Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
Biologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. Zero runtime deps, SQLite, MCP. Benchmarked retrieval with an opt-in TypeSafe Jev reranker.
The open-source alternative to Paper.design. A multiplayer design canvas where humans and AI agents design together, live. MCP built in.
Every LLM starts every conversation from zero. Stash gives your agent persistent memory — it remembers, recalls, consolidates, and learns across sessions. No more explaining yourself from scratch.
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server giving coding agents a ranked, deterministic map of any repo, blast radius, tests-to-run and quality deltas.
Indexes any codebase into a structural knowledge graph — every dependency, call chain, cluster, and execution flow.
🦉 Augur — 本地优先的投资研究记忆系统：18 位投资大师独立分析 + 加权共识，证据带时间语义、每次运行可复查，CLI / Dashboard / MCP。A local-first research memory system with 18 investor personas.
MaverickMCP - Personal Stock Analysis MCP Server
Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client.
The Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.
MCP server to deploy apps to Cloud Run
Pre-build reality check for AI coding agents. Scans GitHub, HN, npm, PyPI, Product Hunt. MCP server. 290+ stars.
Agent Skills
Skill from : How To Use The Hedge Fund Method To Win Every Single Trade.
An iterative deep-logic security audit agent for Claude Code. Nemesis combines two complementary audit methodologies in an alternating feedback loop to find bugs that neither can catch alone.
这个库的旨在为同学消除选择课程，学习资料等信息差。 在大学中存在大大小小的信息壁垒，然而要打破这些壁垒获取情报却要耗费大量时间精力。 有时上完一节课才意识到应该如何去上这门课，但为时已晚，学习结果可能不尽人意留下遗憾。 为了将那些不确定的，流状态的，短暂的，难以获取的，口口相传的信息保存下来，我们建立了这个库，希望能帮助到大家。 （摘自浙江大学课程攻略共享计划）
上周写了一篇文章，与 AI 一起做产品的六条原则，很多朋友都喜欢这套插图，问我怎么做，就把它做成 skill，开源发布。
This skill is maintained as a standalone submodule of Kernel Design Agents (KDA) for easy installation.
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.
Creates Claude Code skills with built-in best practices from Anthropic's official documentation.
A simple CLI for orchestrating Claude Code, Codex, and OpenCode.
把 deepseek-v4-flash 或 deepseek-v4-pro 注册为 Codex 原生自定义子 Agent，并验证实际派发路由。DeepSeek V4 Pro 的 8·13 更新继续使用 deepseek-v4-pro API 标识。
基于 OpenClaw 的论文自动检索、总结、评估智能体框架。 可为任意研究领域生成专门的论文专家智能体。
Declarative Agent Workflow Framework For individual developers and teams, build, debug, deploy, and continuously strengthen your own Claw capabilities
Kilroy is a local-first CLI for running StrongDM-style Attractor pipelines in a git repo.