Grade Claude Code, Gemini CLI and Cursor configs for risky permissions; get public config stats.

Access gate for AI coding harnesses (DSH plugin + Claude Code hook): per-directory deny/read/full, roster groups, audit log, model-facing tools with owner-approved widening.

Claude Code plugin: use ChatGPT (Codex), Cursor, OpenCode Zen, and Antigravity models inside one Claude Code session. Switch with /model, delegate to named native workers, keep each provider's own login and permissions.

Connects AI agents to a user's mailbox with OAuth-scoped permissions, enabling email sending, inbox management, verification-email capture for tests, and migration from Resend.

Provides a local MCP bridge to an end-to-end encrypted personal vault, enabling connected agents to search and save memories, manage accounts and credentials, access personal information and private addresses, and honor granular user permissions.

Agent plugin for major harnesses — DeepSeek Harness (DSH), OpenCode, Pi and Codex: define custom AI agent roles with per-role prompts, models, skills, permissions, memory and multi-agent orchestration.

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.

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 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.

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.

Sovereign AI agents for business: answers from company data, each person's permissions, approvals.

Shared second brain for any AI with agent permissions