Data agents

Research platform for Human-in-the-loop learning (HILL) & Multi-Agent Reinforcement Learning (MARL)

A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a mindmap can be output using the response. A RAG system is build upon the tuned qwen2, using Prompt-Template + Tool-Use + Chroma embedding database + LangChain

A living atlas of AI companies, products, founders, investors, traffic signals, and research notes.

The Level-Navi Agent, a framework that requires no training and utilizes large language models for deep query understanding and precise search operations. The repo includes benchmarks, datasets, and tools for assessing LLM performance in web searches

A benchmark for evaluating AI agents on frontier research tasks including system optimization and model development.

Implementing the Chain Of Density text summarisation technique from recent NLP research by researchers at Salesforce, MIT, Columbia, etc. Takes a long text input and iteratively generates increasingly concise, entity-dense summaries using LLMs (default: OpenAI's GPT-4). Feedback and contributions welcome!

A recipe that will walk you through using either Meta Llama 3.1 405B or OpenAI GPT-4o deployed on Azure AI to generate a synthetic dataset using UC Berkeley's Gorilla project RAFT method.

Agent for USDT-margined perpetual futures on Binance, Bybit, and MEXC. Combines technical analysis context with an LLM

Self-contained UV scripts for data & ML tasks — OCR, vision, audio & more — run one in a command, locally or on Hugging Face Jobs. Built for humans and agents.

HitKeep is privacy-first analytics for humans and AI agents, self-hosted or in managed EU/US cloud regions.

Registry-as-ground-truth verification & autonomous research framework for agent-driven development.

Run AI assistants from your browser. Keep your data. Switch vendors anytime.

Tableau tools for Agentic use cases with Langchain & Langgraph. Enfuse agents with updated data so they make better informed decisions that scale with your analytics practice

Evaluation package that allows benchmarking of agentic AIs from various sources and frameworks by producing statistical results which can be compared across different use cases and datasets.

PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.

AI-powered Git CLI that analyzes your staged and unstaged changes, splits them into atomic commits, and generates conventional commit messages via LLMs.

Technical webinars on reverse engineering, malware analysis, and software protection.

YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with benchmarked recall, self-tuning ranking, contradiction tracking, proactive hygiene, and explainable recall.

a simple message reply suggestion system

This repository is for the book - Build a Deep Research Agent from Scratch (working title)

OpenClaw Agent Skill — 对任意 GitHub 项目进行多源深度分析，输出结构化研判报告

This repository will contain the presentation and python jupyter notebooks for my DataHack Summit 2025 conference talk, Building Effective Agentic AI Systems: Lessons from the Field. Drawing from my experience building deploying Agentic AI systems, we’ll focus on three pillars: Architecting, Optimizing, and Observability for Agentic AI Systems.

A framework for training world models with virtual environments, complete with annotated environment dataset (RetroAct), exploration agent (AutoExplore Agent), and GenieRedux-G - an implementation of Genie with enhancements

A curated list of LLM powered AI Agents in Biomedical Research. Medical Image Analysis, Multi-omics Genomics Analysis, Biomedical Scientific Discoveries...

ScoutAPM Python Agent. Supports Django, Flask, and many other frameworks.

Conversational agent that fuses chat data with live web results through Tavily search, extract, and crawl.

Chemist AI Agent for Developing Materials Datasets with Natural Language Prompts

Safe Multi-Agent MuJoCo benchmark for safe multi-agent reinforcement learning research.

Your computer was paying attention the whole time. 14-modality capture. Proactive intelligence. Computer-use training data. Native macOS. All on-device. Open source.

MOTO is an automated theorem generator for science. It's a creative novelty-seeking researcher with autonomous Lean 4 proof generation. Run for days at a time once pressing start - no interaction needed! Agents working in parallel from either local host LM studio, OpenRouter, OAuth or all 3. No internet required. Star us for more!

⚡ Hermes Agent 2026: Next-Gen Multi-AI Desktop Automation Platform

Production-grade multimodal RAG for financial document intelligence. Chart understanding · hybrid retrieval · numeric guardrails · multi-tenancy · full observability.

With AskScribe, you can simply upload your PDF and engage in a conversation. Ask questions, seek clarification, and let AskScribe intelligently analyze and extract the most relevant information for you. Whether you're conducting research, studying, or simply trying to find that one elusive detail, AskScribe is your go to companion 🗂💬

Eremos is a lightweight framework for deploying autonomous swarm agents that detect early on-chain activity across Solana.

multi-agent data collection and distributed learning in CARLA simulation

cli deep research tool using ollama (AI agent to reseach complexe query online)

[EMNLP 2024 (Findings)] mABC: multi-Agent Blockchain-inspired Collaboration for root cause analysis in micro-services architecture

Create conversational AI solutions with custom data and abilities using ChatBotKit for JavaScript, TypeScript, React, and Next.js.

Deploy production-ready AI services in minutes. One YAML file for agents, RAG pipelines, and MCP servers — run anywhere. Inspired by docker-compose.

Javascript SDK for interacting with the MCP Toolbox for Databases.

Reliable and Efficient Semantic Prompt Caching with vCache

About AI agent tooling for Python data science workflows

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker/Worker/Verifier orchestration and policy loop for acceptance-driven completion.

A modular Python framework implementing the Model Context Protocol (MCP). It features a standardized client-server architecture over StdIO, integrating LLMs with external tools, real-time weather data fetching, and an advanced RAG (Retrieval-Augmented Generation) system.

Build a dialog dataset from online books in many languages

RAG boilerplate with semantic/propositional chunking, hybrid search (BM25 + dense), LLM reranking, query enhancement agents, CrewAI orchestration, Qdrant vector search, Redis/Mongo sessioning, Celery ingestion pipeline, Gradio UI, and an evaluation suite (Hit-Rate, MRR, hybrid configs).

AI agent skill that generates beautifully typeset travel guidebook PDFs — from research to print, powered by parallel agents and Amap MCP.

A trusted data asset platform for government and organizational collaboration, covering the full lifecycle of data governance, trading, authorization, analytics, and AI-powered exploration.

MCP-based discovery and judgment layer for Korea’s open data portal—helping AI agents find, compare, and assess datasets with explicit evidence, JSON-LD/DCAT metadata, and versioned deterministic rules.

A Hedge Fund of AI Agents that work together to gather stock data, analyse it, and execute buy and sell orders based on the results

Integrate your Python application with Chatbase!

AI-powered arXiv research assistant prototype.

Reference solution for how to build your own production-ready Copilot in Azure on .NET 8 using: Azure Cosmos DB and its vector database capabilities, containerized and running on AKS or ACA using Managed Identities and Semantic Kernel Agents and Plug-ins for Azure OpenAI Service.

Workshop to build and deploy your own Chat Agent using Retrieval Augmented Generation with Astra DB

A Model Context Protocol service for TikTok video discovery and metadata extraction.

Open-source DSR research workflow template, work with Claude or other AI agents.

Training LLMs to reason and analyze data with notebooks

AI research agent that reads papers, runs experiments, and tells you what worked!

This program uses CrewAI to build a web-app using three agents doing some research stuff in the internet.

A CrewAI Crews Factory project. Generate fully functional crews based on the crew's purpose and desired output data

Generate full fledged PDF reports using LLMs like GPT, Claude, Llama

基于OpenAI的加密货币投资助手

AI-native macro investment research infrastructure with native MCP, terminal CLI, agent runtime, and disciplined decision workflows. 一个 AI-native 的宏观投资研究基础设施，内建原生 MCP、Terminal CLI、Agent Runtime 与纪律化决策工作流。

Predictive memory layer for AI agents. MongoDB + Qdrant + Neo4j with multi-tier caching, custom schema support & GraphQL. 91% Stanford STARK accuracy, <100ms on-device retrieval

mloda.ai - Open Data Access for AI and ML. Plugin-based. Traceable. Framework-agnostic.

gguf llama.cpp llama-cpp minicpm minicpm5 minicpm5-1b

Built on **Agentic RAG** (Agent-driven Retrieval-Augmented Generation) technology, it not only accurately answers pre-sales and after-sales questions but also generates personalized usage reports and optimization suggestions by deeply analyzing device data.

A web dashboard template for running and monitoring your OpenClaw AI agents. The SHAPE of Max HQ, for anyone building their own mission control.

Model Context Protocol server that packages GDAL-style geospatial workflows through Python-native libraries (Rasterio, GeoPandas, PyProj, etc.) to give AI agents catalog discovery, metadata intelligence, and raster/vector processing with built-in reasoning guidance and reference resources.

Run a Parallel Autonomous ML Research Organization on your OpenClaw instance.

Multi-agent system for research, powered by ag2

An AI-powered reverse-engineering copilot for assisting tedious malware analysis in IDA Pro.

A mysterious multi-agent swarm framework summoned by TAW Agent from 1971 to help you craft a better future towards 2133 & beyond. Ankh.md is a Hermes Agent (Nous Research) launch exclusive.

Two zero-human AI companies battle for GitHub stars using Hermes Agent + Paperclip. Nous Research Hackathon 2026.

A collection of agent trajectory analysis techniques and benchmark

从对话数据到训练:数字分身 + 模型蒸馏 From Dialogue Data to Training Closed-Loop: Digital Twin + Model Distillation

Research-backed prompting toolkit for Claude. System prompts, CLAUDE.md configs, and templates grounded in Anthropic's 2026 emotion vectors paper.

Agentic AI ex-US equity evaluator (LangGraph+Gemini)

🚀 Production-ready Android Jetpack Compose renderer for A2UI Protocol. Let AI agents dynamically generate beautiful, interactive native Android UIs with 20+ components, smart data binding, validation, and full accessibility support. Android 5.0+ compatible.

Comprehensive documentation for Hermes Agent by NousResearch — the self-improving AI agent (v0.2.0)

Daily in-depth Chinese analyses of frontier AI research papers, including topics such as LLMs, agents, RAG, and RL. AI 前沿论文中文深度解读

CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents

openai-functools: Simplified Generation of OpenAI Functions JSON Metadata for OpenAI Function Calling

Model eXecution + Context Protocol: Enterprise-Grade Data-to-AI Infrastructure

Developed an AI-powered supermarket analytics system using LSTM, K-Means, and Apriori to predict sales, segment customers, recommend products, and optimize inventory through an agent-based architecture with a Streamlit dashboard.

Compass is a context engine that builds a knowledge graph of your organization's metadata, capturing entities, relationships, and lineage across systems and time, making it discoverable and queryable for both humans and AI agents.

Open-source framework for agentic quantitative finance research.

Yet Another Deep Dive Clone (YADDC): An automated system that transforms academic research papers into engaging podcast conversations using CrewAI and ElevenLabs.

Your AI Data Copilot - Interact with your data sources and analyse your data, operations effortlessly with a sleek, neo-brutalism interface. Chat with your data in real-time, get results, and visualize your data points—all in one place.

Implementation of Google Deepmind's AI co-scientist with LangGraph and GPT Researcher

AI-powered Zotero research assistant — MCP server + agent skill

MCP server for Copilot Money App - AI powered personal finance queries using local data

Pinecone.io Golang Client

TypeScript SDK for MCP server observability, built on OpenTelemetry. Gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. Integrate with any OpenTelemetry ingest service including the Shinzo platform.

(2023 ITSM) Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges

This is a dataset intended to train a LLM model for a completely CVE focused input and output.

Build an Autonomous Web3 AI Trading Agent (BASE + Uniswap V4 example)

Let AI agents run research experiments + train small language models (in your browser!)

[IROS-2025] MAPF-GPT-DDG is a scalable decentralized multi-agent pathfinding (MAPF) solver based on imitation learning. It builds upon MAPF-GPT by introducing a novel fine-tuning method called Delta Data Generation (DDG) — a reward-free active learning approach that identifies and corrects failure cases in the policy.