claudeers.

Projects tagged #llm

// llm (291)

🔓

A Claude Code skill that keeps your AI grounded across long sessions: named responses + a living TASK.md for clean context handoff between instances. Works w…

// devtoolsobrenoalvim/⟨JavaScript⟩★ 36[ claude ]
🔓

小白也能上手的 Claude Code / Codex 上游配置切换桌面应用 | A cross-platform, site-driven desktop app for switching Claude Code & Codex providers. Only official website: xiaoba…

// devtoolsLicoy/⟨TypeScript⟩★ 19[ claude ]
🔓

Give your agent eyes: any video link in, one typed JSON out. A Claude skill + API.

// skillstomascupr/⟨Python⟩★ 34◷ MIT[ claude ]
🔓

+62 Mode & Anti-Yapping Layer for Coding Agents. Langsung to-the-point ke baris bug, zero basa-basi korporat, dan anti-reasoning dump. (Claude Code, Antigrav…

// devtoolshumanoiseLABS/⟨TypeScript⟩★ 10◷ MIT[ claude ]
🔓

Claude Code usage in the macOS menu bar and as a desktop widget

// devtoolssaeedkolivand/⟨Swift⟩★ 15[ claude ]
🔓

Agent skill: the design of one change as one interactive page — zoomable map, your decisions as controls, lock it. For Claude Code, Codex & co.

// skillsAlmogBaku/⟨JavaScript⟩★ 15◷ Apache-2.0[ claude ]
🔓

A verifiable, time-aware knowledge ledger your LLM keeps for you. An evolution of the LLM Wiki pattern, built on Claude Code.

// ragverbio-labs/⟨Shell⟩★ 27◷ MIT[ claude ]
🔓

See how many times over each AI plan has paid for itself — Claude Code, Codex and the rest, priced against the published API rates, at the edge of your Mac's…

// devtoolsReffWu/⟨Swift⟩★ 29◷ MIT[ claude ]
🔓

Claude skill + plugin that picks the right model and effort for every task: Opus plans, Haiku/Sonnet build, every step is verified, and it escalates only on…

// skillsceliktech24-cell/★ 31◷ MIT[ claude ]
🔓

A deliberately lite personal brain: Obsidian to browse, Claude Code for everything else. No vector DB, no embeddings, no MCP servers, no Obsidian plugins — m…

// ragsturlese/⟨Python⟩★ 29◷ MIT[ claude ]
🔓

Execution posture harness for Claude Code. Your coding agent stops one step early; Castra is the step.

// automationbeyondworks/⟨Python⟩★ 32◷ MIT[ claude ]
🔓

Claude Code'u EVREN'in model filosuna bağla: tek komut kurulum, geri alma, Linux/WSL/Windows

// dataMustafaKemal0146/⟨Shell⟩★ 16◷ MIT[ claude ]
🔓

A Claude skill that removes AI writing patterns from Turkish text while keeping meaning, numbers and terminology intact. Also works with ChatGPT, Gemini and…

// skillsDevVettel/⟨Python⟩★ 11◷ MIT[ claude ]
🔓

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line Python API for Cl…

// automationAimaghsoodi/⟨Python⟩★ 22◷ NOASSERTION[ claude ]
🔓

Claude Skill for Generative Engine Optimization and agent readiness. Get cited by ChatGPT, Perplexity, and Google AI Overviews. Expose MCP, llms.txt, and OAu…

// skillsfseixas/★ 26[ claude ]
🔓

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the dig…

// pluginsAndyShaman/★ 27◷ MIT[ claude ]
🔓

Turn an agent's work: progress, reviews, research, comparisons into a single self-contained, reviewable HTML page (a work canvas). An Agent skill.

// skillsJingbiaoMei/⟨CSS⟩★ 20◷ Apache-2.0[ claude ]
🔓

Developer-grade Claude Code + Codex configuration: cost-tiered subagents, workflow commands, guardrail hooks, MCP parity, and an installable plugin/marketplace.

// mcp-serversdshakes/⟨Shell⟩★ 23◷ MIT[ claude ]
🔓

Tell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops with independent ver…

// devtoolsmorphaxl/⟨JavaScript⟩★ 17◷ MIT[ claude ]
🔓

One AI engineering team for Claude Code. Install once — every project gets a full-stack specialist team that auto-specializes to its stack.

// pluginsberkcangumusisik/⟨TypeScript⟩★ 16◷ MIT[ claude ]
🔓

LLM-maintained personal knowledge vault. Grow a tree of linked Markdown pages with Claude Code or Codex.

// productivitydaehyeonxyz/⟨Python⟩★ 25◷ MIT[ claude ]
🔓

Plugin de skills e agentes para Claude Code — workflows de engenharia reais, do PRD ao PR

// devtoolsrodolfochicone/⟨Python⟩★ 20◷ MIT[ claude ]
🔓

MCP server for deep semantic analysis of Scala via SemanticDB — exact find-usages, class hierarchies, implicit resolution & call paths for AI coding agents l…

// mcp-serversMercurieVV/⟨Scala⟩★ 22◷ MIT[ claude ]
🔓

Your daily AI intelligence dispatch to Email 📧· Robotics, Agents & LLMs analyzed by Claude Opus · 每日多源聚合 + 深度分析,GitHub Actions 一键部署,无需服务器

// automationYifannnnnnnnw/⟨Python⟩★ 23◷ MIT[ claude ]
🔓

Doubt, until what remains is certain. An MCP server that recursively doubts every plan decision — grounding each in real evidence or asking you — until it co…

// mcp-serverspranjalbhatia710/⟨Python⟩★ 21◷ MIT[ claude ]
🔓

Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.

// ragozankasikci/⟨Python⟩★ 15◷ MIT[ claude ]
🔓

AI in Raycast without Raycast Pro: ask, chat, translate and rewrite text through the Claude Code or Codex CLI, using your own Claude or ChatGPT plan.

// productivityumitaltintas/⟨TypeScript⟩★ 23◷ MIT[ claude ]
🔓

Local-first engineering memory for Codex and Claude Code — auditable Markdown, no vector database.

// ragminiLV/⟨JavaScript⟩★ 12◷ Apache-2.0[ claude ]
🔓

A macOS input method with AI commands in every text field: @improve polishes, @translate translates, @question answers, @claude hands off to Claude Code. Als…

// otherMicroZ-LLC/⟨Swift⟩★ 16◷ NOASSERTION[ claude ]
🔓

Behavioral guidelines for LLM tools (AGENTS.md). Installer wires Claude Code, Codex, OpenCode, and Kimi Code; Cursor/Cowork via paste. Principles 1–4 Karpath…

// automationhburaktasyurek/⟨Shell⟩★ 11◷ MIT[ claude ]