","d":"🕵️♂️ Library designed for developers eager to explore the potential of Large Language Models (LLMs) and other generative AI through a clean, effective, and Go-idiomatic approach.","c":"NLP","sc":8.0,"l":"Go","t":"agents,ai,artificial-general-intelligence,artificial-intelligence,artificial-neural-networks,autonomous-agents,chatgpt,generative-ai,go,golang,gpt,language-models,llm,llmops,machine-learning,neural-network,nlp,openai,rag,vector-database","st":507,"ns":5.4}
]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |