Havuz

Practical engineering knowledge for building and operating production AI systems — LLMs, RAG, agents, inference, evaluation, system design,

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

FlowState QMD — Anticipatory Memory for AI Agents. Hermes 2026 Hackathon Entry.

一个本地ai聊天模型localaiAgentWithRAG，让你的本地数据不上传云端，可以自己加入所需要的记忆文件等等，修改角色形象，记忆对话，记忆库允许自己导入或者对话后自动记录

Local-first markdown notes with a first-class MCP server. 16 tools + 2 resources for Claude Code, Claude Desktop, Cursor and any MCP agent.

A production GenAI architecture guide for Forward Deployed Engineer (FDE) and Applied AI interviews—RAG, agents, evals, security, and operat

croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and en

Local-first desktop assistant for the whole job hunt — scrape listings, match with a local LLM, generate applications in your own voice, and

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

Production-oriented multi-agent course advisor with deterministic action governance, offline regression evaluation, SSE contracts and observ

A multi-tenant vector database focused on extreme RAM efficiency. Lightweight, scalable, and optimized for high-density deployments.

A local, open-source alternative to NotebookLM. Chat with your documents using any LLM.

本地优先的角色 Agent 工作台：通过自然语言完成资源管理、服务启动、知识检索、语音处理与可恢复长任务。

One-click knowledge system for documents, internal bots, and AI agents

基于 FastAPI + Vue 3 构建的智能客服系统，具备 RAG（检索增强生成）与 AI Agent 核心能力，可为企业提供高效、可扩展的智能客服解决方案。

Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance

Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Im

Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservic

Transforme Claude Code en générateur autonome de knowledge vault Obsidian. Pattern Karpathy. Par LE LABO IA.

Local-first CLI + MCP server: Any file → AI-ready Markdown + JSON

CloakPipe is the verifiable control plane for production AI agents: evaluate a release, certify it, enforce it at runtime, and prove what ha

A local-first second brain for scientists, researchers, coders, and nerds.

Synthetic datasets, experiment protocols, and evaluation code for "Governed Memory: A Production Architecture for Multi-Agent Workflows"

X-ray for documents: lossless PDF & PPTX extraction to JSON with bounding boxes, fonts, and colors — CLI, HTTP API, and an in-browser playgr

A very fast, feature-packed, AI-first Markdown (CommonMark/GFM) gem for Ruby, based on pulldown-cmark (Rust).

RoR engine that enables natural language queries over your database using RAG and LLMs.

道路交通事故的分析报告生成系统

LingXi: multi-agent CTF and pentest framework originated from Tencent Security Hackathon

Reference Java & Spring implementation of the Open Ingestion Standard (OIS). It provides a secure, decoupled, and vendor-neutral enterprise

Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection,

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI

A comprehensive hands-on, AI-first Python curriculum with 80+ interactive Jupyter notebooks for AI Engineers from core basics to LLMs, RAG,

Markdown-first work-memory protocol for existing agents, with maintained knowledge, candidate notes, evals, and an example KB.

"Review Ducktective" is an automated code review platform based on an LLM: it takes a diff as input and outputs structured findings with sev

A terminal-based, multi-domain support-ticket triage agent grounded in a local support corpus.

Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-we

基于 FastAPI + RAG 的多模型智能客服平台。 装完依赖点一下运行，剩下全在网页上配 —— 不改配置文件，不跑初始化脚本。

Advanced Memory for LLM characters

Production-ready cross-border e-commerce multi-agent system built on AgentScope 2.0 with DDD onion architecture, GatewayThrottle, semantic c

GIS agent是一个基于 ArcGIS Pro 3.6 的 arcpy构建的开源的地理空间智能体（AI Agent）框架。其核心设计采用独特的三层抽象架构（模型抽象、输出标准化、提示词动态适配），将您的自然语言指令与底层大语言模型及专业 GIS 工具链解耦。智能体自身能通过

A verifiable, time-aware knowledge ledger your LLM keeps for you. An evolution of the LLM Wiki pattern, built on Claude Code.

Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.

Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries

Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek

Persistent project memory for AI coding agents — isolated workspaces per project, web dashboard to review what your agent remembers, team co

A schema standard for LLM-compiled personal knowledge bases. AGENTS.md spec, templates, worked example, spaced repetition learning layer.

Local knowledge base for AI agents (hermes plugin): hybrid search over your PDFs, DOCX, sites, YouTube and Obsidian; answers grounded strict

Framework for building continuous-loop autonomous AI agents.

Smart India Hackathon 2025 repository featuring AI-based solutions including a multimodal offline RAG system and a blockchain-enabled touris

A brain for your mail: MailFathom turns IMAP mailboxes into a self-hosted, AI-native service. Mail synchronizes into your own PostgreSQL, is