LangChain, ReAct

hwchase17/langchain: ⚡ Building applications with LLMs through composability ⚡

langchain/ at master · hwchase17/langchain · GitHub

Welcome to LangChain — 🦜🔗 LangChain 0.0.132

[2302.07842] Augmented Language Models: a Survey

[2302.04761] Toolformer: Language Models Can Teach Themselves to Use Tools

ACT-1: Transformer for Actions

Could you train a ChatGPT-beating model for $85,000 and run it in a browser?

A simple Python implementation of the ReAct pattern for LLMs | Simon Willison’s TILs

Run Python code in a WebAssembly sandbox | Simon Willison’s TILs

A simple Python wrapper for the ChatGPT API | Simon Willison’s TILs

ReAct: Synergizing Reasoning and Acting in Language Models

The surprising ease and effectiveness of AI in a loop (Interconnected)

Fuzzy API composition: querying NBA stats with GPT-3 + Statmuse + Langchain

OODA loop - Wikipedia

natbot/ at main · nat/natbot · GitHub

openai/chatgpt-retrieval-plugin: The ChatGPT Retrieval Plugin lets you easily search and find personal or work documents by asking questions in everyday language.

homanp/langchain-ui: 🧬 The open source chat-ai toolkit

nat/natbot: Drive a browser with GPT-3

m1guelpf/browser-agent: A browser AI agent, using GPT-4

refcell/run-wild: Augment GPT-4 Environment Access

(1) Yohei on Twitter: “So this “AI founder” experiment is kind of blowing my mind. I set an objective, and say “your first task is to create your next task”. It then continues to generate and reprioritize its own task list as it executes them one by one. Only hooked up to search now. Kinda scary.” / Twitter

(1) Yohei on Twitter: “🔥1/8 Introducing ”🤖 Task-driven Autonomous Agent” An agent that leverages @openai’s GPT-4, @pinecone vector search, and @LangChainAI framework to autonomously create and perform tasks based on an objective. “Paper”: [More 🔽]” / Twitter

Task-driven Autonomous Agent Utilizing GPT-4, Pinecone, and LangChain for Diverse Applications – Yohei Nakajima

(1) Yohei (@yoheinakajima) / Twitter


[WIP] TypeScript BabyAGI 🚀✨ by yourbuddyconner · Pull Request #5 · Intuitive-Systems/react-agent-ts

Torantulino/Auto-GPT: An experimental open-source attempt to make GPT-4 fully autonomous.

KaneCohen/Auto-GPT at dev

microsoft/JARVIS: JARVIS, a system to connect LLMs with ML community

[2303.16434] TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs

[2303.17580] HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace

[2303.17071] DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents

[2303.17491] Language Models can Solve Computer Tasks

Can LLMs Critique and Iterate on Their Own Outputs? | Eric Jang

pHaeusler/micro-agent: A tiny implementation of an autonomous agent powered by LLMs (OpenAI GPT-4)

Ozennefr/GPPPT: A simple one file python script that executes AI processes defined in YML.

PrefectHQ/marvin: 🤖🪄 A batteries-included library for building AI-powered software

Welcome to Marvin - Marvin

Configure OpenAI - Marvin

Torantulino/AI-Functions: AI-Powered Function Magic: Never code again with GPT models!

(1) Luke ⚡ (@theluk246) / Twitter

langchain-ChatGLM/ at master · imClumsyPanda/langchain-ChatGLM · GitHub

Trending repositories on GitHub today




jina-ai/auto-gpt-web: Web-based platform that makes GPT-4 fully autonomous.

cfortuner/promptable: Build LLM apps in Typescript/Javascript. 🧑‍💻 🧑‍💻 🧑‍💻 🚀 🚀 🚀

Shardj/code-genie-cli: Uses OpenAI’s GPT API to turn natural language into Python code and execute it on your desktop.

Farama-Foundation/miniwob-plusplus: MiniWoB++: a web interaction benchmark for reinforcement learning

MiniWoB++ Documentation

World of Bits: An Open-Domain Platform for Web-Based Agents - shi17a.pdf

[1802.08802] Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration

abhiprojectz/SingularGPT: SingularGPT - Gives GPT eyes & hands to automate your device using AI based vision.

reworkd/AgentGPT: 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

farizrahman4u/loopgpt: Modular Auto-GPT Framework

muellerberndt/micro-gpt: A minimal generic autonomous agent based on GPT3.5/4. Can analyze stock prices, perform network security tests, create art, and order pizza.


GPT-4 Auto Coder · Streamlit

rumpfmax/Multi-GPT: An experimental open-source attempt to make GPT-4 fully autonomous.

piyushK52/hal-agi: AGI assistant

GoalGPT by Nando.AI

context-labs/babyagi-ts: A CLI tool for creating and managing BabyGI agents


The Complete Beginners Guide To Autonomous Agents

microsoft/semantic-kernel: Integrate cutting-edge LLM technology quickly and easily into your apps

pashpashpash/vault-ai: 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.


seanpixel/council-of-ai: Security measure for agentic LLMs using a council of AIs moderted by a veto system. The council judges an agent’s actions outputs based on specified categories.

seanpixel/Philoshoggoths: Make philosophical GPT-4 instances talk to each other.



Cognosys: Your personal AI Agent


eumemic/ai-legion: An LLM-powered autonomous agent platform



HeyGPT - Empower your ChatGPT experience

Browse GPT

ibiscp/LLM-IMDB: Proof of concept app using LangChain and LLMs to retrieve information from graphs, built with the IMDB dataset

imartinez/privateGPT: Interact privately with your documents using the power of GPT, 100% privately, no data leaks

uilicious/english-compiler: POC AI based Compiler, for converting english based markdown specs, into functional code

smol-ai/developer: with 100k context windows on the way, it’s now feasible to for every dev to have their own smol developer

irgolic/AutoPR: Fix issues with AI-generated pull requests, powered by ChatGPT

Transformers Agent

Hannibal046/Awesome-LLM: Awesome-LLM: a curated list of Large Language Model

pbhu1024/awesome-augmented-language-model: ⚡Research papers about leveraging the capabilities of language models⚡

microsoft/guidance: A guidance language for controlling large language models.

Chainlit/chainlit: Build Python LLM apps in minutes ⚡️

Large sequence models for software development activities – Google AI Blog

Vercel AI SDK

Documentation - Vercel AI SDK