16 boosters for "knowledge-base" — open source, verified from GitHub, ready to install
"name": "understand-anything", "description": "AI-powered codebase understanding — analyze, visualize, and explain any project", "homepage": "https://github.com/Lum1104/Understand-Anything",
"name": "arscontexta", "description": "Conversational derivation engine — generate agent-native memory architecture from natural conversation. 15 kernel primitives, 26 commands, 17 feature blocks, 3 presets.", "url": "https://arscontexta.org"
"name" : "neo.mjs", "version" : "13.0.0", "description" : "Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.",
This wiki is maintained entirely by your coding agent. No API key or Python scripts needed — just open this repo in Codex, OpenCode, or any agent that reads this file, and talk to it. Describe what you want in plain English: Or use shorthand triggers:
Effect Patterns Hub is an MCP server providing a community-driven knowledge base for Effect-TS design patterns and functional programming practices. It benefits TypeScript developers using Effect-TS who need structured guidance on implementing complex patterns.
DyNote 是面向 Codex 这类 Agent 的抖音学习工具，不是一次性摘要器。核心原则是“数据资产先行，学习笔记后置”：先把字幕/转写、评论、元数据和 AI 快读沉淀为可复用资产，再按用户需求生成可追溯的学习笔记、总结和写作材料。默认目标不是字幕工程文件，而是先落一份原始数据包：、、、、、、，并用 归档可复用资产。默认把独立字幕轨或本地自动语音识别转写当作事实主干；当转写密度低、任务需要画面理解或用户只要快速筛选时，再用已登录抖音网页版的“问AI / 识别画面”补充，豆包只作为抖音 AI 不可用时的备用快读或待核验假设。 联网或登录态操作必须先使用 。不要读取、复制或打印 Cooki
"name": "@ragieai/mcp-server", "description": "A Model Context Protocol (MCP) server for Ragie", "author": "Ragie Corp",
<!-- Real instructions live in config/config.md and meta/instructions/general.md. This file only bootstraps Windsurf into those. --> Check whether exists. If it does, you are in framework mode — this repo is being used to develop or maintain the llm-context-base framework itself, not as a personal
人脑不是硬盘，不会无差别存储所有信息。人脑会： DNA Memory 模拟这个过程，让 Agent 真正"进化"。 并且仅在有新的 写入后才执行 ，避免重复归纳同一批记忆。
"name": "@aashari/mcp-server-atlassian-confluence", "description": "Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases us
"description": "LLM-powered personal wiki — autonomous knowledge base with research-on-miss, ingestion, search, a browsable web UI, and universal data gravity. Saves and retrieves knowledge automatically whenever relevant.", "repository": "https://github.com/Oshayr/llm-wiki", "agents/backlink-manage
"description": "Dual-scope knowledge base for LLM workflows with hybrid full-text + semantic search, typed relations, and publishing.",
"name": "research-skill", "name": "Hector Oviedo" "description": "Persistent project-scoped store for deep research findings",
Obvec transforms Obsidian vaults into AI-searchable knowledge bases using Cloudflare Vectorize and serverless Workers, enabling developers and knowledge workers to query their notes with AI-powered semantic search through Claude.
This booster enables AI agents to retrieve and summarize Zendesk ticket history and customer context, helping support teams provide informed, contextual responses without manual ticket searching.
Arbiter is a domain-agnostic knowledge hub MCP server that integrates Discord bot capabilities, AI agent functionality, and vector search for building intelligent knowledge management systems. It benefits developers building AI-powered applications that need flexible knowledge retrieval and Discord community integration.
