> Project Note: This project was primarily developed using AI (Cursor AI) with minimal human code intervention. It was created as a self-imposed challenge to evaluate the current capabilities of AI coding assistants. While the AI was able to generate most of the functionality, success required p
> 比 Claude Cowork 更底层、更自主的 AI 智能体系统
AI-powered contract review copilot built on Streamlit, designed for Alauda's enterprise SaaS/PaaS business. Combines senior legal partner acumen with LLM panoramic reading to seal fatal loopholes in B2B contracts within seconds.
zjwangalauda__Alauda-GROS-Copilot
- 语义检索：基于向量相似度的智能匹配，理解语义关联 - 全文检索：BM25 算法精确匹配关键词，适合查找特定内容 - 混合检索：结合两者优势，可自定义权重平衡（默认语义 0.7 + 全文 0.3）
一个生产级的个人知识库系统，支持语义搜索和基于 LLM 的问答功能。
English | 简体中文
> 📚 推荐阅读：如果你关注的是"如何从真实问题到系统设计"，建议先阅读 方法论文档。
输入一个问题，系统自动从远域知识中发现结构同构，生成跨领域创新假说，经多模型验证与风险精炼，输出包含直接答案、可追溯证据和风险边界的完整研究报告。
請確保您已安裝 uv，然後執行：
A fully automated research system for quantitative finance that orchestrates the entire research lifecycle—from literature review to experiment execution to report generation—using a multi-agent collaboration architecture powered by Claude AI.
Using GPT-5 (or Claude 4.5 opus, Gemini 3 pro, Llama 3.2 on Vertex AI), generate a 3D CAD model (STEP file) from a 2D CAD image.
Using GPT-5 (or Claude 4.5 opus, Gemini 3 pro, Llama 3.2 on Vertex AI), generate a 3D CAD model (STEP file) from a 2D CAD image.
Context Manager is an intelligent memory management system designed to solve the context window limitations in large language model (LLM) applications. It treats context as expensive RAM and external data as pageable disk/cache, providing a "memory manager" subsystem for models.
AI Companion for Humanity
AI人狼ゲーム — 1人のプレイヤーが8体のAIと人狼を遊ぶWebアプリケーション。
An agent that can't do math. A calculator it can call. Word problems it has to solve.
Vijil Dome is a fast, lightweight, and highly configurable library for adding runtime guardrails to your AI agents. It combines top open-source LLM safety tools with proprietary Vijil models to detect and respond to unsafe content — with built-in support for observability, tracing, and popular a
llm-box brings the power of large language models to your command line. Instead of just listing files, it describes what they do. Instead of dumping file contents, it explains them. Instead of searching by filename, it understands what you're looking for.
A modern AI chatbot application built with Streamlit, FastAPI, and LangChain, powered by Ollama for local language model inference.
AI pipeline that scrapes 22+ RSS sources, clusters articles into business trends via Leiden community detection, then runs a LangGraph agent pipeline to find target companies, contacts, and generate outreach emails. Self-learns through 6 feedback loops (Thompson Sampling, EMA drift, weight adaptatio
Official LangChain integration for Ujeebu Extract API - Extract clean, structured content from news articles and blog posts for use with Large Language Models (LLMs) and AI applications.
> roshni (روشنی) — "light" in Urdu
O Banco Ágil é um sistema de atendimento virtual para um banco digital fictício, onde agentes de IA especializados trabalham em conjunto para atender o cliente de forma transparente. O cliente percebe uma conversa fluida com um único atendente — os handoffs entre agentes são invisíveis.
LangChain-based harness to benchmark memory compaction on long-horizon web QA tasks (e.g., BrowseComp-style questions).
topcuburak__agentic_carbon_characterization
Forging Elite AI Systems
Unified code quality pipeline for AI-assisted development.
AI-powered investment research platform that combines 18 analyst agents for market analysis with automated content generation and optional live trading.
Kiro-style Spec Driven Development implementation on AI-DLC (AI Development Life Cycle)
A production-ready Retrieval-Augmented Generation pipeline for answering questions over Kazakh company annual reports written in Russian/Kazakh, featuring complex PDF layouts (financial tables, ESG diagrams, multi-column blocks).
LegacyLens is a production-focused RAG workspace for Fortran/LAPACK code intelligence.
Multi-agent RAG system for Type 1 Diabetes management with mandatory safety guardrails and authoritative knowledge grounding.
the-schoolofai__ragchatbot-langchain
the-schoolofai__langchain-chatbot
A LangGraph-powered MCP server for infrastructure orchestration with autonomous subagents.
thahiti__agent-prototype
> Deterministic, config-driven guardrails for LLM agent tool calls. > Zero-LLM enforcement. Compliance audit trail built in.
> Guardrail lifecycle for LLM agent tool calls. > Define. Lint. Enforce. Test. Measure. Audit.
FastAPI backend for the Certis patent drafting platform.
> 基于 LangGraph 和 Milvus 的企业级 AI 多智能体协作系统
Before ANY work on this project, complete these checks:
Your intelligent document assistant powered by RAG (Retrieval-Augmented Generation)
> Offline-first, extensible AI Agent runtime in Python 3.11+ / pydantic v2
Documentation: DSPy Docs
A comprehensive demonstration of LangChain foundational models with examples for basic invocation, model customization, multiple providers, agents, and streaming responses.
Run the complete pipeline with:
- Python 3.11+ - uv package manager (installation guide)
You're about to build a multi-agent orchestration system using LangGraph that analyzes company earnings reports. This assignment will showcase your ability to design, implement, and containerize a production-ready multi-agent workflow.
Submission Deadline: 48 hours from receipt