#knowledge-base

📚 Student LLM Wiki — AI-compiled knowledge base for university students. Drop course slides, get a persistent interlinked wiki. Feynman review, exam prep, confidence decay, cross-course connections. Based on Karpathy's LLM Wiki pattern. Works with Claude Cowork / Claude Code / Claudian + Obsidian.学生大语言模型维基百科——专为大学生打造的AI编译知识库。

Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.

Claude Code Skills, Agents & Plugins — UitKit

Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.

Portable marketing second brain for Codex, Claude Code, and Agent Skills with 502 sources for strategy, SMM, content, growth, CRO, and buyer psychology.

Ready-to-fork starter for an AI-maintained knowledge base on the Open Knowledge Format (OKF) v0.1 — Markdown + YAML frontmatter, with a Claude Code skill, conformance validator, and EN/TH docs.

AI-powered knowledge base on a USB stick. 3D graph, markdown wikilinks, works with Claude Code & OpenCode. Zero install, fully portable.

AI agent knowledge & long-term memory · MCP server, knowledge graph, BM25 + RRF retrieval · drop-in for Claude Code/ Openclaw/ Cursor / Codex / Hermes

Trustworthy AI Knowledge Workbench — Verifiable RAG with citation tracking, document-grounded review, and self-contained desktop mode. Windows / macOS / Linux / Android / iOS.

Obsidian + Claude Code template: Karpathy's LLM Wiki as a 4-axis second brain

3D cockpit for markdown knowledge vaults — synthwave force graph, reader, finder, workspace, and real-time AI-agent activity replay & analytics. Zero deps, no build step.

把任意抖音博主蒸馏成可对话的 AI 知识分身 · download → transcribe → categorize → RAG

Self-hosted knowledge base for AI agents: ingest Markdown into Qdrant with H1-H...-aware chunking, hybrid (dense+sparse) search and cross-encoder reranking.

An AI-native KMS and next-gen RAG prototype. Enforces strict tree-shaped index constraints and compiler-like diagnostics after every write, enabling agents to self-heal knowledge structures and eliminate garbage-in, garbage-out RAG pain points.

AI-powered knowledge management platform with RAG, multi-engine OCR parsing, vector search, wiki graphs, and Agent skill integration. Docker Compose deployment.

Repository-native Work, Docs, History and durable Memory for humans and AI agents — Markdown as the source of truth, with a local UI, CLI and MCP server

An infinite canvas your local LLM draws on. Typed widgets, BYO model (Claude/OpenAI/Ollama), MCP-native, local-first, MIT.

Universal control system for coding agents: shared memory, cross-project handoffs, research management, & MCP + Obsidian dashboards across products/repos.

Memex.ai-Inspired AI Knowledge Base 2026 - Smart Markdown Wiki with Graph Search & Static Publishing

Local-first second brain: turns YouTube videos and podcasts into a searchable Markdown knowledge base with Claude. CLI + Telegram bot.

A knowledge-precipitation harness for Claude Code and Codex — the workflow is the pipe, knowledge is the moat. Single Rust binary + per-harness adapters with real per-role isolation.

Self-hosted memory for Claude — markdown knowledge base with wikilink graph, hybrid semantic search (pgvector + Ollama), and a first-party MCP server. One docker compose up.

Topic-grained, layered memory layer for AI coding agents — local-first, MCP, single binary. Plug Claude Code / Cursor / Windsurf / Antigravity into persistent memory across sessions and machines.

Offline semantic search for everything on your disk - documents, code, PDFs, scanned images (OCR), video by the second. 100% local AI: hybrid RAG with keyword + vector + rerank, no API key, no cloud. Desktop app + 24 MCP tools for Claude Code, plus a multi-engine web researcher that quotes sources verbatim. 本地离线多模态语义检索

GTT Bot — a RAG-powered Discord bot grounded in an Obsidian knowledge base. Local vector search, Claude API for answers, built for the Goju Tech Talk community.

Persistent memory for Claude Code — your sessions distilled into a Google OKF knowledge bundle (plain markdown you own, not a database you're locked into) and injected back at the start of every session.

智造本质 · GEO文章库 — 制造业ISO管理体系知识库，面向AI搜索引擎的纯证据容器

🧠 AI 视频知识管理平台：把"收藏即积灰"的视频变成可搜索、可回顾、可对话的个人知识库。Save videos you'll "watch later" and turn them into a searchable, reviewable, and chat-able personal AI knowledge base — powered by LLM video understanding and RAG.

Persistent shared long-term memory + knowledge-ingest pipeline for AI coding agents (Claude Code, Codex…) over a Markdown/Obsidian vault. Inspired by Karpathy's LLM Wiki Pattern + GBrain.

Slack-native internal knowledge chatbot with nightly-reindexed RAG (Pinecone) and source-cited answers. Reference build behind a 50% onboarding-time-reduction case study.

Second brain / PKM starter template

AI-powered Industrial Knowledge Copilot that uses Retrieval-Augmented Generation (RAG) with Google Gemini to answer questions from equipment manuals, SOPs, maintenance guides, and safety documents using semantic search and source citations.

Persistent memory for coding agents over MCP — typed knowledge, semantic search, session lifecycle. PostgreSQL + pgvector, FastMCP.

File-native judgment practice for partner-coupled agents - propose then accept, thin load, your vault stays private

A filesystem for AI agents — mount the Unison brain as a real FS (FUSE on Linux, NFS on macOS) with a local SQLite cache, sync loop, and semantic grep.

A file-system memory architecture for AI agents: typed markdown, a mechanical placement algorithm, and a nightly consolidation loop. Specification + skeleton + worked example. No vector database.

Fast, private, client-side developer tools and clear references — plus explainers on modern AI infrastructure (context windows, MCP, RAG, embeddings, agent patterns). Everything runs in your browser; nothing is uploaded.

Plugin for Claude Code, Hermes Agent, and Codex that adds write operations (publish, sync, maintain) to a self-hosted SAG (Zleap-AI/SAG) knowledge base — without modifying SAG's source code. Agents self-assess and auto-publish durable knowledge under a safety floor (secret scan, dedupe, cost cap), with manual commands always available.

Self-hosted local-AI stack over Ollama: private chat, a structured-output API, and a QLoRA fine-tune → serve → chat loop. No cloud, no secrets.

🧠 Self-learning, always-on personal AI agent on your Claude Max subscription — terminal + Discord at once, persistent memory, a structured knowledge vault, autonomous skills & heartbeat. Self-hosted, open source.