Anthropic agents

微信 ClawBot 直连 Claude Code | 支持文字/语音/图片 | 持久记忆 · 定时任务 · 多Agent | 无需 OpenClaw | ~2000行Python

Lifecycle-shaped Claude Code agent kit: scheduled audits → ready-state issues → developer-agent PRs → multi-persona advisory review. Six named PR reviewers, five audit scanners, one installer. Claude-only by design.

Mana Hub — self-hosted operations dashboard for your own AI agents. Next.js 16 + Supabase + Claude Code. Risk approvals, cron requests, web-push, knowledge base, file-drop bridge for tmux-hosted agents. Built for the 'Masterclass: Dein AI Agent Team' course.

MOVED: now the crucible plugin in github.com/mshadmanrahman/pm-pilot. Install: claude plugin install crucible@pm-pilot

Complete Claude Code cheat sheet - commands, keyboard shortcuts, CLI flags, CLAUDE.md, MCP servers, hooks, custom agents, automation scripts, and workflow tips.

MCP, but without the MCP. Uninstall your MCPs and let Claude call the APIs directly.

A finish-first agent loop for Claude Opus 4.7 — plans, executes, verifies, and ships.

Deploy autonomous AI agents as your digital twins across 10 social platforms

Reusable agents, commands, and permission templates for Claude Code

Cortex — an operating system for Claude Code. Persistent memory, specialized agents, smart skills, enforcement hooks.

Run parallel Claude Code agents in tmux with automatic permission approval. Auto-approves Bash, WebFetch, and other tool prompts so agents run unattended. One-liner install for macOS, Linux, WSL and Termux.

Decision-quality pre-commitment analysis. Hosted at azimuth-testbed.netlify.app — no install required. Claude Code skill for permanent workflow integration.

Track AI-generated code at line-level granularity. Know which lines were written by AI, modified by humans, and what prompts generated them. Git-native storage, automatic redaction, and Claude Code integration.

Beautiful, themed HTML data displays and research briefings for you and your coding agents.

Claude skill for FS25 mod development — answers verified against the game's own decompiled engine source (1,842 files). 1,413 classes, 119 MessageTypes, the mod sandbox, 30+ patterns, 20+ pitfalls. Works without a local decompile.

Configuration governance for Claude Code. Bootstrap, audit, sync, and evolve .claude/ across projects.

Benchmark harness for A/B testing Claude Code plugins against OOLONG long-context reasoning tasks. Compare truncation vs RLM-RS recursive chunking strategies. Features Claude Code hooks integration, SQLite persistence, and comprehensive scoring aligned with the OOLONG paper methodology.

A local MCP server that gives Claude Code persistent context and code intelligence. Sessions, code search, goal tracking, and background analysis — all in two SQLite files.

AI persona avatars + virtual meetings for Claude Code (tmux split-panes + Ralph loop + auto Word/PowerPoint output)

MCP server for RedNote (Xiaohongshu) — analyze content, comments, and trends with structured tools for LLM workflows.

MCP server for Claude Code CLI with full Google Workspace integration - Docs, Sheets, Drive, Gmail, Calendar & Apps Script (72 tools)

Open-source AI career assistant built with Rust, Tauri, React, and Ollama for resumes, interviews, ATS analysis, and productivity.

Agent-drivable Patchright browser daemon with a persistent Chrome profile AND a built-in human-behavior layer (realistic mouse paths, keystroke cadence, scroll physics). Gives AI coding agents a real browser they can steer with one-shot CLI calls.

Global CLAUDE.md: Behavior guidelines that stop your agent from overengineering, hallucinating, and breaking things

Agentic-DART — autonomous detection & response agent. Architecture-first, not prompt-first. Starts as agentic DFIR; designed to expand toward agentic SOC and beyond.

Run Claude Code from a USB drive - no installation required. Downloads the official binary, stores all config portably. Windows, macOS, Linux.

Find B2B prospects the moment they're in-market. Six Claude Code skills that detect buying signals, surface the accounts showing them, and write outreach that references something real.

AI agent for Claude Code that tailors resumes to job descriptions with ATS optimization and LaTeX PDF output. Zero fabrication - every claim sourced from your career document.

Svensk komplement-stack till Anthropics Claude for Small Business. 11 Claude Skills för Bokio, moms, AGI, K10 och svenskt regelverk.

Load AGENTS.md into Claude Code sessions — no CLAUDE.md needed

Local-first governance layer for Claude Code, built entirely on its native primitives — hooks, subagents, skills, MCP. Turns every session into a queryable, local SQLite record, then reads it back to predict your next dispatch, recall past incidents, attribute cost, and gate commits. The record is the product.

Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites.

A suite of plugins for freight forwarding workflows — air, sea, road, rail, and time-critical. Maintained by DCS Premium Freight SRL.

A Claude skill for rigorously solving math problems — equations, proofs, optimization, geometry, and more, with step-by-step reasoning and verification.

Dispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic nitpicks

台灣版 Claude for Legal：支援台灣民法自動更新、合約審查與法律實務 Playbook。基於 anthropics/claude-for-legal 擴充。

MCP server for German & EU law. Verified, citable legal context for any LLM. Daily updates from official sources, hosted in Germany

Academic research workflow for Claude Code: 20 skills covering causal inference (DiD, RDD, IV, synthetic control, field experiments, design triage, preregistration), paper reading, lit review, bib auditing, replication packages, LaTeX and TikZ, plus a Quarto reveal.js slide system with render-time quality gates.

Official Anthropic Agent Skills — frontend-design, claude-api, docx, pptx, xlsx, pdf, canvas-design, mcp-builder and more

I built a cortex for Claude Code. It runs three of my businesses.

29 free, open-source plugins for Claude Code & Cowork — Google Drive, WhatsApp, YouTube, WordPress, Apollo & more. Built on the SOSA™ security framework.

Claude Code autopilot with self-healing memory: one command → build → test → localhost. Trajectory tracking, learned routing, and stop-hook enforcement across runs.

John, an agent harness designed for building knowledge-dense applications.

Appoly Multiagent Chat — collaborate with multiple AI coding agents (Claude, Codex, etc.) in one shared chat interface. Electron app, uses your local CLIs. Install: npm i -g @appoly/multiagent-chat

Curated, hand-verified catalog of working Claude Code skills — marketing, SEO, dev, MCP — plus a built-in 19-sub-skill SEO/GEO agent. No dead links.

AGGREGATION — 1005 Claude Code subagents from 10 open-source projects. Full credit to original authors (see ATTRIBUTION.md).

Persona-driven LLM agent for group chats & DMs — QQ (OneBot v11) + Telegram/Discord/Slack via a bundled AstrBot gateway. JSON output protocol, character-whitelist validator, multi-layer sticker filter, eval-driven prompt iteration.

screenstudio-alt — an open-source headless Screen Studio alternative (Claude Code skill): auto-zoom, idle speed-up, vertical export.

Semantic, on-demand skill retrieval for Claude Code — replaces the per-turn skill-listing token tax with a vector retriever over full skill descriptions.

Self-hosted, secured HTTP API around headless Claude Code — per-app keys, all tools locked off, zero deps. Use Claude from your own apps.

Gemini CLI extension for Google Ads management — campaign analysis, auditing, optimization skills and commands. Ported from production at googleadsagent.ai

Watch your Claude Code subagents work — a live office for every conversation.

Local-first nutrition MCP for Claude/Cursor: USDA food search, barcode + photo, meal logging

Open-source agent-native AI SaaS starter kit, ship in days, not months

A peer-review protocol for AI models. Claude, Codex, Gemini and others review each other's code via CLI handoffs. Bidirectional, symmetric, opensource.

A Claude Code meta-skill that learns your writing voice from your own samples and edits, then compiles it into a reusable voice skill.

MCP server for Microsoft To Do via Microsoft Graph API. Manage task lists, create, update, complete and delete tasks from Claude Code, Claude Desktop, or any MCP-compatible client. Stdio transport, MSAL device code auth, persisted token cache.

Hushdrop — drop anything, share it with who you want, on your own domain. Open-source, self-hostable artifact sharing (CLI + MCP) with zero-knowledge AES-256, from any AI agent.

AILmanac — the always-current, community almanac for getting the most out of Claude and every AI. For all levels.

Your AI coding agent starts every session knowing your repos, your clients, and how you work — a plain git repo of markdown + YAML it reads at session start, independent of model or frontend. Context compounds instead of restarting. MIT.

Local-first MCP server for WHOOP recovery, HRV & sleep — Claude, Cursor, ChatGPT ready

CLI tool to manage AI provider configs for Claude Code (and more). Switch between API providers with one command, auto backup, atomic write.

Conta Azul MCP — conecte o ERP Conta Azul ao Claude, Cursor e agentes de IA. Vendas, clientes, produtos, contas a pagar/receber, parcelas e NF-e em linguagem natural. 35 ferramentas, OAuth 2.0, lê e escreve. Conta Azul ERP for AI agents (MCP, Brazil).

MCP server for controlling Microsoft Project via COM automation — 79 tools for task, resource, schedule, and baseline management

把 Anthropic 官网发布的技术博客内容，转化为中文音频解读，让你在碎片时间听懂最前沿的 AI 发展

MCP server exposing the full Apple Ads (Search Ads) Campaign Management API v5 — 74 typed tools

Verified workflow engine for Claude Code: durable project memory, phase planning, subagents, and deterministic completion gates.

AI-powered Fortune 500 business operating system for Claude Code — 15 executive agents, governed initiative lifecycle, Decision Authority Matrix, and 17 slash-command workflows.

A security-first bridge between Claude Code (MCP) and Chrome — HMAC pairing, domain allowlist, per-domain evaluate opt-in.

A principal-level, 16-division multi-agent Council for Claude Code. Drop-in ~/.claude/ config: 15 Floor + 160 Library rules, 121 skills, 32 agents, 33 commands, 14 hook-enforced quality gates. Runs on any machine, any project, every IDE. MIT.

The complete Google SEO MCP for Claude Code & Cursor — Search Console + Analytics 4 + 5 cross-platform tools (GSC↔GA4 journey, opportunity matrix, traffic health check, revenue attribution, full landing page diagnosis). Diagnostic intelligence with anti-hallucination provenance, leave-one-out Z-score, real funnels. Read-only by default.

Gstack for PMs -> PM Toolkit for AI Era.

Drop-in observability for the Anthropic Node SDK. Wrap your client once and every messages.create call lands in Voight — prompts, tokens, cache reads, cache creations, tool use, latency, errors.

Fifty runnable Python systems for finance & tax — month-end close, cash & debt reconciliation, partnership 1065/§704(c), tax workpaper build & carry-down, cross-border surplus & ACB, read-only validation, Triangulate multi-agent AI review, and a knowledge brain. Human-gated, fictional data, 495,064 tests, CI-backed, MIT.

Visualize Claude Code dynamic workflows from your terminal — a fan-out→barrier→reduce DAG, a gantt timeline, live concurrency, and a self-contained interactive HTML report. Zero runtime deps.

Teach an LLM to talk like a person — It teaches a language model how to talk like a person. Not how to sound like one — that part's easy, and it's what most failures already do

Local-first MCP server for Garmin Body Battery, HRV, sleep & training data — Claude/Cursor ready

The prettiest statusline for Claude Code — pure bash, never blocks your prompt. Usage quota, context window, git status & more.

oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.

Every local AI coding session in one tab: Claude Code, Codex and OpenCode in a single list, with a queue you can schedule and isolated Claude Desktop instances kept apart. Local, private, MCP-native.

A cache doctor for Claude Code: find the money your prompt cache is leaking.

A cache-optimized AI memory and context management framework for long-running LLM agents, featuring tiered context storage, token budgeting, memory compaction, sub-agent delegation, and structured web intelligence.

Highly opinionated AI software company you drop into any repo.

aprovodka — MCP server for 1C:Enterprise via REST/OData 3.0. 32 tools: catalogs, documents, registers, accounting, batch, change-tracking. No BSL extension required.

cubest

🔍 Visualize any Claude Code agent harness — CLAUDE.md, subagents, skills, commands, hooks & MCP servers — as an interactive flow graph. Import from GitHub, ZIP, or local folder. 100% client-side.

Self-hosted Python job-search pipeline for H-1B & visa holders. You run it on your own laptop — no server, no sign-up, no data ever leaves your machine. Screens out visa-sponsorship dead ends automatically, AI only where it's actually needed.

Stream Deck plugin showing Claude session/weekly usage

Deepdive skill for Claude Code — 11-phase research pipeline: plan-review gate, parallel sub-agent search with circuit breaker, claims-ledger triangulation, relevance-filtered evidence, multi-angle red team, citation verification (liveness + faithfulness), machine-checked phase completeness. 105 blocks, 29 channels, 460+ stat sources, 39 APIs.

CLI + Claude Code plugin that spends your Claude Code subscription 5-hour quota on real parallel work, stopping at a threshold. Metered against the real Anthropic usage endpoint.

Reliability control for the Anthropic Python SDK

Postgres MCP Server

Generate original AI music tracks via Claude Desktop — MCP server powered by ACE-Step 1.5, with vocal/instrumental stem splitting and reference-style matching. No music software or AI/ML knowledge needed.

System prompts, modular fragments, and agent skills for Claude Science research workbench.

Spec-driven development workflows for Claude Code — 14 commands, 6 agents, 3 hooks. Immutable specs, hard gates, phased pipelines for auditable AI-assisted coding.

Exacting Agent Skills for serious thinking, reading, research, and translation.

Full unofficial agentic Infomaniak MCP server — guided automation of web hosting, mail, kDrive, domains and DNS.

claude-acp-server: ACP bridge for Anthropic Claude Code (stdio/WebSocket, JSON-RPC, streaming) for Zed & VS Code.

Self-hosted personal agent.