Jie's repositories
airbyte
Data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes.
AppAgent
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
llama_index
LlamaIndex (GPT Index) is a data framework for your LLM applications
Backfill-GA4-to-BigQuery
Backfill-GA4-to-BigQuery" repository offers a solution for users to backfill their GA4 data into BigQuery. This is useful for those who need historical data from the start of their GA4 property, as GA4 data is typically only available in BigQuery after linking the two services. Our solution provides a complete backfill of data to BigQuery
code-wizard
🧙AutoDev: The AI-powered coding wizard with multilingual support 🌐, auto code generation 🏗️, and a helpful bug-slaying assistant 🐞! Customizable prompts 🎨 and a magic Auto Dev/Testing/Document/Agent feature 🧪 included! 🚀
dspy
DSPy: The framework for programming—not prompting—foundation models
honcho
User context management solution for building AI Agents and LLM powered applications.
json_repair
A python module to repair broken JSON, very useful with LLMs
llm.c
LLM training in simple, raw C/CUDA
ludwig
Low-code framework for building custom LLMs, neural networks, and other AI models
memary
Longterm Memory for Autonomous Agents.
openai-cookbook
Examples and guides for using the OpenAI API
OpenDevin
🐚 OpenDevin: Code Less, Make More
ragas
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
reader
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
Scrapegraph-ai
Python scraper based on AI
site-analysis
analyze website using gpt
snowplow
The enterprise-grade behavioral data engine (web, mobile, server-side, webhooks), running cloud-natively on AWS and GCP
superagent
🥷 Superagent - The agent framework for large language models
swarms
Build, Deploy, and Scale Reliable Swarms of Autonomous Agents. Join our Community: https://discord.gg/DbjBMJTSWD
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.
TikTokLive
Python library to receive live stream events (comments, gifts, etc.) in realtime from TikTok LIVE.
trl
Train transformer language models with reinforcement learning.
unstructured
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.