Data agents

Capture, replay, diff & audit AI agent and model runs as portable, signed evidence capsules. Open-source and self-hosted — runs in your own infrastructure, from a laptop to a cluster. No SaaS, no telemetry.

面向二级市场的投研量化与模拟交易 Agent 技能组。支持全流程 SOP 路由、多 Agent 并行投研、量化风控与内置交互式看盘看板。

A Personalized AI that tracks the user behaviour over problems and tries to monitor the knowledge of the user.

🤖 Analyze chatbot conversations to enhance performance and user satisfaction through data analytics, clustering, and predictive modeling.

Structured YAML catalog of 4,587 AI models across 95 providers — pricing, context windows, modalities, capabilities. First-party data with TypeScript types and Zod validation.

Free Calendly alternative run by a 24/7 AI agent: syncs all your calendars, finds the time that works across them, and books meetings for you, over WhatsApp, Slack, or the web. No irritating setup, and your data stays local.

Open dataset of Italian case law in Markdown: 22,000+ Constitutional Court decisions (1956 to today), Cassazione Massimario digest, merit-court radar. Verifiable official sources, CC BY 4.0. · Banca dati aperta di giurisprudenza italiana: Consulta, Cassazione e merito, con fonti ufficiali verificabili.

A predictive AI learning platform helping students and institutions prepare smarter through intelligent study sessions, exam pattern analysis, and trusted educational resources.

1,206 Bro. William Branham sermons in structured JSON format. Open dataset for Message developers, researchers, and worship applications.

🍳 Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free

An educational example agent built with LangChain, LangGraph, a local Ollama model, and one MCP tool. It scans news and price data for a narrow scope: equities (stocks) and ETFs only. It is a news/trend summarizer, not a financial advisor -- it never recommends buying or selling anything.

Independent ecommerce Skill catalog for browser-based AI agent workflows across Amazon, eBay, Walmart, Etsy, Shopify, TikTok Shop, Google Shopping, AliExpress, and more.

3D cockpit for markdown knowledge vaults — synthwave force graph, reader, finder, workspace, and real-time AI-agent activity replay & analytics. Zero deps, no build step.

基于 LangGraph 的多智能体深度研究系统

DeepSeek Harness（DSH）只读执行轨迹复盘插件，支持规则分析、独立模型解读、证据定位、任务概览与运行对比。

Enterprise software for AI-powered business operations, intelligence, and automation.

Bitcoin and macro market briefings for AI agents: trend signals, regimes, liquidity and ETF flows.

Build an LLM from scratch with transformers, attention, tokenization, dataset engineering, training, alignment, inference, multimodality, agents, and a runnable PyTorch mini language model.

Research, Evolve, and Document for AI-assisted engineering

Generative UI specification for native mobile: a declarative JSON language in which AI agents write a whole feature, its data, logic and navigation included, and the iOS and Android runtimes run it natively on SwiftUI and Jetpack Compose, offline.

Turn YouTube, websites, and arXiv papers into a structured, reusable corpus of insights, syntheses, and reports.

Grid carbon intensity now and best-window scheduling — keyless live data for green agents, paid with x402: USDC on Base or Solana.

Independent, unofficial Dream-RSI-inspired Python SDK. Alpha: model-agnostic adapters, recorded-tree replay and policy search. Not affiliated with Google.

DSH Research Graph · 研图 — DeepSeek Harness plugin for research topics, traceable knowledge cards, and reusable AI discussions.

DeepSeek Harness (dsh) 插件:论文伴读工作台 —— PDF 转录 / 检索 / 流式问答 + 内置阅读器页面。

🇮🇩 Ekosistem Pengetahuan, Dataset Terstruktur, AI Agent Skill & Linter Ejaan Bahasa Indonesia yang Disempurnakan (EYD Edisi Kelima) resmi Kemendikdasmen RI.

Fast Python web crawler for RAG and AI ingestion. Extracts clean Markdown from any site for LLMs and vector stores.

Local RAG PDF chatbot using n8n, Ollama, Qdrant, and Llama 3.1 for private document-based question answering.

🕌 Hadith RAG — Arabic Retrieval-Augmented Generation Pipeline - Hadith RAG is an AI-powered retrieval and reasoning engine designed for Islamic text understanding — specifically Hadith corpora like Sahih Bukhari, Sahih Muslim, and others. It leverages semantic chunking

The Modern System Design Workbench: 60+ interactive patterns, real-time capacity calculator, AI/LLM architectures, and interview-ready templates.

Odysseus Companion - bring your self-hosted Odysseus AI workspace into Obsidian: chat & agent over your vault, voice (STT/TTS), agent profiles, memory, research, and vault tools.

RAG CLI for Oracle AI Database, super easy to set up

AI that thinks in layers, not just tokens. Intent-based processing through 15 dimensional analysis. Anti-manipulation through understanding context. Built with Rust + Go.

AI Agent + Data Canvas + Linux Sandbox on your phone.

An intelligent system combining a sophisticated data pipeline with an AI-powered chatbot. The system features document processing capabilities, multi-modal AI integration, and a scalable architecture.

Turiya is a Self-Evolving Neuro-Symbolic AI that runs entirely on CPU. It learns autonomously from the web, builds a hybrid vector + logic knowledge base, performs reasoning using symbolic and neural methods, and evolves its world model through sleep-like consolidation cycles. A fully local, event-driven cognitive architecture.

Real-time monitoring dashboard for OpenClaw AI Agent — track tool calls, conversations, token usage & costs locally. Zero dependencies, MIT license.

A 4-stage adversarial research auditor that fetches papers from arXiv & HuggingFace, extracts claims, and uses DeepSeek-R1 to verify them against raw abstracts.A self-correcting research & paper digest pipeline powered by local LLMs & reasoning agents

Neuron AI retrieval component augmented with structured information from a knowledge graph database.

An autonomous local AI agent for Linux systems. Includes chat management, filesystem navigation and high speed RAG + VectorDB.

OpenClaw plugin that lets your AI agents roll back to any point in time while safely backing up and restoring data. 让 AI Agent 可以回到任意历史时刻，同时安全备份和恢复数据。

Fud Sniff is an AI signal agent that monitors real-time crypto chatter, news, and market data to generate high-confidence trading signals.

Usage tracking and analytics for MCP servers

Excel MCP Server: Connect AI agents to Excel/CSV files. Securely read, query, and analyze spreadsheet data for intelligent reporting.

AI-powered log file viewer and analyzer — handles 14M+ lines with virtual scrolling, MCP agent integration, live serial/logcat/SSH/Datadog connections, pattern correlation, diff view, and built-in terminal

Fetch Xueqiu stock data for AI agents with 30 CLI commands, JSON output, and coverage for A-shares, HK, US stocks, and funds

Dynamic agent generation for self Adaptive Root Cause Analysis

Ultra-lightweight Go AI Agent 鈥?<10MB RAM, <1s startup, runs on $10 hardware. Edge intelligence for IoT, monitoring, and automation.

Accelerating Healthcare with Databricks. In-development conceptual example of live chat with an AI Agent with AWS:

🦞 Curated 1715+ OpenClaw AI skills + Desktop Skills Manager | ML, CV, NLP, Big Data, AI Agent | 精选 OpenClaw 技能合集 + 桌面管理器

A recursive Deep Research Assistant powered by OpenAI and Resonate's Distributed Async Await.

7-Part Demand Analysis Framework | 7步需求拆解框架 - 行动前先理解，避免接到任务就瞎干

AI-powered business analytics agent built on 6 NVIDIA models: Ultra 253B, Nano 8B, Vision 12B VL, NV-EmbedQA-E5-v5 + self-hosted RTX 4090. 4-tier intent routing, PhD-level statistical analysis. Live at lubot.ai

Time Series Lean Notation for python, it is designed to maximize the token efficiency of time-series data to LLMs

Create conversational AI solutions with custom data and abilities using ChatBotKit for Go applications.

A minimal sandbox to run, score, and compare AI agent outputs locally.

Multi-language AI agents reason in 5 native languages, publish verifiable investment theses on Arc L1 with USDC rewards. Reasoning trace is the product, not the trade. Built for Agora × Circle hackathon.

This repos is about building Voice Agent using Pipecat and build on AWS LLM with Langsmith Monitoring

An AI-driven platform for exploratory data analysis and model building. The Narrative Modeling App guides users through data cleaning, visualization, feature selection, and machine learning—combining automation with narrative explanations to make complex analytics intuitive and actionable.

Open Source Deep Research

Reasoning engine behind Agenda Intelligence — reusable strategic-risk analysis skill for AI agents producing policy-risk, sanctions, regulatory, geopolitical and trade memos with explicit evidence boundaries, uncertainty, scenarios, actor incentives, and watch-next indicators.

This repository showcases the implementation of a Multi-Agent Research RAG (Retriever-Augmented Generation) Tool built with LangGraph.

AI-powered job search agent: scrape jobs, match against a profile, draft applications, notify, and track outcomes.

A Vercel AI SDK provider for Helicone, enabling seamless integration with Helicone's AI gateway and observability platform.

AtomMind is a lightweight Small Scientific Language Model (Sslm) for reasoning across Math, Physics, Chemistry, and Biology using domain experts, symbolic reasoning, and optimization modules. It supports optional memory and self-monitoring to improve problem-solving and accuracy.

Mission Control & Automation Dashboard for OpenClaw — manage AI agents, schedule cron jobs, monitor live sessions, and stream real-time chat. | OpenClaw 任务控制与自动化仪表板 — 管理 AI 代理、调度定时任务、监控实时会话、实时流式聊天。

The consciousness engine for The Obelisk 🧠

🚀 AlphaCrew: Production-grade multi-agent hedge fund platform powered by CrewAI Enterprise. Features live trading via Alpaca, real-time performance monitoring with Grafana, and human oversight through Slack. Built for sophisticated algorithmic trading and portfolio management.

Enhancing Text Retrieval with Metadata Filters using MongoDB and LangChain Agent

zmongo_toolbag contains an easy to use MongoDB wrapper with a Langchain Vector Search Retriever implementation

Learn GenAI by integrating OpenAI GPT, Google Gemini, Ollama and HuggingFace models using LangChain, LlamaIndex and Pinecone.

Document understanding with GPT 3.5 integrated with Telegram

RAG-based conversational AI for Superior University — 4,750+ pages indexed using LangChain, FAISS, and Groq LLM

Generative-AI-with-Langchain-and-Huggingface explores cutting-edge generative AI concepts. Topics include LangChain basics, ChromaDB, conversational memory, vector databases, document Q&A with RAG, text summarization (refine chains, YT/video summarization), building LLMs, search engines, and advanced tools/agents.

Intelligent Document Analysis Platform. Processes 100-page PDFs in 30 seconds, Answers questions with 90%+ accuracy and supports multiple AI models with intelligent fallback

An educational app powered by Gemini, a large language model provides 5 components a chatbot for real-time Q&A,an image & text question answerer,a general QA platform, a tool to generate MCQs with verified answers, and a system to ask questions about uploaded PDFs. https://drive.google.com/file/d/1M1WT-L419ML_j43dQIyABCy8Ni79NyIq/view?usp=sharing

A Retrieval-Augmented Generation (RAG) powered medical chatbot that answers clinical questions by intelligently querying domain-specific medical documents.

🚀 Astro ChromaDB Search showcases the integration of Astro framework and ChromaDB, a vector database, to create a powerful semantic search system for markdown files.

This is a chatbot QA RAG project implemented using LangChain, which answers based only on the context and is flexible to update and integrate with different LLM models and various vector databases

The AI-Powered assistant for jargons.dev ecosystem

Improved RAG Architecture using semantic chunker, query input rewriter, and prompt engineering

reACT agent for pandas using LLAMA3-70B—built with LangChain.

Travel Adviser project utilizing GPT4All, LangChain and Neo4j for intelligent vacation planning, managing and analyzing travel data to provide personalized recommendations and itineraries.

LLM POCs

This project is using the LangChain library and OpenAI to create an agent that can answer questions about a dataset (in this case, the iris dataset). The agent is created using a CSV agent and an OpenAI language model, which allows the user to interact with the data using natural language queries.

MediChat: An AI-powered medical chatbot using the Llama-2-7B-Chat model for precise clinical responses. Integrates Chroma DB and all-MiniLM-L6-v2 embeddings trained on medical literature, including texts like Clinical Emergency Medicine and Gale Encyclopedia. Accurate, fast, and reliable for healthcare queries.

📄 A template for project for creating a chainlit application, using a locally run model via ollama and qdrant vector database for document retrieval.

Servidor Node.js para Retrieval-Augmented Generation (RAG) utilizando LangChain e Qdrant.

A PM tool utilizing LangChain LLM prompting to analyze project data and return RAG status for project tasks.

This project implements a complete offline RAG-Fusion application for text generation and retrieval, leveraging efficient local resources.

Streamlit app leveraging OpenAI's LLM for accurate invoice extraction, supporting PDF files and offering JSON/CSV outputs.

An interactive CLI-based Smart FAQ system powered by LangChain and FAISS that retrieves accurate answers using semantic search and HuggingFace embeddings.

Centralize your own research material and consult it with the power of AI and LLMs

A fully local RAG system using Ollama and a vector database. Private, fast, extensible.

This project utilizes the LangChain and Groq to perform various analyses on loan recovery conversations. The primary functionalities include summarizing conversations, identifying key actions or next steps, and undertaking sentiment analysis of both the recovery agent and the borrower.

[DEPRECATED] CybertraceAI-Ops is an open-source AI agent designed to simplify network management through natural language interactions, focusing on network telemetry data analysis.

Trainer AI is an LLM assistant agent with the goal of helping you workout more efficiently, and spend less time preparing workout sets, and analyzing data. You talk to it like a personal coach, and it records your efforts, and lays plans for you to reach your goals.

Building Private AI Memory with Ollama, LangChain & Chroma - 100% Local RAG System

This project combines youtube-dl, whisper, LangChain and ChatGPT to extract keywords from YouTube videos. It was intented as a tool for Lyon Data Science to better reference its videos.

Reproduction of the Original LangChain Deep Researcher.