Skip to content

taishi-i/awesome-ChatGPT-repositories / skills/awesome-chatgpt-search

awesome-chatgpt-search

Unverified

Search 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.

data/repos-reimplementations.json

View on GitHub
[
{"u":"https://github.com/lucidrains/palm-rlhf-pytorch","n":"PaLM-rlhf-pytorch","d":"Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM","c":"Reimplementations","sc":8.0,"l":"Python","t":"artificial-intelligence,attention-mechanisms,deep-learning,human-feedback,reinforcement-learning,transformers","st":7900,"ns":7.8},
{"u":"https://github.com/karpathy/mingpt","n":"minGPT","d":"A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training","c":"Reimplementations","sc":4.0,"l":"Python","st":24000,"ns":8.8},
{"u":"https://github.com/amazon-science/mm-cot","n":"mm-cot","d":"Official implementation for \"Multimodal Chain-of-Thought Reasoning in Language Models\" (stay tuned and more will be updated)","c":"Reimplementations","sc":5.0,"l":"Python","st":4000,"ns":7.2},
{"u":"https://github.com/jaymody/picogpt","n":"picoGPT","d":"An unnecessarily tiny implementation of GPT-2 in NumPy.","c":"Reimplementations","sc":7.0,"l":"Python","t":"deep-learning,gpt,gpt-2,large-language-models,machine-learning,neural-network,nlp,python","st":3500,"ns":7.1},
{"u":"https://github.com/eleutherai/gpt-neox","n":"gpt-neox","d":"An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.","c":"Reimplementations","sc":6.0,"l":"Python","t":"deepspeed-library,gpt-3,language-model,transformers","st":7400,"ns":7.7},
{"u":"https://github.com/burhanultayyab/gptzero","n":"GPTZero","d":"An open-source implementation of GPTZero","c":"Reimplementations","sc":3.0,"l":"Python","st":590,"ns":5.5},
{"u":"https://github.com/ridgerchu/spikegpt","n":"SpikeGPT","d":"Implementation of \"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks\"","c":"Reimplementations","sc":4.0,"l":"Python","st":900,"ns":5.9},
{"u":"https://github.com/nouamanetazi/bloomz.cpp","n":"bloomz.cpp","d":"C++ implementation for BLOOM","c":"Reimplementations","sc":5.0,"l":"C","t":"bloom,cpp,multilingual","st":811,"ns":5.8},
{"u":"https://github.com/apple/ml-ane-transformers","n":"ml-ane-transformers","d":"Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)","c":"Reimplementations","sc":3.5,"l":"Python","st":2700,"ns":6.9},
{"u":"https://github.com/huggingface/swift-coreml-transformers","n":"swift-coreml-transformers","d":"Swift Core ML 3 implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT for Question answering. Other Transformers coming soon!","c":"Reimplementations","sc":5.0,"l":"Swift","st":1700,"ns":6.5},
{"u":"https://github.com/hundredblocks/large-model-parallelism","n":"large-model-parallelism","d":"Functional local implementations of main model parallelism approaches","c":"Reimplementations","sc":4.0,"l":"Jupyter Notebook","st":95,"ns":4.0},
{"u":"https://github.com/lucidrains/memorizing-transformers-pytorch","n":"memorizing-transformers-pytorch","d":"Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch","c":"Reimplementations","sc":8.0,"l":"Python","t":"approximate-nearest-neighbors,artificial-intelligence,attention-mechanism,deep-learning,memory,retrieval,transformers","st":644,"ns":5.6},
{"u":"https://github.com/lightning-ai/lit-llama","n":"lit-llama","d":"Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.","c":"Reimplementations","sc":5.0,"l":"Python","st":6100,"ns":7.6},
{"u":"https://github.com/lightning-ai/lit-parrot","n":"lit-parrot","d":"Implementation of the StableLM/Pythia/INCITE language models based on nanoGPT. Supports flash attention, LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.","c":"Reimplementations","sc":4.5,"l":"Python","st":13000,"ns":8.2},
{"u":"https://github.com/ricklamers/gpt-code-ui","n":"gpt-code-ui","d":"An open source implementation of OpenAI's ChatGPT Code interpreter","c":"Reimplementations","sc":5.5,"l":"Python","t":"chatgpt,gpt,llms,openai","st":3600,"ns":7.1},
{"u":"https://github.com/zeqiang-lai/draggan","n":"DragGAN","d":"Online Demo and Implementation of DragGAN - \"Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold\"","c":"Reimplementations","sc":6.5,"l":"Python","t":"draggan,gradio-interface,image-editing,image-generation,interngpt","st":5000,"ns":7.4},
{"u":"https://github.com/keyvank/femtogpt","n":"femtoGPT","d":"Pure Rust implementation of a minimal Generative Pretrained Transformer","c":"Reimplementations","sc":6.5,"l":"Rust","t":"from-scratch,gpt,llm,machine-learning,neural-network,rust","st":936,"ns":5.9},
{"u":"https://github.com/lightning-ai/lit-gpt","n":"lit-gpt","d":"Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2....","c":"Reimplementations","sc":4.5,"l":"Python","st":13000,"ns":8.2},
{"u":"https://github.com/turboderp/exllama","n":"exllama","d":"A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.","c":"Reimplementations","sc":3.5,"l":"Python","st":2900,"ns":6.9},
{"u":"https://github.com/deepgraphlearning/astarnet","n":"AStarNet","d":"Official implementation of A* Networks","c":"Reimplementations","sc":2.5,"l":"Python","st":155,"ns":4.4},
{"u":"https://github.com/shroominic/codeinterpreter-api","n":"codeinterpreter-api","d":"Open source implementation of the ChatGPT Code Interpreter 👾","c":"Reimplementations","sc":6.5,"l":"Python","t":"chatgpt,chatgpt-code-generation,code-interpreter,codeinterpreter,langchain,llm-agent","st":3900,"ns":7.2},
{"u":"https://github.com/mrgreyfun/local-code-interpreter","n":"Local-Code-Interpreter","d":"A local implementation of OpenAI's ChatGPT Code Interpreter.","c":"Reimplementations","sc":3.5,"l":"Python","st":313,"ns":5.0},
{"u":"https://github.com/openllmai/chatpixiu","n":"ChatPiXiu","d":"ChatPiXiu: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXiu-貔貅 means fortune.","c":"Reimplementations","sc":6.5,"t":"chatglm,chatgpt,chatgpt-alternatives,chatgpt-app,chatgpt-bot,chatzhangsan,chatzhihu,chinese-chatgpt,llama,openllm,openllmai","st":266,"ns":4.9},
{"u":"https://github.com/lifeiteng/vall-e","n":"vall-e","d":"PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html","c":"Reimplementations","sc":6.5,"l":"Python","t":"chatgpt,in-context-learning,large-language-models,text-to-speech,tts,vall-e,valle","st":2200,"ns":6.7},
{"u":"https://github.com/shibing624/textgen","n":"textgen","d":"TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型,实现了包括LLaMA,ChatGLM,BLOOM,GPT2,Seq2Seq,BART,T5,UDA等模型的训练和预测,开箱即用。","c":"Reimplementations","sc":8.0,"l":"Python","t":"bart,bert,chatglm,chatgpt,gpt2,llama,seq2seq,t5,text-generation,textgen,xlnet","st":979,"ns":6.0},
{"u":"https://github.com/conceptofmind/lamda-rlhf-pytorch","n":"LaMDA-rlhf-pytorch","d":"Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.","c":"Reimplementations","sc":7.0,"l":"Python","t":"artificial-intelligence,attention-mechanism,deep-learning,human-feedback,machine-learning,reinforcement-learning,transformers","st":469,"ns":5.3},
{"u":"https://github.com/brainlid/langchain","n":"langchain","d":"Elixir implementation of a LangChain style framework.","c":"Reimplementations","sc":5.5,"l":"Elixir","t":"chatgpt,elixir,langchain,llm","st":1200,"ns":6.2},
{"u":"https://github.com/adityang/kan-gpt","n":"kan-gpt","d":"The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling","c":"Reimplementations","sc":8.0,"l":"Python","t":"gpt,kanformers,kolmogorov-arnold-networks,kolmogorov-arnold-representation,llm,text-generation,transformers","st":725,"ns":5.7},
{"u":"https://github.com/voidful/textrl","n":"TextRL","d":"Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)","c":"Reimplementations","sc":8.0,"l":"Python","t":"chatgpt,controlled-nlg,gpt-2,gpt-3,language-model,nlg,nlp,pytorch,reinforcement-learning,rlhf","st":564,"ns":5.5},
{"u":"https://github.com/sharegpt4omni/sharegpt4video","n":"ShareGPT4Video","d":"An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","c":"Reimplementations","sc":6.5,"l":"Python","t":"chatgpt,gpt,gpt-4v,large-language-models,large-multimodal-models,large-video-language-models,large-vision-language-models,sora,text-to-video","st":1100,"ns":6.1},
{"u":"https://github.com/affjljoo3581/gpt2","n":"GPT2","d":"PyTorch Implementation of OpenAI GPT-2","c":"Reimplementations","sc":6.0,"l":"Python","t":"gpt2,language-model,natural-language-generation,natural-language-processing,nlp,pytorch,transformer","st":358,"ns":5.1},
{"u":"https://github.com/mael-zys/t2m-gpt","n":"T2M-GPT","d":"(CVPR 2023) Pytorch implementation of “T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations”","c":"Reimplementations","sc":7.0,"l":"Python","t":"gpt,motion-generation,vq-vae","st":758,"ns":5.8},
{"u":"https://github.com/dlr-rm/stable-baselines3","n":"stable-baselines3","d":"PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.","c":"Reimplementations","sc":7.0,"l":"Python","t":"baselines,gsde,gym,machine-learning,openai,python,pytorch,reinforcement-learning,reinforcement-learning-algorithms,robotics,sb3,sde,stable-baselines,toolbox","st":13000,"ns":8.2},
{"u":"https://github.com/collabora/whisperlive","n":"WhisperLive","d":"A nearly-live implementation of OpenAI's Whisper.","c":"Reimplementations","sc":6.0,"l":"Python","t":"dictation,obs,openai,tensorrt,tensorrt-llm,text-to-speech,translation,voice-recognition,whisper,whisper-tensorrt","st":4000,"ns":7.2},
{"u":"https://github.com/nirdiamant/genai_agents","n":"GenAI_Agents","d":"This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive A...","c":"Reimplementations","sc":7.5,"l":"Jupyter Notebook","t":"agents,ai,genai,langchain,langgraph,llms,openai,tutorials","st":22000,"ns":8.7},
{"u":"https://github.com/juncongmoo/chatllama","n":"chatllama","d":"ChatLLaMA 📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT","c":"Reimplementations","sc":4.5,"l":"Python","st":1200,"ns":6.2},
{"u":"https://github.com/dzhng/deep-research","n":"deep-research","d":"My own open source implementation of OpenAI's new Deep Research agent. Get the same capability without paying $200.  You can even tweak the behavior of the agent with adjustable breadth and depth. ...","c":"Reimplementations","sc":7.0,"l":"TypeScript","t":"agent,ai,gpt,o3-mini,research","st":19000,"ns":8.6},
{"u":"https://github.com/fareedkhan-dev/all-rl-algorithms","n":"all-rl-algorithms","d":"Implementation of all RL algorithms in a simpler way","c":"Reimplementations","sc":7.0,"l":"Jupyter Notebook","t":"agent,llm,openai,python,reinforcement-learning,rl","st":1600,"ns":6.4},
{"u":"https://github.com/fareedkhan-dev/all-rag-techniques","n":"all-rag-techniques","d":"Implementation of all RAG techniques in a simpler way","c":"Reimplementations","sc":7.0,"l":"Jupyter Notebook","t":"ai,llm,llms,multi-modal,openai,python,rag"},
{"u":"https://github.com/m4thyou/tokendagger","n":"TokenDagger","d":"High-Performance Implementation of OpenAI's TikToken.","c":"Reimplementations","sc":4.0,"l":"C++","st":475,"ns":5.4},
{"u":"https://github.com/rollczi/litecommands","n":"LiteCommands","d":"☄️ LiteCommands - Command framework for Velocity, Bukkit, Paper, BungeeCord, Minestom, Sponge, Fabric, JDA and future implementations.","c":"Reimplementations","sc":8.0,"l":"Java","t":"bukkit,chatgpt,discord-bot,fabric,hacktoberfest,java,jda,kyori,litecommands,minecraft,minestom,papermc,spigot,sponge,spongepowered,velocity,velocitypowered","st":195,"ns":4.6},
{"u":"https://github.com/qx-labs/agents-deep-research","n":"agents-deep-research","d":"An implementation of iterative deep research using the OpenAI Agents SDK","c":"Reimplementations","sc":7.0,"l":"Python","t":"agentic-ai,agents,deep-research,deepresearch,llms,openai","st":762,"ns":5.8}
]
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 323kUpdated Claude CodeCodexVerifiedInstall