DeepSeek Harness 的 soul.md 风格人设 + 长期记忆插件：设置页输入人设卡名称和内容即可，文件由插件自动管理；可按工作区指定人设、聊天框可给会话单独切人设；AI 可自行演化人设与记忆（soul_read/soul_update/memory_*）。

Estimates a home's after-repair value from gated, scored nearby sold comps and returns the supporting evidence, excluded comps, confidence tier, and local market context so results can be explained and challenged. Also looks up verified property records and supports what-if overrides such as added square footage or a pool.

Enables AI assistants to access a user's Pusan National University Moodle-based LMS account, browsing courses, materials, notices, assignments, grades, calendars, and Q&A, downloading course files, and performing write actions like submitting assignments after a confirmation preview. It combines the official Moodle Web Service API with authenticated session scraping for the ubboard notice/Q&A boards.

Enables AI assistants to persist and recall local memory across sessions and projects through hybrid BM25/TF-IDF retrieval over a file-based vault. Facts are tracked with dual-clock timestamps and require no native dependencies.

The official C# SDK for Model Context Protocol servers and clients. Maintained in collaboration with Microsoft.

Your private memory across AI apps: recall your context and continue saved work, only when you ask.

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.

Deep Zendesk MCP server for your AI assistant: search, draft, update and translate Help Center articles and manage Support tickets end to end — comments, triage and image attachments.

Long-term memory for AI assistants: permanent, portable across clients, searchable and exportable.

AI mentoring fit and book: check the fit with Marian Kamenistak and book a session in 10 minutes.

💻 Give AI models complete control of your computer (probably a bad idea)

The official Java SDK for Model Context Protocol servers and clients. Maintained in collaboration with Spring AI

A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal Engine through the native C++ Automation Bridge plugin. Built with TypeScript and C++.

A rail of your Claude Code session's prompts: hover to read, click to jump (function hooks / Mods)

DSH 设置面板会话管理器：归档 / 恢复 / 彻底删除 / 移动到其他工作区，带工作区标签与会话日期；统一「会话管理」面板。Session manager for the DeepSeek Harness settings panel — archive / restore / permanently delete / move sessions across workspaces, with workspace tags & session dates in one unified panel.

Unified DSH checkpoints: session + workspace + config three-state snapshots with one-shot rollback — /checkpoint and /rewind commands, a checkpoint tool, automatic interval snapshots, a Settings page timeline with pairwise diffs, and seed-replay session r

Two main-stage panels for the DSH web GUI: a multi-column kanban board with real execution through DSH sessions, schedules, session rules and auto-cruise automation, plus a task-list workbench whose rows are themselves cards on one canvas, with a navigati

Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, session/daily/monthly budget caps with threshold alerts (desktop notification + webhook) and alert/block/degrade over-limit policies, built-in carbon footprin

Cross-session plaintext memory plugin for the DeepSeek Harness — deterministic BM25 recall, writes take effect immediately, signal-driven injection, no embeddings

Resolve Git merge conflicts by extracting only unresolved paths, conflict hunks, and compact diffs instead of loading whole files into context. Use when a merge, rebase, cherry-pick, or stash pop stops on conflicts, when `git status` shows unmerged paths, or when files contain conflict markers.

Search, extend, and act on your team's Naumu knowledge graph: notes, threads, and nodes.

Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.

Send this coding session's transcript to the Convex team for an AI post-mortem that improves the quickstart system. Run only when the user explicitly asks.

Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.