Open-source GrokBot alternative built on DeepSeek Harness. Build your personal bot team: multiple personal agents with persistent memory, identities and permissions, extensible through DSH plugins.｜基于 DeepSeek Harness 的开源 GrokBot 平替：有长期记忆的个人 AI Bot 团队，支持多 Bot 协作、身份权限与插件生态扩展。MIT.

为 DeepSeek Harness 提供电脑控制插件：新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入（目前支持macos）｜Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.

Snowflake AI Kit: Cortex Code plugin for automatic Snowflake routing, envelope-based permission policy, and one-command installers for Snowflake CLI + Cortex Code CLI.

Permission-first rules, agents, skills and workflows for AI coding agents. One source → native CLAUDE.md, AGENTS.md and GEMINI.md for Claude Code, OpenAI Codex and Google Antigravity. Claude Code plugin + one-line install.

The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.

Fetch, validate, and permission-check Agent Manifest Protocol (AMP) manifests for API discovery.

Lets AI assistants read cookieless website analytics and manage goals, alerts, and uptime checks through a hosted MCP endpoint with permission-scoped access tokens.

Enables MCP hosts to spawn, supervise, and collect results from parallel panels of pinned-model OpenCode v2 agents for delegated tasks, reviews, and cross-model comparisons. Supports per-member roles, models, permissions, follow-up prompts, cancellation, and persisted result retrieval.

Enables Claude and Cursor to search a team's synced Slack, GitHub and Notion content through permission-aware hybrid search with citations, retrieve a source document with its review and comment thread, and query time-aware knowledge graph facts when the graph is enabled. Every tool call runs with the signed-in user's permissions, so the assistant sees exactly what that user can see.

Enables AI agents to read messages from user-approved WhatsApp chats via a blocking long-poll tool and send signed replies to chats where the user has explicitly allowed responses. Permissions, watch/reply switches, and a live feed of everything the agent sees and sends are managed through a local web UI.

Enables AI clients to securely access and manage IMAP mailboxes through OAuth-protected tools for searching, reading, organizing, flagging, moving, and deleting emails or folders, with optional write permissions.

Enables MCP clients like Claude Code, Codex, Cursor, and Claude Desktop to search, read, and download attachments from NetEase mailboxes (163/126/yeah.net/188), wait for verification codes, and create drafts or send and move messages only after a two-stage preview and confirmation, with readonly, draft, and full permission modes.

Enables users to search songs, play liked music or playlists, control playback and volume, and query playback status and timestamped lyrics using their own account and membership permissions.

Connects AI assistants to a Telegram bot so the model can message the user, send files, ask questions and wait for button answers, and read or search chats, groups and forum topics. It also lets the assistant reply as the user in connected personal chats, within the permissions granted in Telegram.

The most powerful MCP Slack Server with no permission requirements, Apps support, GovSlack, DMs, Group DMs and smart history fetch logic.

Enables Claude to search and read an organization's internal documents (Word, PDF, HTML, Markdown) through hybrid BM25 + vector retrieval, returning answers with exact citations while enforcing server-fixed role permissions, hiding confidential and superseded content, and logging the token cost of every request.

Enables agents to retrieve permission-filtered document knowledge across organizations and knowledge bases, and to identify and expand business terms and typed object relationships through a unified MCP interface.

Exposes explicitly approved local Windows stdio and loopback HTTP MCP backends through a single OAuth-protected remote HTTPS MCP endpoint, letting a mobile AI client invoke whitelisted tools with namespacing, PKCE-based authorization, and per-tool permissions.

Gives AI agents read-only access to curated, deduplicated, and well-described data products, complete with source metadata, freshness tracking, and per-agent permissions that preserve the source's access rights. The server can also answer "I don't know" rather than guessing when the approved data doesn't cover a question.

Enables an MCP-compatible assistant to log in with UNC single sign-on and explore the FCEFyN virtual classroom, listing enrolled courses, retrieving course indexes and materials, and reading or searching pages, activities, and PDFs. It works read-only with the user's own credentials, without tokens, admin permissions, or downloading entire courses.

Turns a Frappe site into a remote MCP server that AI clients such as Claude can sign in to with OAuth and use curated, task-level tools registered by installed apps. Every call runs as the signed-in user with that user's permissions, with schema-checked arguments and rollback on failure.

Enables external AI tools to query authorized WeChat messages and available media through read-only or full-permission keys, with restricted conversation scopes.

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling _notice JSON.

Solk CRM for Claude: accounts, pipeline, visits, quotes, orders and tickets with your permissions.