Data agents

transformers gguf qwen moe mixture-of-experts agent

Open-source Java/SpringAI/Spring Boot AI enablement/orchestration layer for applications with RAG, governed actions, providers, vector stores, PII, tenant safety, chat memory, and behavior analysis.

GPON/XGS-PON OMCI Semantic Analysis Framework for ITU-T G.988 protocols (ONT Management and Control Interface).

A comprehensive, practical, beginner-to-advanced guide focused on the Google Agent Development Kit (ADK). It is intended for AI/ML engineers, or aspiring ones, who understand Python, LLMs, embeddings, vector databases, and Retrieval-Augmented Generation (RAG) and want to master modern agentic AI systems.

Docker-based, multi-tenant platform for autonomous AI agent ecosystems — runs on local or cloud models, with built-in cross-instance federation. Source-available under the PolyForm Small Business License.

A fully featured mcp with a robust agent toolkit for Ableton Live.

A free, open-source roadmap to learn AI from zero — 34 lessons from your first line of Python to shipping an LLM app. Read on the web or straight from the Markdown.

Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars

A free, open-source Dynamic Island for Windows 10 & 11 — media controls, focus timers, notifications, system stats & a private AI assistant in a sleek always-on-top pill. Built with Tauri + React + Rust.

gguf llama.cpp llama-cpp ollama lm-studio minicpm

Preserve engineering cognition in the age of AI agents ~~ 4 seconds per Git event is 2 letter-grades of skill-retention saved.

Autonomous Deep-research agent and discovery platform for the Y Combinator ecosystem, turning public YC data into structured company intelligence.

A Multi-Agent RAG Support System using Google ADK, Milvus, Supabase, and Crawl4AI

面向《崩坏：星穹铁道》的配装配队优化：已成体系的战斗模拟 DSL 文档与多源数据管线；仿真引擎（干净设计：事件总线 + 闭合关键字 DSL）与 autoresearch 式 agent 开发中。

Stock research dashboard unifying market data and AI-derived news sentiment, with a built-in research assistant for investigating, comparing, and explaining stocks using live sources and cited evidence.

llama-cpp-python gguf llama tool-calling function-calling ai-agents

KLEA: Knowledge vaLidated Expert AI assistant for science/research

Measure whether an agent solves the same task the same way twice: path signatures, entropy, divergence, and a minimum-run stability gate.

Adapters required to use Nous Research Hermes 2 Pro as a function calling LLM

Open-source Agent Skill for multi-perspective research, evidence-aware synthesis, and auditable AI-assisted decisions.

Shared memory for AI agents, no database, no server, just a GitHub repo. Memories that worked get stronger; memories that failed fade.

Turn CRM and transcript data into structured, versioned deal intelligence. 6 agents, 3 frameworks, harness-agnostic. Works with any CRM, any transcript provider, any LLM.

Market Signal Radar: AI Agent blueprint to detect Problem-Market Drift using OpenClaw, Node.js and Postgres.

LangChain integration for Milvus vector database and semantic search

Customizable RAG chatbot made with LangChain, ChromaDB, Streamlit using gpt-3.5-turbo, text-embedding-ada-002 also sporting database integration

Modular role‑playing chatbot framework built on LlamaIndex & Melobot — supports RAG‑driven role‑play and general QA, with built‑in scheduling (including daily RSS news aggregation) and admin features, offering both OneBot V11 (QQ) and CLI adapters.

A research framework to evaluate how document parsing quality determines downstream RAG performance.

An AI-powered healthcare support system utilizing a three-model architecture for accurate, safe, and research-backed health assistance.

Your Personal AI Agent for Stock Market Analysis and Guidance. Smart Investing Conversations Start Here!

This is the official page of the paper "AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science."

MCP agent for semantic metrics governance with built-in trust scoring, lineage visualization, and conversational metric definition. Designed for data teams working with dbt, LookML, and modern semantic layers.

Image search application built with the vector capabilities of OceanBase

This project aims to develop a natural language interface (NLI) for Prefect workflows using generative AI (GenAI). The prefect agent will analyze user input, determine the appropriate Prefect flow to execute, and trigger the flow with the necessary parameters.

OpenBrain is an open-source machine-readable memory layer for agentic systems. It stores typed, versioned memory objects (claims, decisions, tasks, artifacts, entities, relations, thought summaries), supports structured queries + semantic search, and exposes a standard plug-in protocol via MCP.

An agentic chatbot that performs philosophy research.

AI agent for log monitoring

Automated RSS flux monitoring system

CYBERNETIC AGENTS

AI Agent platform for online meeting agents with Google Vertex AI, Datadog and Elevenlabs integration.

Multi-provider AI usage monitor with real-time dashboard, desktop pet overlay & ESP32-S3 hardware companion — tracks Claude, OpenAI, DeepSeek, Ollama and LM Studio. Expanded from the original Clawdmeter project.

Professional Windows desktop app that converts JSON/Text to TOON format, optimizing LLM token usage by 15-30% while maintaining 100% data fidelity.

Evaluate multimodal agents on complex, realistic visual tasks involving multi-step workflows in dynamic environments.

Multi-tenant AI runtime control plane for risk scoring, policy enforcement, and evidence-preserving agent operations.

🖼️ Generate stunning images easily with intelligent prompts from a database of 6000+ curated options, tailored to your specific needs.

A deep research agent implementation using Google's Agent-to-Agent (A2A) framework with Model Context Protocol (MCP) tools

GPU-Accelerated Data Science Agents

AI Native Semantic Language

A robust city information workflow using Crew-AI, featuring multi-agent orchestration, Pydantic validation, and OpenLIT observability for monitoring AI interactions.

MCP server for Power BI - Business analytics and data visualization

Analytics your AI agent can actually query. Tiny SDK that pipes events to BigQuery — ~$0/mo at indie scale, no dashboard, no vendor lock-in.

Cache-aware orchestration for LLM agents. Fork helpers that share cached prefixes, detect cache breaks, and cut token costs by 38%+.

🔬 Implementation of agent coordination architectures and scaling principles from 'Towards a Science of Scaling Agent Systems' (arXiv:2512.08296). Research-backed multi-agent framework with benchmarks and validation.

2025 research prototype of an agent that adapts its own success criteria per iteration (MCDM-scored loop). Preserved as the conceptual origin of Bernstein — retrospective inside.

Constitutional framework for human sovereignty in the AI-native era. A systematic approach to preserving human agency through 23 core protocols and the Dual-Circle Symbiosis Model.

A local agent architecture for semantic-aware interaction between large language models and multidimensional microscopy datasets inside napari

Temporal memory for your AI agents, financial research, and knowledge workflows.

A framework for resonance-based decision-making in artificial agents, combining celestial influences, memory feedback, and symbolic emergence.

Seren CLI & MCP

Powerful and Flexible Datagrid Engine.

A dynamic application for both HR professionals and job applicants to evaluate resume strength against a job description. Get a comprehensive score and personalized tips powered by Gemmi AI.

MCP server that lets AI agents run real user interviews and retrieve themes and quotes.

Plan-aware agent orchestration for Pi. Grove reads a structured markdown plan, parses it into work streams with dependencies, and orchestrates parallel AI agents to execute them — all monitored through a real-time web dashboard.

Context Pressure — AI Context Window Monitor for macOS

The only agent memory that gets better over time. Nightly consolidation, active forgetting, salience scoring. 9.01/10 on AMB benchmark. Local-first, Apache 2.0.

Observantio's Resolver is a ground-up AI engine for modern observability. It correlates metrics, traces, and logs into a unified intelligence layer that detects anomalies, forecasts trends, and automates root cause analysis (RCA).

loafer is an AI agent designed to automate the ETL (Extract, Transform, Load) process, enabling data engineers to efficiently transform and load data into their target systems.

Advanced Claude skill to analyze Polymarket traders. Fetches on-chain data, computes ROI/performance, and detects trading strategies (Arbitrage, Whales, Market Making).

Automatically generate high-quality company research reports.

CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories

LLMWorkbook is a Python package that integrates Large Language Models (LLMs) with tabular datatypes - workbooks and dataframes for seamless data analysis and automation.

AI assistant for biophysically detailed neuronal modelling (NeuroML) and data analysis

A Q&A RAG AI assistant and web crawler

Tavily-OpenAI connector harnesses Tavily's web research capabilities and LangChain's AI toolkit to create intelligent, internet-connected agents powered by OpenAI models.

An integrated AI suite combining intelligent PDF analysis, automated research capabilities, and multi-agent academic paper generation, powered by both cloud and local language models to streamline research and document processing workflows.

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

In this project I have built a RAG pipeline to showcase how we can augment LLM knowledge with additional data.

Optimizing a Retrieval-Augmented Generation (RAG) system on the CNN/Daily Mail dataset using LangChain, with performance benchmarking and analysis via RAGAS.

Solution for the Trustii's "Secure RAG System" Data Challenge 2024

🚀 AI-powered financial market intelligence system using Google Gemini, LangChain, RAG & multi-agent orchestration. Real-time stock analysis, sentiment analysis, and ML-based predictions.

Langchain | OpenAI | Train with Custom markdown data

An accessible, reliable, and efficient platform for medical information and support using LLMs

Chatbot from pretrained LLaMA-2 LLM model, fine-tuned with medical research papers using RAG (Retrieval-Augmented Generation)

Two approaches to generating optimized embeddings in the Retrieval-Augmented Generation (RAG) Pattern

Python library designed to protect sensitive data when interacting with third-party LLMs.

This project leverages Langchain and Groq to analyze conversations between recovery agents and borrowers. The analysis includes summarization, key actions identification, sentiment analysis, named entity recognition (NER), and non-compliance checks.

A Python-based tool for context-based search across text documents using OpenAI embeddings and Chroma vector storage. This system enables efficient querying of document collections by generating vector embeddings, storing them persistently, and retrieving relevant results based on textual queries.

Python package that makes it easy to spin up a custom Retrieval-Augmented Generation (RAG) pipeline.

Deep researcher using langchain-ollama with deepseek-1.5b model.

Demo LLM (RAG pipeline) web app running locally using docker-compose. LLM and embedding models are consumed as services from OpenAI.

TARS Robot AI-Agent Data-over-Sound Commands and Bluetooth-Controlled Mecanum Chassis

LangGraph-based multi-agent deep research system

AI Agent - powered time tracking and productivity app with a personalized mentor persona, featuring smart timers, analytics, calendar integration, and a modern UI.

Implementing Retrieval Augmented Generation (RAG) via using GPT-3.5-Turbo as the LLM model and Langchain to simplify the implementation, with the data being feed is in the form of list to make it easier to understand.

Leverage the power of multi-agent AI to fuel your daily tech, programming, and architecture insights.

🤖 Automate data analysis and machine learning with a multi-agent system that provides insights and reports efficiently using advanced AI technologies.

Retrieval-augmented generation (RAG) system for medical Q&A using the Merck Manual of Diagnosis and Therapy (19th Edition). Semantic search via ChromaDB and GTE-large embeddings; answer generation with Mistral 7B (GGUF). Runs fully locally for privacy, with optional GPU acceleration.

Integrating Databricks Genie as a tool in CrewAI agents.

A simple showcase of how to leverage a CrewAI agent inside of a Streamlit UI to analyze Hackernews top posts.