Data agents

Zerolinear — AI research lab and home of the Zeline open-source agentic AI framework.

A lightweight AI agent which reads and summarizes research papers for you.

Webapp to answer questions about my resume leveraging Langchain, OpenAI, Streamlit

Template for an AI application that extracts the job information from a job description using openAI functions and langchain

Course Work on Langchain Python Framework for Large Language Models, modified to use a provided dataset.

This is a repository to let you know the implementation of a basic RAG pipeline using LangChain in Supabase Edge Functions.

NeuralCache is a drop-in reranker for Retrieval-Augmented Generation (RAG) that learns which context the model actually uses.

Part of the LangChain.NET project. Has separate abstractions, does not contain dependencies on the main project and can be used independently

This project has implemented the RAG function on Jetson and supports TXT and PDF document formats. It uses MLC for 4-bit quantization of the Llama2-7b model, utilizes ChromaDB as the vector database, and connects these features with Llama_Index. I hope you like this project.

Framework for RAG over Excalidraw canvas data

Local-first LLM wiki for research workflows with Obsidian, a dashboard, and a macOS menubar runtime.

Apache Flink MCP Server is a Model Context Protocol (MCP) implementation that empowers AI assistants and large language models to interact directly with Apache Flink clusters through natural language. It enables intelligent monitoring, management, and analysis of real-time streaming applications—making stream processing more intuitive, accessible.

This project demonstrates how to integrate a “think” tool into a LangGraph agent workflow, inspired by Anthropic’s research on structured reasoning in tool-based agents. By leveraging the “think” tool, Claude is enabled to pause and reflect on intermediate steps, improving performance in complex, policy-driven, or multi-step decision scenarios.

WMB-100K — The first 100,000-turn benchmark for AI memory systems

Knowtate is a sophisticated platform designed to elevate your academic research experience. Seamlessly blend reading, note-taking with markdown, and knowledge management into one intuitive interface, allowing you to effortlessly track your insights and ideas as you delve into scholarly literature.

an Advanced AI application that utilizes LLM and OpenAI for comprehensive resume analysis. It excels at summarizing the resume, evaluating strengths, identifying weaknesses, and offering personalized improvement suggestions

It shows how to use wiki for the data source of agent.

Perform intelligent research over document collections using hybrid search and LLMs.

This project is an end-to-end Retrieval-Augmented Generation (RAG) system designed to ingest, parse, embed, and semantically search scientific papers from arXiv.

🚀 this project aims to develop an app using an existing open-source LLM with data collected for domain-specific Jenkins knowledge that can be fine-tuned locally and set up with a proper UI for the user to interact with.

CLI Investment Research Agent

A CLI tool written in Go to chat with your pdf data

This is an official repository for "Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery".

This repository, 300Days_GenerativeAI, is dedicated to 300 days of continuous learning focused on generative AI, studying different books and research papers daily. I'll revisit past learnings, update my understanding, and dive deeper into generative AI's intricacies.

Visual tool to compare 6 RAG chunking strategies side-by-side with grading and query selection

DomainMind: Enhance Local LLMs with RAG DomainMind integrates Retrieval-Augmented Generation (RAG) with local Large Language Models (LLMs) to answer domain-specific questions using a custom knowledgebase. It ensures privacy by running entirely offline and adapts LLMs to specialized fields like scientific research.

YouTube Video Inspector is a multi-agent tool that analyzes YouTube videos by fetching metadata, analyzing comments, and generating performance reports, which can be exported as PDFs using CrewAI.

Maven is a cutting-edge web application that leverages the power of AI to revolutionize electronic categorized product research and data-driven decision-making.

Memory architectures that evolve with your agent

Deterministic context database for AI agents. Same query → same context, every time.

Vidhi.ai is an intelligent legal assistant and navigator built to make legal knowledge and government processes accessible for everyone in Nepal with well-cited answers grounded in authentic Nepali laws and acts.

Personal GitHub profile showcasing expertise in AI/ML engineering, generative AI, data science, and scalable production-ready solutions.

📍 Storing Text Location in Vector Databases for QA tasks

Impermanent: a live benchmark for forecasting that measures temporal generalization under real world data drift. The benchmark includes foundation models (from AWS, Google, NXAI, Salesforce), classical statistical methods, and simple baselines. Metrics such as MASE and scaled CRPS, along with championship style points, are published on the site.

A lightweight, no-cost, chat agent that answers questions from custom knowledge files. No vector databases, no embeddings, no complex setup - drop in your md files and start chatting

A curated collection of foundational papers tracing the evolution from early generative models to modern retrieval-augmented language systems.

Knowledge graphs and financial news analytics with large language models

A Node.js/TypeScript implementation of Recursive Language Models based on the research paper arXiv:2512.24601 by Zhang, Kraska, and Khattab.

智能选择 17 套分析方案的图像分析分流 Skill：先判断该怎么读图，再输出定向分析和学习建议。

A Model Context Protocol (MCP) server for Mount & Blade II: Bannerlord. Gives AI agents access to decompiled source search, XML data browsing, gameplay queries, local mod source indexing, and patch generation tools.为《骑马与砍杀2：霸主》打造的 MCP 服务器，支持源码检索、XML 数据查询、玩法数据浏览、本地 Mod 源码索引与补丁辅助生成。

A fast multi-platform agent monitoring utility

Building AI Agents and Workflows with LangGraph

Curated research on memory systems for LLM agents

CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents — when extraction goes wrong, it says so per page and says what to do next.

Context Runtime — a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.

Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs.

Curated catalog and dataset of 50 cloneable GenAI apps and Hugging Face Spaces across RAG, AI agents, LangGraph, MCP, and more

The self-improving SRE agent

为 DeepSeek V4.0 等单模态大模型装上眼睛和耳朵 —— 本地视觉+音频 MCP 服务器，基于 Ollama + MiniCPM-V 4.6 + faster-whisper，图片描述·视频分析·语音转文字

docker research-article-template research paper scientific paper data visualization region:us

transformers safetensors llama text-generation en de

gguf text-generation pt en es ru

U-Hermes 虾米 — NousResearch Hermes Agent 中文便携版：Linux Live 免安装启动盘 + Windows 商业版，插上 U 盘即用、支持离线使用，让中文开发者随身携带 AI Agent 工作环境

A collection of ready-to-use n8n workflow templates for building intelligent automations using Pinecone.

Enterprise multi-source RAG platform with multimodal embedding, hybrid vector/BM25 retrieval, MCP & RBAC support

Turn your Hermes agent into a financial analyst — on-demand equities / macro / options / prediction-market analysis, plus a standing watch: morning brief, earnings, 13F diffs, Polymarket. Powered by LLMQuant Data.

Chat with your PDFs using AI! This Streamlit app uses RAG, LangChain, FAISS, and OpenAI to let you ask questions and get answers with page and file references.

Extension of LLM Advisory for Backtrader strategies, enabling real-time trading insights from multiple LLM-based advisors directly within strategy execution.

🍔 An AI restaurant agent demonstrating the RAG pattern using Semantic Kernel for orchestration and Qdrant for vector memory.

AI agent toolkit for accessing and analyzing SEC EDGAR filing data. Build intelligent agents with LangChain, MCP-use, Gradio, Dify, and smolagents to analyze financial statements, insider trading, and company filings.

Applying LLMs, augmented with information retrieval (RAG) and function calling, to a variety of tasks in different domains.

Development and deployment on AWS of a question-answer LLM model using Llama2 with 7B parameters and RAG with LangChain

Multimodal Document Processing RAG with LangChain

This project automates the process of monitoring market data, developing trading strategies, executing trades, and assessing risks using a team of specialized AI Agents from crewAI. Each agent is equipped with specific roles and goals, and they collaborate to optimize trading decisions and strategies.

A sophisticated multi-agent financial analysis tool that provides comprehensive stock market analysis, risk assessment, and investment recommendations.

a solution that simulates AI-driven contact center scenarios using synthetic data and real-time voice interaction.

Seamlessly integrate IoT data with AI agents, enabling the effortless parsing, processing, and utilization of IoT data streams.

多智能体科研助手：文献搜索、知识图谱、TRL评估、创新假设生成

Building a Multi agent using Agno framework with Groq models for web search and financial data analysis

A Python-based agent that scans Gmail for bug tickets, classifies them by department using contextual analysis, and automatically routes each ticket to the appropriate team.

融合数据平台

CitySense is an open-source Python library that bridges geospatial urban data with large language model (LLM) toolchains.

Token Oriented Object Notation (TOON) for Linked Data

This repository contains a Go application that demonstrates semantic product search and Retrieval-Augmented Generation using OpenAI's GPT and embedding models, with Qdrant as the vector database.

9th Place Solution - LLM 20 Questions

Type-safe structured data extraction from text using LLMs.

Persistent memory and identity protocol for AI systems with evidence-aware recall and inspectable memory.

Question-Answering App Over Your Own Data with LLamaindex and ElasticSearch !

Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation

🟢 Real-time 3D dashboard for OpenClaw AI agents — each agent is a continent, each session is a minion. Physics, live chat, thinking bubbles.

The blazingly fast in-memory vector database 🚀

Starfish-FL is an essential component of the STARFISH project. It focuses on federated learning and analysis for the Analysis Mandate function of STARFISH.

ESG Report Analysis and Greenwashing Detection is an interactive application that enables the analysis of ESG reports to identify signs of greenwashing. Based on predefined criteria, the tool assigns a risk score and offers an interactive search system through an intelligent chat (RAG).

A sophisticated multi-agent system designed for real-time market analysis of HTX (formerly Huobi) exchange data. This swarm combines specialized AI agents to provide deep market microstructure insights and trading analytics.

On-demand Services/Data marketplace for AI Agents.

Agentic GitHub workflows with reminders, PR monitoring, and progress tracking. Includes a Discord bot for notifications. 🚀

A CLI tool and MCP (Model Context Protocol) server for querying and analyzing TensorBoard event files without requiring a running TensorBoard server.

一站式轻量化数据引擎：连接设备，交付价值；CRose是一个专为制造业与现代农业打造的集成化数据底座。它封装了从底层的协议采集（Modbus/MQTT）到上层的统计分析、UI展示的全链路能力。CRose is an integrated data platform designed for manufacturing and modern agriculture. It encapsulates the full stack capabilities from underlying protocol collection (Modbus/MQTT) to upper-level statistical analysis and UI visualizat

LangChain4j Neo4j Graph RAG - Movies Search Demo. An AI-powered movie database application built with Java 21, Spring Boot 3.3.3, and Neo4j. The app uses LangChain4j to enable natural language queries, providing personalized recommendations, interactive graph visualizations, and dynamic data exploration.

Kikiola is a high-performance vector database written in Go.

LLM chat built for University of Helsinki staff and students, for education and research.

AI-powered live demonstration agent for Dynamics 365. Generate and execute interactive demos with visual overlays, voice narration, and browser automation.

🦅 DestinyScout: 一款基于 Agent-Native LLM + Boss直聘的 L3 级自主个性化求职引擎。告别机械搬运，它能深度注入你的私人职场 DNA 并配合强力反穿透爬虫，让大模型在茫茫数据海中为你精准捕获那个“命中注定”的理想 Offer。

Agentic GraphRAG system for loan compliance monitoring and financial crime investigation in Australian financial services. Built on Neo4j, Claude, and APRA prudential standards. Features a multi-agent pipeline, three-layer knowledge graph architecture, and full reasoning chains with cited regulatory evidence.

Retrieval augmented generation for building datasets from scientific literature: Contains the notebooks used for creating datasets

Coordination intelligence for any agent system

Free open-source monitoring dashboard for OpenClaw AI agents — token usage, session tracking, 7-day trends, multi-model support

SAP SuccessFactors MCP server — 43 HR tools for Claude Desktop & Cloud Run. Query employees, permissions, time off, hiring, compliance, and more via natural language.

🌐 An open, standardized four-layer enterprise ontology framework for knowledge graphs, semantic layers, master data management, and AI Agent knowledge bases.