agent

It allows users to query databases using natural language and receive results as SQL code and beautiful visualizations.

[ICML'26] Toward Human-like Audio-Visual Intelligence of Omni-MLLMs

Frontend interface for building chat based system and connecting with agent driven workflows.

🔒 Privacy-first MCP server for Claude using PostgreSQL + Ollama. Local alternative to cloud-based code context with full data sovereignty. No API keys, no external calls, 100% local.

Pizzly, financial market analysis combining technical indicators with LLMs, featuring real-time data processing and AI-powered market insights ⚡️

Official Implementation of "Visual Agentic Memory: Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval"

A curated collection of Claude Code agent skills that accelerate the entire vLLM development lifecycle.

Cognitive-structured Multimodal Agent (CMA-Harness): a memory-centric agent for long-horizon multimodal understanding, generation, and editing — externalizing visual history into episodic memory with selective retrieval. Includes the M2CA-Bench benchmark.

项目描述：为解决电商客服在物流、售后等高频咨询场景下，人工重复查询、知识定位慢及信息需反复核对等痛点，搭建 Agent 智能客服系统。通过意图分流、业务工具调用与 RAG 知识库检索，完成订单物流查询、售后信息收集和商品问答，提升响应效率与回答准确性。

This repository contains practical AI projects applying machine learning techniques to real-world problems.

A curated list of papers, benchmarks, project pages, and code for proactive agents.

It is a chatbot based on LangChain.

The blazingly fast in-memory vector database 🚀

It is a case study of an intelligent agent for Ocean.

A multimodal live AI assistant designed to enhance the browsing experience using Gemini.

AI 面试训练系统：跨会话能力建模闭环 — LangGraph 编排 + 三层上下文融合出题 + Mem0 式画像更新 + RAG 知识增强 + SM-2 复习调度。FastAPI · React 19 · LlamaIndex · Qdrant

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。

Agent skill that prepares a Linux server with NVIDIA GPUs for LLM workloads - driver and CUDA, Docker with NVIDIA Container Toolkit, staged verification gates, compose presets for vLLM, Infinity, OpenWebUI and Ollama