Havuz

🚀 多Agent协作智能知识库系统 — 五层可编排Agent架构 + RAG全链路 + 统一ToolRegistry，Spring Boot + FastAPI + React，核心亮点是 五层可编排 Agent 架构——Interface、Orchestrator、Tool、M

Open-source natural-language analytics platform that converts business questions into safe, explainable SQL.

A quiet, layered memory engine for long-term human-AI relationships.

Spring AI multilingual customer-service Agent platform for cross-border ecommerce, with RAG, order tools, escalation, and Vue admin UI.

面向中文内容创作者的 AI 写作工作台 | Harness 单层 Agent 编排 · 多源检索 · 风格化写作 · 质量评审 · 分层记忆 · 编辑部多 Agent 协作

Open-source causal graph memory for AI agents. 85.55 on LoCoMo under a frozen, reproducible protocol. MCP server with ACT-R scoring, spreadi

llmwiki (Quiz_wiki) — auto-captures your coding-agent sessions (Claude Code / Codex / OpenCode) into a compounding, local-first project wiki

A hex-native embedded database for Go. Morton keys, native ring scans, seams (contradictions), MVCC, provenance, and optional HNSW embedding

把财经博主的喊单变成可追踪的战绩:AI 标立场 · 记转向 · 回测跑赢大盘 | Turn finfluencer noise into trackable signals — AI stance labeling, flip radar, beat-the-market bac

Local-first LLM wiki — ingests your documents into a curated, citation-backed knowledge base you can read and chat with. Marimo + SQLite/FTS

Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL review

High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-on

Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.

Self-hosted chat-with-your-database: natural-language questions answered by real read-only SQL, with a curated context layer and a physical

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matry

A local-first, LLM-agnostic memory layer for AI assistants

Governed AI analytics from natural language to auditable SQL, powered by a mandatory semantic layer, policy enforcement, and a visual Studio

Self-hosted NL-to-SQL analytics — query your database with plain English

Apricity — a fast, local-first web UI for MemPalace: browse, search, edit & curate your AI agent's memory, knowledge graph & vector store. Z

Cloud IDE + autonomous AI coding agent - Kubernetes-powered instant dev sandboxes with LangChain ReAct agent that reads, writes & ships mult

Local-first, open-source AI assistant platform built with Java, Spring Boot 4 and Spring AI 2.0

AI-powered Lead Qualification & Routing System built with n8n, Gemini and Python.

Sistema Operativo de Memoria y Orquestación para Desarrollo con IA

AI Town Portable is a browser-based multi-agent simulation built on Generative Agents, with LLM-driven residents, long-term memory, planning

Validated, private, shareable knowledge-graph memory for AI — per-tenant, write-gated, PostgreSQL-authoritative, served over MCP.

Production-ready RAG assistant for Moodle — containerized with Jenkins CI/CD on AWS.

High-performance LLM gateway in Go. 35x less RAM than Node.js version.

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works w

Advanced RAG (Retrieval-Augmented Generation) system for private document intelligence. Uses OpenAI GPT-4o and Vector Databases to provide z

Terminal-first workspace for supervising AI coding agents (Claude Code, Codex, Gemini): live agent status per project, code viewer + Git, sy

Persistent, queryable memory for AI agents with intake policy, smart recall, context packs, graph recall, and multi-agent scoping

Twoja pierwsza i ostatnia strona, na której będziesz sprawdzać co się dzieje w sejmie

Independent token usage and work-purpose audit service for New-API, with SQLite, LLM classification, HTML

生产级 LangGraph + FastAPI AI Agent 框架，支持阿里云 Qwen / DashScope，含中文注释、长期记忆、向量检索完整链路。

One prompt → a swarm of 150+ specialist Cursor agents that plan, build, test & harden your whole project in parallel, sharing an Obsidian br

Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief r

Local-first memory for AI agents: one SQLite file, zero deps. Recency-aware exact recall, conflict detection, time-travel journal, MCP serve

Evidence-first memory for Claude Code, Codex, and the terminal. Kimetsu sits beside your AI agent, watches what actually solves problems, re

Knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph the agent navigates over MCP. Curated summari

Postgres MCP Server

Stop reading AI replies. Your LLM places typed widgets (charts, kanbans, code, live timers) on an infinite canvas. Any model incl. local Oll

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summa

pi-loop-studio/orchestra — evidence-driven, recoverable multi-agent engineering runtime with XState, SQLite WAL, isolated worktrees, indepen

AI-powered shopping assistant to search, compare, and track product prices across Vietnamese e-commerce sites — built with Google Gemini, Fl

😼 AI-участница Telegram-чата с памятью, локальными мемами, реакциями и собственным характером