Havuz

This is a mathematical discovery engine, which searches new mathematics applying techniques to existing results

🚀 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

Claude Code plugin for building LLM-maintained Obsidian wikis from raw research — compile, query, lint, and evolve your personal knowledge b

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every

Zil lang DSL for Lean 4

Persistent memory for AI agent teams: private silos, shared hive, and curator workflow.

DURU — 두루 돕는 AI · 내 PC에 설치해 내 문서를 근거로 답하는 AI 에이전트. 망분리 환경 동작, 지식베이스·에이전트를 암호화한 파일로 공유. An on-premise AI agent that answers from your own doc

A marketing world model for merchants — make marketing data findable, understandable, and usable for AI, agents, and MCP apps.

一体化 AI 工作平台 SaaS

AI Agent engineering and quantitative finance knowledge base: source-level architecture analysis, Agent-to-Agent protocol research, runnable

Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clie

Turn any YouTube video into a deck of timestamped knowledge cards. Runs locally, works with free models.

Your agents, briefed. Not flooded. Self-hosted context compiler: git-backed team knowledge served to coding agents as token-budgeted bundles

A deliberately lite personal brain: Obsidian to browse, Claude Code or Codex for everything else. No vector DB, no embeddings, no MCP server

Knowledge-base-driven article generation, fact audit, and 7-platform publish packs for WeChat, Xiaohongshu, Zhihu, Juejin, CSDN, Toutiao, an

Vault health, connection review and Recall for Obsidian. Studio recipes and editable diagrams in the 2.3.0 release candidate.

Local-first AI bookmark manager with semantic search, cleanup review, Chrome sync-back, and MCP support.

Research Pilot helps AI agents understand, maintain, and advance research projects through papers, claims, evidence, experiments, and human-

Compile documents into a living Obsidian wiki. Any AI agent. Based on Karpathy's LLM Wiki pattern.

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

An open, source-audited field guide to general game development: 143 principles for humans and AI.

A self-improving knowledge base about LLM agent infrastructure

The first LLM-maintained knowledge wiki purpose-built for Product Managers — Karpathy's LLM Wiki pattern turned into a PM schema, rituals, a

A structured knowledge base for large language model technologies, covering LLMs, Agents, RAG, model training, evaluation methodologies, and

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

Open Knowledge Format with JSONSchema

Local-first memory context for Pi coding agents.

Constantly-updated memory for your legal documents.

AI-managed personal knowledge base using Karpathy LLM Wiki Pattern. Obsidian vault with automated workflows for ingestion, compilation, Q&A,

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

Claude Code skill implementing Karpathy's LLM-wiki pattern on a personal GitHub repo, with qmd for on-device hybrid search.

The open-source CMO: growth playbooks from 16 operators (Cursor, Notion, Linear, Deel, Gamma, Granola...) as an installable AI skill

Open-source agent skills for building scope-safe Markdown knowledge vaults with deterministic validation and research workflows.

中文 GBrain 实操手册 for Amazon sellers: build an AI-native second brain with real commands, examples, governance, and Agent workflows.

Self-learning AI agent that gets smarter and cheaper over time. Routes between local and cloud LLMs, learns from every interaction, remember

Sovereign personal memory network starter · markdown + git · AI-collaboratable · clone & use immediately

Your AI forgets. A wiki doesn't. Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base — verify links, fil

Permission-aware Agentic RAG for enterprise knowledge bases — folder ACLs, hybrid retrieval, OCR, grounded citations, and secure LLM evidenc

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

Crow: build your second brain from the documents on your computer. Downloads for macOS, Windows and Linux.

CogDoc — 面向个人与团队的本地优先 AI 知识与研究工作台：多源 RAG、Deep Research、可验证引用、审核闭环、细粒度 ACL 与 Rust 加速混合检索。 CogDoc — A local-first AI knowledge and research w

Karpathy-inspired LLM Wiki demo: AI agents compile raw sources into a persistent, self-linking Markdown knowledge base. The Agent writes. Th

Evidence-grounded AI secretary for Claude Code and Codex, with frozen context, deterministic retrieval, bounded quality review, and explicit

Shared project knowledge and handoff for coding agents across long-running projects

格物 · 大模型知识库 — 628 篇 AI 大模型深度解析离线镜像（全文搜索/PDF网页化/标注/账号体系）

Local-first Markdown memory for AI agents · 跨 Agent 本地长期记忆系统

LLM WIKI 知识工厂 — Reasonix Skill：端到端知识库构建流水线（查重清理→格式转换→LLM理解融合→Obsidian输出→持续维护）

Mint 是本地优先的 AI 知识工作台：将文档、网页与对话沉淀为可持续积累的 LLM Wiki，借助 Agent 与记忆 理解和复用个人知识。采用 SDD 规格驱动开发，以自动化验收闭环交付。

DocUp is a lightweight personal blog and knowledge base built with Next.js, React, and Notion.

Local-first crystalline intelligence for AI agents: the knowledge that endures across sessions, taught as Markdown Domains and captured as E