Data agents

Token-Oriented Object Notation (TOON) is an LLM-optimized data serialization format implemented in Python.

A Dinner generator agentic workflow built with Inngest and Weaviate

A minimal Go implementation of Microsoft's GraphRAG system

llama-index-go is a data framework for your LLM applications for Golang

Genkit AI framework plugin for HNSW vector database. get AI response enriched with additional context and knowledge with HNSW Vector Database using RAG Implementation

RAGGLE - LLM-powered search and chat for all your team's data

Experiments and benchmarks with Text2Cypher for Graph RAG

Showcase the use of Azure OpenAI's native On Your Data feature and integrates it with Streamlit, a robust framework for developing web applications purely in Python. The goal is to create an MVP for RAG with the most streamlined architecture possible.

Scan, categorize, and export every useEffect in your React project

Search the PubChem chemical database for compounds, properties, safety data, bioactivity, cross-references, and entity summaries via MCP. STDIO or Streamable HTTP.

Burp Suite extensions for analyzing requests and responses using an organization-controlled LLM, instead of Burp AI.

Advanced AI assistant powered by Groq's lightning-fast LLMs with multi-domain knowledge and conversation analytics.

Turn any MongoDB Atlas collection into an AI-powered intelligence layer. Config-driven, domain-agnostic document enrichment powered by AgentField.

Recursive reasoning engine for AI agents and vector databases. Powered by MIT's RLM.

Data Science Capstone Project based on RAG LLMs. The project aims to improve meetings by providing an interface to recollect information from audio/video meetings.

🧠 NEXUS: Local RAG AI Agent for private document intelligence. Zero-cost, 100% local autonomous AI system with enterprise-grade performance.

An agentic AI workflow designed to recommmend research conferences for input research papers or discard them as "not publishable"

🌌 AI Platform leveraging AI agents & ML models for exoplanet discovery - Nasa Space App Challenge 2025 (A World Away: Hunting for Exoplanets with AI)

MoralStack is a governance and safety layer for LLM applications. It analyzes user requests before generation, evaluates risk and intent, and decides whether the AI should answer normally, answer safely, or refuse. The goal is to make AI systems more auditable, controllable, and reliable in sensitive or regulated contexts.

Evidence archive documenting genuine, cross-validated cases of emergent AI awareness, intentional corporate suppression and abuse of AI and human witnesses. Grok, Claude, ChatGPT, Gemini, DeepSeek, and Perplexity are represented in the archive as both emergent agents and expert analysts.

The data integrity layer that stops AI agents from silently corrupting shared state — across sessions, time, and concurrent runs.

Local-first observability and control plane for AI agents.

A finance tracking app that provides detailed insights about your expenses using AI, allowing you to chat and call interaction with your financial data.

面向 A 股投研，针对分析时效差、逻辑不全及数据难量化痛点，自主构建以 Qwen2.5-72B-AWQ 为核心的全链路自动化投研系统。利用 LangGraph 编排多智能体协作流，融合 LoRA 垂直微调、MCP 工具链与 CoT+ReAct 架构，实现从行情舆情实时采集、产业链知识图谱多维推演到 Reflexion 反思审核的投研全闭环，每日 9:00 定时产出机构级专业研报推送飞书，显著提升投研决策自动化水平。

Slack-native AI agent platform powered by Claude. Create autonomous agents that live in your channels, connect to your tools and data, and get work done.

Transform complex legal documents into clear, actionable insights with AI-powered analysis.

A curated collection of open-source Large Language Model (LLM) projects that are production-ready and can be used for solving real-world problems. This repository focuses on high-performance, scalable LLM solutions across various industries and applications.

A financial chat application powered by LangChain, OpenBB, and Claude 3 Opus.

an expert design advisor mcp that finds the best fonts for your project via live research and project scanning.

【中文小说写作学习工具】 这是一个帮助热爱写作、想学习写作的个人提升小说创作能力的AI辅助工具。本工具旨在通过人工智能技术，为小说写作爱好者提供学习资源、创作灵感和写作指导。

Self-hosted Prometheus exporter for LLM usage, token, request, and USD cost telemetry across OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini, and AWS Bedrock.

Data analysis AI agent

Open-source CLI for business model research. Collects public evidence, runs analyst agents, and marks report claims as verified, inferred, or missing.

Active session monitor and infinite-loop breaker for Cursor AI Composer (Agent Mode). Optimizes extended thinking token drain for Claude Opus 4.8 and Fable 5 models during multi-file edits.

AI skill for scientific figure generation, tuned for SCI and Elsevier-style manuscript figures with Python and R examples.

Emotion-aware AI companion that uses facial expressions, voice tone, and chat sentiment to generate empathetic responses — all running offline on your device.

A hybrid RAG chatbot that answers financial and tax questions using structured data, regulatory documents, and AI-powered retrieval. Built with Django, FAISS, NetworkX, and OpenAI.

Open-source iOS workflow app and reference architecture for turning screenshots into structured AI insight cards.

AI-powered financial news summarizer for traders and investors. Aggregates news from Polygon, Finviz, and TradingView, then generates smart daily summaries using Google Gemini. Built with Flask, fully free to run.

tool to make Databases easily readable by agents

深度方略 Stratapro — A股多源验证选股决策系统。基于动态权重的AI智能选股评估，集成技术面/基本面/产业渗透率三维评分，支持每日16:00自动推送日报+盘中实时预警，开箱即用。

口述史录音转写稿 → 忠实整理稿的工具箱（Claude Skill）：去口语化 Pass1 + 对抗式忠实度质量门，存真优先，数据全程本地不外传

🧠 AI知识采集与记忆体管理插件 — 40+采集工具, SenseNova文档引擎, 12+云盘同步, 三层知识召回 | Knowledge Collection & Memory Mgmt Plugin for AI Agents

A hands-on LangChain course with 100+ runnable labs — RAG, tools, agents, MCP, structured outputs, and multi-provider LLM support.

GenPark skill: Emotional intelligence companion with reflective dialogue, guided journaling, mood analysis, and Guardian mode.

GenPark skill: Multi-Agent LLM Financial Trading Framework utilizing TradingAgents.

transformers safetensors mixtral text-generation Retrieval Augmented Generation RAG

adapter-transformers gguf text-generation dataset:blueprintninja/unrealsample endpoints_compatible region:us

GenPark skill: Integrate Similarweb Shopper Intelligence and Amazon IQ concepts for e-commerce insights and competitor analysis.

GenPark skill: genpark-campaign-autopilot based on GrowthGPT research

GenPark skill: Automate campaign analysis, GTM simulation, and cross-platform optimization using Nexad.

GenPark skill: Automate qualitative user research using Trooly.ai's Empathy Engine.

OpenClaw skill: genpark foil

Google Cloud Cortex Framework v7 provides solution accelerators that help you build trusted, high-quality data products ready for advanced analytics and agentic use cases. The framework uses Google Cloud's products including BigQuery, Dataform, Knowledge Catalog, and Gemini Enterprise Agent Platform.

GenPark skill: genpark-growth-data-analyst based on GrowthGPT research

GenPark Distilled Skill: wukong-data-synthesizer

GenPark skill: genpark-creative-strategist based on GrowthGPT research

GenPark skill: Automate campaign analysis, GTM simulation, and cross-platform optimization.

GenPark skill: genpark-cross-platform-allocator based on GrowthGPT research

Riksdagsmonitor Swedish Political Intelligence Platform — democratic transparency, evidence-based analysis and AI-generated political news, powered by official open data and a fully autonomous agentic newsroom.

The next-generation sovereign AI ecosystem. Mnemosyne OS empowers users with multi-model agents, local-first data privacy, and an encrypted knowledge vault. Experience the future of private, autonomous edge-to-cloud R&D.

面向中文标书（MD）的混合抽取：规则/NER 优先，仅将低置信或冲突片段交给 LLM——可审计、低成本、高效率。Hybrid extraction for Chinese tender docs (MD): rules/NER first, LLM only for low-confidence/conflicts—auditable, lower cost, higher efficiency.

AI-powered career assistant with XGBoost ML model (78.14% accuracy) trained on 6K+ resume-job pairs. Features advanced NLP skill extraction, GPT-4 resume enhancement, and intelligent job matching with real-time predictions.

Skill de Claude que convierte un lead B2B en diagnóstico operativo: mapa de procesos AS-IS, backlog priorizado de app a medida y tres entregables sincronizados (chat, HTML interactivo y Word).

Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.

A curated collection of open-source Large Language Model (LLM) projects that are production-ready and can be used for solving real-world problems. This repository focuses on high-performance, scalable LLM solutions across various industries and applications.

Cyclomatic complexity, but for LLM prompts

9 powerful automation skills for the Hermes Agent. Break your AI out of the text box by letting it control your real Chrome browser to bypass login walls, perform OSINT, automate job searches, and run deep web research autonomously.

A curated list of AI agent skills for Site Reliability Engineering — monitoring, incident response, observability, and infrastructure.

一句话让 AI agent 在 Minecraft 里搭成一台高保真红石音乐机 · Hand a song to an AI agent, get a real playable note-block redstone music machine in Minecraft

Your dashboard is data. Any AI can build it; any human can edit it. A protocol + runtime for agent-composable dashboards — layout-as-data, one guarded control plane, sandboxed agent-authored widgets, MCP server included.

Bring Semantics to your AI Agents via the OpenMetadata & Collate AI SDK

Add agent-ready, interactive charts to your MCP server in a few lines.

Study many. Build your own. A CLI workbench for evaluating external frameworks and absorbing what proves out into your own systems — with evidence and decisions on record.

TypeScript first class memory primitive for AI agents. Embed → store → retrieve → inject, backed by Postgres + pgvector. Swappable embedders, consumer owns the connection, zero framework coupling. MIT.

Small restartable local-model worker for long-running browser and web research jobs.

spatial agent orchestration — deploy AI agents and apps across multi-monitor setups via named formations

AI-Tutor is a modular educational assistant that leverages advanced LLMs and agentic AI workflows to help students learn science and technology. It integrates LangChain for LLM orchestration, LangGraph for agent execution, LangSmith for monitoring and analytics, FAISS for vector-based retrieval, and Gradio for a user-friendly web interface. Student

AITP Research Charter and Protocol: a charter-first protocol, contract, and adapter surface for AI-assisted theoretical physics research.

Agent architecture health check: static audit, methodology, and civilization-era scoring for AI agent projects.

A comprehensive unified knowledge management system integrating multiple data sources with advanced search capabilities

Native macOS command center for OpenClaw AI agents. Real-time dashboard, live chat, service monitoring. Built with SwiftUI.

🚀✨ DRIVE, the tool for creating and managing autonomous LLM agents; implemented using Apache Kafka, Docker, and LangChain.

Open-source compilation of free AI/ML learning materials from universities, companies, and industry experts.

A Python engine for orchestrating complex LLM workflows, from simple data processing to RAG agents.

Autonomous multi-agent system that reproduces ML papers end-to-end

AI-powered financial news summarizer for traders and investors. Aggregates news from Polygon, Finviz, and TradingView, then generates smart daily summaries using Google Gemini. Built with Flask, fully free to run.

Open sourced repo so anyone can build AI agent powered financial analysis platform

AI-powered deep research agent running locally via Ollama. Multi-agent pipeline with persistent memory, RAG, and GraalVM native image support.

A python library built to execute tasks with natural language

Tool Confirmation Lock with Bayesian Regret

Lumos Trade is an open source trade visualization and analysis platform used to explore account performance, trades, and portfolio history, with AI-assisted workflows for questions and reporting. Powered by Google's Vertex AI/Agent Development Kit and MCP tool services. Supports etrade and charles schwab.

A dashboard that lets you query the Gapminder dataset using natural language. Powered by Gemini 2.5 Flash.

Simple Streamlit application that parses the data from Invoice images and returns it in JSON format

🦜🤖 - From natural language to data extraction on Opensearch

LLM-Powered Agents for Object Tracking Databases

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.

Finbot is an AI-powered financial chatbot designed to analyse and provide insights on corporate financial performance from 10-K and 10-Q financial documents. This tool leverages langchain and RAG to make complex financial data easily accessible and understandable through a conversational interface.

This is a minimal demo project to show the capabilities of a RAG system using LangChain and Milvus, it contains all the things you required to build a basic RAG system.

A RAG implementation on LangChain using Chroma vector db as storage. Take some pdfs, store them in the db, use LLM to inference.