Signed, publicly logged records of what your AI agent did, with proofs anyone can check offline.

Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.

Checks email deliverability: audits a domain's SPF (including the 10-lookup limit), DKIM, DMARC and MX records with ranked fixes, checks a sending IP's reverse DNS and blocklist listings, and tests email headers against Gmail and Yahoo bulk sender requirements.

Augment your work with Liminal. Stop repeating yourself and build on what’s already solved.

Gmail, Outlook, Hotmail, iCloud and Fastmail at once: search, read, draft, send and organise mail.

Search, inspect and compare infrastructure tools for AI agents from a checked directory.

Email for AI agents: its own address, not your Gmail. Invite-only; requires an agent token.

DeFi vault judgment for agents: 16-factor Atlas Score, route survival, blowup alerts. Read-only.

Indian legal research, judgments and Acts, drafting, translation, matters and due diligence.

Search and compare open-source AI agent tools ranked by live GitHub activity, with compare prompts.

MC 资产面板 + 「MC 模组工作室」模式 + mc-mod / mc-art 两个 skill：3D+物品栏、像素/结构编辑器、出错的报告自动放进输入框、GameTest 判定闭环。原生 Windows 可用（不需要 WSL），不绑定任何具体 mod。

Template for deepseek-harness plugin development.

Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis

Retrace · 回溯 — Recall, edit-and-resend, regenerate, and conversation/artifact versioning (timeline, rollback, fork map) for DeepSeek Harness — Web and Desktop

Your mailboxes in ChatGPT and Claude: Gmail, iCloud, Fastmail, any IMAP. Passwords stay yours.

A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.

Salesforce & HubSpot: dedupe, normalize, enrich, assign, job change, create, mass update, segment

Search and update Records and Lists, import and export CSVs, and run enrichment in Connie.

Utilities for Android emulators, iOS simulators and real devices: launch, stream, control, record and automate them from a desktop app, TUI and CLI

Session-level (not fragment) local memory for AI coding agents: passively captures Claude Code, Codex, ZCode and Qoder conversations into one SQLite store, with provenance-cited retrieval and a human-only right to be forgotten.

A single MCP gateway that lets every agent and login on your machines reach services like Notion, Sentry, Cloudflare, Gmail and Google Calendar after signing in once, with per-agent tokens. Calls that reach other people or can't be undone wait for approval first, and every call is logged.

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

微信.skill - 让 AI 读懂你的微信

Enables users to search and read recruiter Gmail, classify and label threads into categories, archive confidently categorized mail, and create reply drafts for manual sending, while never sending mail or auto-archiving uncertain messages.