Anthropic agents

Self-hostable AI agent runtime — single Rust binary, Tailscale cluster, runs across Mac/Linux/Windows/Android/iOS without a cloud account. Apache 2.0.

A software factory where AI agents propose and deterministic code disposes. A Python ADW engine runs coding agents in bounded phases; a Next.js cockpit observes and controls them. Both halves meet at one SQLite trace - the single source of truth.

Multi-agent AI factory: one-line idea → researched, quality-scored project specification. LangGraph + FastAPI + Next.js, Claude web_search grounding, HITL gates.

🧙‍♂️ pivoshenko's AI workspace

Physical hardware controls for Claude Code on the Logitech MX Creative Keypad — live status, one-press prompts, git, and offline voice.

An end-to-end BD pipeline on Claude Managed Agents — lead sourcing, research, outreach drafting, and a deployable CRM. The system researches and drafts; a human always sends.

Relocate Claude Code projects without losing sessions, memory, or worktrees.

Native Windows tray monitor for Claude Code usage — shows your rate-limit %, projects when you'll run out, and turns the icon red before you hit the limit. Plus a local 24h usage breakdown.

Browse, search & replay every Claude Code session on your Mac. Local-first session viewer, timeline scrubber & cost tracker (ccusage alternative).

An Agent Skill that makes any AI explain like Richard Feynman: mechanism before name, one honest analogy with its limits, and a ladder from kitchen-table to specialist. Built from a ~88k-word primary-source corpus.

Spec-driven iOS/macOS app development for Claude Code — from idea to App Store via /apple:* commands, specialist agents, and optional App Store Connect automation.

Native macOS menu bar app showing Claude Code usage (session / weekly / Sonnet / credits) — no backend, notarized, brew install

Your own context engine

AI short-form video ad generator as a Claude Code skill: turn app/web/SaaS screen recordings into Reels, TikTok & Shorts using Higgsfield AI video (Veo, Sora, Kling, Seedance), music, and ffmpeg. Claude + Higgsfield MCP. 16:9 + 9:16, kinetic captions.

Local MCP server for Gmail, Google Calendar and Contacts — runs on your own OAuth credentials, keeps secrets in the OS credential manager

Per-prompt model routing and offline cost tracking for Claude Code — keep simple prompts cheap, delegate complex work to a stronger model.

Based on Anthropic's skill-creator — with bug fixes, working Cowork support, and official best practices baked in. Claude skill for creating, testing, and improving other Claude skills.

AI-powered subtitle translation for the arr stack. Translate existing foreign-language subtitle tracks (Russian fansubs, embedded Japanese, etc.) into any language via Claude/GPT/Ollama with reading-rate adaptation and ASS/SSA style preservation.

Vibe-code MicroPython apps for the EMF Camp Tildagon badge. Browser UI, Ollama or Anthropic, deploys over Web Serial.

Token governance for Claude Code: the top model directs, execution goes to the cheapest adequate means. Routing kernel, hook-enforced pre-budget, telemetry, statusline with plan quotas.

Recover Claude Code desktop app sessions that disappear after switching accounts. Local-only, zero dependencies.

Chat with claude.ai in Chinese, send in English, and read back in Chinese.

A virtual software company for Claude Code: 19 agents, 38 workflows, 16 quality gates. Takes an application project from idea to release.

Find your forgotten side projects and figure out what to ship next. Scans local + GitHub, diagnoses health with Claude, suggests next steps.

Claude Code skill: decide when to render output as HTML over Markdown — based on Thariq Shihipar's html-effectiveness examples. Bilingual (zh-CN / en).

Autonomous Claude Code agent — 14 specialized agents, 10-parallel execution, project-specific skill learning, mechanical checkpointing, wave-based planning with acceptance gates, caveman ultra (~75% token savings). One prompt → finished project.

Agent Knowledge Cycle (AKC) — a knowledge cycle for AI agents: agent behavior compounds, human judgment sharpens. Six phases keep behavior aligned with operator intent as human attention becomes the scarce resource. ADRs, JSON schemas, dependency-free Python reference.

Proactive screen awareness + Claude Vision assistance

Autonomous memory and learning system for AI coding agents. LLM-powered knowledge extraction, triple fusion retrieval (FTS5 + TF-IDF + entity graph), quality-gated storage, and self-curating consolidation. Your agent never makes the same mistake twice.

Multi-agent orchestration, automation pipelines & recursive self-improvement for Claude Code. Mode-switching, swarm agents, TDD loops, learned instincts. One-command install: npx claude-power-setup

Self-learning agent system for Claude Code. Humans steer at every layer. The agent learns at every layer.

🎯 14-Dimension AI Agent Intelligence Assessment | 14维度 AI Agent 智能度自动评估技能 | OpenClaw Skill | Aligned with CLEAR/T-Eval/Anthropic standards

🔧 AI Coding Agent Token Optimizer | Skills for Claude Code, Cursor, Windsurf, Codex | Save 40-80% tokens & costs | 省Token神器

✨ AI-powered Obsidian plugin — 20 tools, Magic Write, agentic loops, vault diagnostics. Claude actually touches your vault.

Nexus is a self-evolving market analysis AI. It started with 10 rules and one system prompt — and rewrites both every session.

GAN-inspired multi-agent system that autonomously builds full-stack web apps from a single prompt using Claude AI agents

Lunheng (论衡) — Multi-agent paper review framework aligned with NeurIPS/Nature/JACS rubrics. Claude-native, no extra API key.

Open-source multi-agent orchestration templates for Claude Code.

Professional Claude Code plugin for AI-powered spec-driven development with automated code review and multi-agent collaboration

Personal AI assistant with 50+ integrations. Email, calendar, tasks, messaging, and more — all working together.

Spin up a Claude-powered multi-agent team from one sentence

Clone-run-forget Claude Code agent toolkit — D&D-themed multi-agent workflows for planning, reviewing, investigating, and shipping code.

Multi-agent pipeline for Claude Code — 12 steps with cross-model council and blind verification

Curtis Bot — Claude Code + OpenClaw bridge for Linux and macOS. Use your existing Claude Code CLI subscription (Max/Pro) as a full AI agent you can text from Telegram. No extra API keys. Phone-to-code, cron monitoring, 50+ skills, multi-agent orchestration, LocalSend file transfers, Git from your pocket.

Drop-in thinking-partner personality layer for Claude Code, Cursor, ChatGPT, and 20+ AI agent runtimes. MIT. Plaintext. Persistent memory. Framework-grounded. Calibration-disciplined.

Battle-tested 7-phase methodology for shipping real software with AI coding agents (Claude Code, Cursor, Copilot) — from idea to production. The structured alternative to vibe coding.

Kodama for Claude Code — Reliable session memory & smart restart for the Claude CLI

A research-grounded course on writing high-quality Claude Code skills — 9 modules, 14 universal patterns, deployable assess-skill and write-skill, and a terminal reader. Based on analysis of 8 production repos and 6 peer-reviewed papers.

ClaudeRoam — Your Claude Code config, anywhere. Across Macs. Across accounts. Without the copy-paste.

🐳 Run Claude Code safely in isolated Docker containers with persistent projects and easy setup on macOS using Justfile automation.

Local dashboard to manage Claude Code — skills, agents, teams, commands, hooks, settings and CLAUDE.md in one place

Self-learning AI standards system - learns from corrections and auto-updates CLAUDE.md

FlipClaw — Flip the tables. Claude Code CLI is your primary interface. OpenClaw wraps around it with persistent memory, auto-skills, Dreaming, and 24/7 automation.

CLI-based AI coding assistant using AWS Bedrock and Claude models. Features interactive mode, file context, git integration, web search, and image analysis.

Browser companion plugin for AI coding assistants — Chrome automation MCP, in-page hint messaging, and persistent project memory across Claude Code sessions.

Claude Code plugin that hard-blocks dependency additions, bumps, and downgrades until a fresh, source-cited version check is recorded. Supports npm, pip, Poetry/uv, Cargo, and NuGet.

Self-hosted Mac assistant powered by Claude Code. Telegram, Discord, Slack, iMessage, Web — same butler, anywhere.

One-click Windows setup + zero-to-expert guide for Claude Code. Includes installer, CLAUDE.md templates, example agents, slash commands, and config files. No experience required.

Seamless, infinite context for your LLMs. Handles long conversations and long messages.

Complete step-by-step AI workflows for study, research, writing, business, and more — built for non-technical users. No coding required.

Claude Code plugin marketplace by DeBytes — AI-powered tools for productivity

Real-time surveillance dashboard for Claude Code Agent Teams — monitor agents, tasks, and messages live

Prompts extracted from Anthropic’s Claude Code CLI — organized and translated for research.

Give Claude Code a memory that persists across sessions and survives context compaction. Zero dependencies, pure Python, 30-second install.

Claude Code security snippets for safer permissions, sandboxing, and shell guardrails.

Own Your Stack — open-source agent security (redstamp · truecopy · strongroom) and AI infrastructure you own instead of rent by the token.

A Claude Code plugin that turns any project's docs into a persistent, compounding, LLM-maintained knowledge base — with hook-enforced discipline at tool-call time. Inspired by Andrej Karpathy's llm-wiki.md gist.

Claude Code plugin marketplace with plugins for improving English, Spanish, or any of your other languages

Talk to your Oura Ring data through Claude. Local SQLite mirror, 14 MCP tools, OAuth2, ~5-minute setup.

Prompt-injection defenses for Claude Code. A PreToolUse Bash hook blocks compositional credential-exfiltration shapes (secret read plus network, env dump to network, remote script to shell, reverse shells). A sanitizing MCP server wraps untrusted URLs and files in sentinels, strips invisible unicode, flags jailbreaks.

ADAM — self-improvement layer for Claude Code. Observes session friction (corrections, retry loops, dead-ends, error loops, edit churn) via lightweight hooks and proposes targeted skills, memory entries, and agent edits. Auto-applies low-blast changes with cross-session evidence; queues everything else for review.

This is a FastAPI service that provides a RESTful API for the Anthropic Claude AI model using anthropic-sdk-python.

Local AI Interface is an Electron desktop application designed to streamline your personal AI stack. It provides a unified, user-friendly hub for Dockerized services like Ollama (for LLMs) and n8n (for workflow automation), with built-in dark mode and easy one-command setup.

WhatsApp Business API from Claude Code — create templates, send messages, run ops in natural language. Direct Meta Cloud API, no BSP.

Public institutional archive for the BANNED BY ANTHROPIC campaign

Comprehensive ZSH tab completions for the Claude Code CLI — all commands, flags, and values

Free Claude Code skill that audits CLAUDE.md, AGENTS.md, subagents, settings.json, hooks, and Anthropic SDK call sites for Claude Opus 4.6 ⇄ 4.7 compatibility issues. 70 patterns. MIT.

AI-powered city council debate simulator for data center proposals. 5 AI agents debate a data center proposal in a simulated city council meeting, streaming in real-time.

A comprehensive Swift SDK for the Anthropic API

Linter & runtime auditor for Claude Code configs — 40+ lint rules, write-blindness, agent-bypass, orphan agents, ghost MCP servers, token economics, session recovery. Fully offline.

Paste clipboard images directly into Claude Code

A comprehensive AI toolkit for Claude Code featuring multi-language agents, reusable skills, and MCP services to supercharge your development workflow

Generate a Customized Poem for Valentine's Day using Anthropic, Twilio SendGrid, Replicate, and Exa!

Official SDK for Rulecatch — AI coding analytics, monitoring, and rule enforcement for Claude Code, Cursor, and AI coding assistants

MCP server for AI-powered 3D model & environment generation via Meshy AI — text to 3D, image to 3D, textures, GLB/FBX/USDZ — plug into Claude Desktop in 60 seconds

Multi-agent AI system for YouTube content production. 6 specialized Claude Code agents automate the entire video pipeline from market research to publishing.

Stop waiting for Opus on every grep — routes 80% of tasks to faster models. Zero dependencies.

🥋 Teach yourself coding in real-time using your own projects with this free, open-source Claude Code plugin for active learning.

VS Code extension that shows your Claude Code rate limit usage in the status bar. Tracks 5-hour session and weekly limits with live progress bars, color alerts, and reset countdowns via passive diagnostics_channel interception — zero extra API calls.

nushell + anthropic + tool use + rich documents + cross.stream

Aggregating MCP proxy with ~95% context reduction through progressive tool disclosure

Open-source Claude prompt library for GEO and AEO. 19 prompts for AI search visibility — no setup, no API key.

Rich statusline for Claude Code — 30+ items (context / tokens / cost / rate limits / git), color ramps, bar styles, and a live TUI editor. Runs fully offline.

🔓 Four opinionated skills for Claude Code: rootfix (root-cause debug), rootclean (refactor only), rootbuild (feature add), rootimagine (pre-deploy simulation). Stop patching symptoms. Stop ignoring patterns. Stop merging without tests. Stop deploying without simulating.

30-second physical micro-break suggestion for Claude Code — rule file, snippet, or hook.

🧠 Modern Neovim setup with AI superpowers: Claude Chat Agent integration, Local Fill-in-the-middle LLM Qwen-Coder Autocompletion w/ code Semantic Search, and Perplexity.AI Web Reseach via NerdPrompt. Features sleek Dracula theme, & productivity shortcuts.

Your local Claude Code terminal, accessible from your phone. Approve permissions, send commands, watch it work — all over Tailscale. No cloud, no relay, nothing leaves your machine.

Tempo - macOS menu bar app that tracks Claude Code token and credit usage. Polls the Anthropic API via OAuth and syncs data to iCloud, which an iOS companion reads and forwards to Apple Watch via WatchConnectivity. Delivers haptic alerts on Apple Watch when a session ends. Built with SwiftUI across macOS, iOS, and watchOS targets.

Hook-driven test framework for Claude Code plugins - automates integration testing with YAML/JSON test definitions, variable capture, and rich reporting

Forge battle-tested CLAUDE.md files that actually get followed. Audit, score, and generate CLAUDE.md with anti-slop rules, plan enforcement, and verification gates.