João Galego's repositories
MetaGPT
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
opro
official code for "Large Language Models as Optimizers"
AI-Scientist
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
autogen
A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap
ScrapeGraphAI-Bedrock
Streamlit app that demonstrates how to integrate Amazon Bedrock ⛰️ and ScrapeGraphAI 🕷️
Scrapegraph-LabLabAI-Hackathon
Code for the streamlit demo of Scrapegraph-ai for GPT4-hackaton
sqlite-rembed
A SQLite extension for generating text embeddings from remote APIs (OpenAI, Nomic, Ollama, llamafile...)
llm-colosseum
Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM
Quizplosion
Turns quizdown-formatted markdown files into quizzes 💣💥
LLaMbda.cpp
Run LLaMA.cpp at scale on AWS Lambda using function URLs and response streaming
concordia
A library for generative social simulation
Hack-GraphRAG
Learn how to run GraphRAG pipelines backed by Amazon Bedrock using LiteLLM proxy 🌄
LLM-PuzzleTest
This repository is maintained to release dataset and models for multimodal puzzle reasoning.
dspy
DSPy: The framework for programming—not prompting—foundation models
SLaMbda
Run SLMs at scale on AWS Lambda 🤏
deploy-langserve-aws
Learn how to deploy 🦜🔗 LangChain applications with 🦜️🏓 LangServe in minutes on Amazon ECS and AWS Fargate using AWS Copilot.
project-lakechain
:zap: Cloud-native, AI-powered, document processing pipelines on AWS.
amazon-rekognition-code-samples
Amazon Rekognition Code Samples
LambdaChain
Learn how to run LangChain.js apps on AWS Lambda
Scrapegraph-ai
Python scraper based on AI
ChatDev
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
bedrock-access-gateway
OpenAI-Compatible RESTful APIs for Amazon Bedrock
auto-code-rover
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 15.95% tasks in full SWE-bench
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.
FrugalBedrock
FrugalGPT-style LLM cascades with Amazon Bedrock for fighting hallucinations 🍄
chroma
the AI-native open-source embedding database
MemGPT
Building persistent LLM agents with long-term memory 📚🦙
LLMTest_NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy