Agents

Before Google integrated Gemini into Google Workspace & Gmail, I built a multi-agent AI system using CrewAI, Flask, & React. Summarizes Gmail emails, generates replies with human review, extracts AI newsletters, & posts to X/LinkedIn. Customizable, scalable, & modern.

Generate solution architecture diagrams

🐧 is currently a work in progress... Stay tuned!

This repository hosts a Jupyter notebook that demonstrates the seamless integration of the Bard API with the LangChain library. By leveraging the capabilities of both platforms, we've crafted a custom Language Learning Model (LLM) that allows users to harness the power of Bard within the LangChain ecosystem.

Controllable and Transparent LLM Application Framework

专为《原神》打造——利用视觉 AI 代理进行云游戏，让您无需亲自操作

An MCP server for real-time financial market data. Access stock prices, options chains, and technical analysis tools via conversational AI

A general-purpose, command-line AI agent built from scratch.

Autonomous SRE agent built on Hermes - detects, heals, and learns from production incidents. Uses Memory + Skills + Cron + Gateway + Subagents + Atropos RL.

A procedurally generated dataset of cryptographic CTF challenges for training and evaluating LLM agents with Reinforcement Learning.

A sophisticated multi-agent system designed to handle customer queries related to InfinitePay services through intelligent routing and specialized agent responses.

A composable Python DSL for building GBNF grammars compatible with llama.cpp.

🤖📜 AI Agents & Planning papers hub

Moje rozwiązania do zadań z kursu AI_devs3

PaperDoctor 是一个用于科研论文审阅与修改的 AI Agent。

A Python-based agent showcasing the use of Google's Gemini 2.0 Flash Thinking Experimental model to reason by combining search results with user queries

An autonomous, context-aware AI Code Review Agent for GitLab. Powered by multi-LLMs (OpenAI, Anthropic, Gemini) with a self-learning feedback loop to enforce repository best practices.

A Query-Answer chatbot for PDFs using local Large language and Embeddings models. Please read this readme fully before using.

Digital Artificial Intelligence Agent

Make LLM workflows explicit and deterministic

a basic proof-of-concept implementation of https://python.langchain.com/docs/use_cases/question_answering/

Intelligent RAG system with knowledge graphs. Processes documents → extracts entities & relationships → stores in Neo4j → enables semantic search & AI-powered Q&A with citations. 🔗 Where documents become knowledge graphs. Advanced RAG system that turns your files into an intelligent, queryable knowledge base.

A comprehensive library for building Deno-based MCP (Model Context Protocol) servers with OAuth and workflow capabilities.

This project provides an API for uploading PDF documents and extracting structured summaries using either OpenAI's GPT-4o or Anthropic's Claude models. It is optimized for environmental and agricultural reports, transforming unstructured PDF content into structured JSON for downstream use.