#anthropic-claude

Awesome Claude Code And Agent Tools

Keep Claude Code working across usage limits — loop runner with a web dashboard, Telegram progress notifications, and per-round model switching

One markdown file. Two hooks. Memory that survives Claude Code's context compaction. Zero deps.

Open-source AI SDR agent on Cloudflare Workers. Generates personalized cold outreach, classifies replies, adapts strategy. Built on mails-agent.

Early-detection internship pipeline: polls ~290 ATS endpoints + community repos every 15 min, fit-ranks via Claude, alerts first.

Technical case study of a production AI-powered lead qualification system built with WhatsApp, Claude, Whisper, Supabase, and Cloudflare Workers.

12-question wizard that recommends an optimal RAG architecture (Standard / Graph / Agentic) with an AI-evaluated pipeline.

AI Engineer portfolio hub — 9 standalone production-grade projects covering RAG, fine-tuning, agents, Document AI, Computer Use, Code AI, AI Safety, GraphRAG, and Voice AI. Each project in its own repo; this is the master spec + landing page.

全球顶尖大模型统一API网关 | 1:1充值 0.09x倍率 原生官方号池 | GPT Claude Gemini

全球顶尖大模型统一API网关 | 1:1充值 0.09x倍率 原生官方号池 | GPT Claude Gemini

AI agent that answers product analytics questions conversationally — queries metrics, compares segments, detects anomalies, and generates charts using Claude and MCP

OpenAI API wrapper for your AI subscription

My latest flagship project — a multi-tenant RAG customer-support SaaS. Upload your docs, embed one line of code, and let AI answer customer questions with citations. Built with Next.js 16, React 19, FastAPI, PostgreSQL + pgvector, Voyage embeddings, Clerk auth, and Anthropic Claude.

Experimental kernel-from-scratch project exploring how far Claude can go in systems programming.

A gated, moat-first elimination funnel for judging business quality — a Claude Skill. Nine gates in fixed order, HALT at the first failure, valuation deferred to gate 7, and no composite score, ever.

巴菲特/林奇范式 A股+港股价值投资分析工具：4 类行业 profile + 5 数据源 + LLM 定性分析

Multi-line, mode-switchable status line for Claude Code with prompt-cache TTL, hit rate, burn rate, skill/MCP usage