anthropic
Tracked open-source repos tagged anthropic, sorted by stars.
- #211
Claude skills for LinkedIn. 11 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and build a publishing cadence, all from your terminal. Content engineering by Creative Content Crafts. MIT.
★ 838+203Star change over the last 7 days - #212
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.
★ 835+13Star change over the last 7 days - #213
Stack-agnostic Claude Skills covering the full website lifecycle: brand, design, content, SEO, dev, ops, growth, and research. Build, ship, audit, optimize.
★ 832+22Star change over the last 7 days - #214★ 828+11Star change over the last 7 days
- #215
open-source skill that learns any brand and turns it into a complete design system. works on claude code and codex. install once, every UI your assistant builds matches your brand.
★ 828+11Star change over the last 7 days - #216
🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.
★ 827+0Star change over the last 7 days - #217
A minimalistic MCP client with a good feature set.
★ 826-1Star change over the last 7 days - #218
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
★ 825+3Star change over the last 7 days - #219
ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloads, seamless closed LLM integration, and offline-first RAG knowledge bases, ARGO becomes a DeepResearch powerhouse for autonomous thinking, task planning, and 100% of your data stays locally. Support Win/Mac/Docker.
★ 825+3Star change over the last 7 days - #220
Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.
★ 813+0Star change over the last 7 days - #221★ 812+0Star change over the last 7 days
- #222
Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.
★ 810+4Star change over the last 7 days - #223
Evidence-constrained commercialization assessment: deterministic retrieval, a six-stage LLM workflow, auditable scores and checkpoint recovery. Qwen / DeepSeek / OpenAI / Claude.
★ 807+45Star change over the last 7 days - #224
parrot.nvim 🦜 - the plugin that brings stochastic parrots to Neovim.
★ 790-1Star change over the last 7 days - #225
A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.
★ 787+1Star change over the last 7 days - #226
CLI, SDK, and IDE plugins for Duel Agents
★ 772+0Star change over the last 7 days - #227
A web-based Kanban board for viewing Claude Code tasks
★ 762+3Star change over the last 7 days - #228
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.
★ 750+5Star change over the last 7 days - #229
AI gets the context. Not your private data. Local-first privacy proxy for browser chat, AI APIs, and coding agents.
★ 743+3Star change over the last 7 days - #230
JARVIS — a voice assistant for Claude Code. Talk to your Mac and he brainstorms a project with you, builds it, and tells you out loud when a Claude Code session needs you. macOS, on your Claude subscription, no API key.
★ 735+27Star change over the last 7 days - #231★ 731+44Star change over the last 7 days
- #232
Cross-session context for Claude Code. CLI + MCP server + /story skill that tracks tickets, issues, handovers, and roadmap in a .story/ directory.
★ 730+31Star change over the last 7 days - #233★ 722-1Star change over the last 7 days
- #234
The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.
★ 720+7Star change over the last 7 days - #235
Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation, App Store optimization, and more
★ 712+19Star change over the last 7 days - #236
Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disciplined factory: durable specs, fresh-context workers, adversarial cross-model reviews, receipts. Everything in your repo, zero dependencies. Claude Code · Codex · Cursor · Droid.
★ 694+2Star change over the last 7 days - #237
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.
★ 693+11Star change over the last 7 days - #238
Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.
★ 692+1Star change over the last 7 days - #239
Desktop app to control your computer with AI using your terminal, browser, mouse & keyboard
★ 686+3Star change over the last 7 days - #240
Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.
★ 683-1Star change over the last 7 days