🔓kpopper is a checkable knowledge record for AI-assisted projects: decisions linked to their evidence, assumptions and falsifiers.
// pluginsilanbm/⟨Rust⟩★ 12◷ MIT[ claude ]
Projects tagged #ai-agents
// ai-agents (776)
🔓
🔓A local dashboard for running Claude: every isolated Desktop instance and its account, live-tailed Claude Code sessions, and a queue of claude runs dispatche…
// devtoolsLunarWerxs/⟨TypeScript⟩★ 43◷ MIT[ claude ]
🔓A procedural Agent Skill that teaches custom-provider models how to discover, use, verify, and recover from Claude Desktop/Cowork-style tools and workflows
// skillsAbolfazlshahi/⟨Python⟩★ 35◷ MIT[ claude ]
🔓Is your project as good as the best out there? sota-scan benchmarks your repo against real top projects and hands you a scorecard + to-do list. A Claude Code…
// devtoolsMerlijnW70/⟨JavaScript⟩★ 43◷ MIT[ claude ]
🔓Linux, macOS ve Windows için kaynaklı ikinci beyin. Claude Code, Codex ve Antigravity adaptörleri; yerel Markdown kasa, ayrı hafıza incelemesi, isteğe bağlı…
// ragfornhere/⟨Python⟩★ 20◷ MIT[ claude ]
🔓One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server, CLI & VS Code e…
// ragBetaBots-LLC/⟨Rust⟩★ 41◷ AGPL-3.0[ claude ]
🔓A Claude Code meta-skill that learns your writing voice from your own samples and edits, then compiles it into a reusable voice skill.
// pluginseranshir/⟨Python⟩★ 10◷ MIT[ claude ]
🔓Local-first observability dashboard to monitor, compare and analyze Codex, Claude Code and GitHub Copilot CLI sessions
// devtoolsDaniBelmonte/⟨JavaScript⟩★ 14◷ MIT[ claude ]
🔓Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
// mcp-servers00200200/⟨Python⟩★ 11◷ MIT[ claude ]
🔓clodfarm (say it out loud): a farm of Claude Code agents. Plant a mission, they split it into sub-agents, open the work, and pace themselves on each account'…
// devopsmatank001/⟨Python⟩★ 10◷ MIT[ claude ]
🔓A durable state machine for Claude Code. Work survives /clear; nothing is done until a verify command exits 0.
// automationuk0/⟨Python⟩★ 10◷ MIT[ claude ]
🔓Confine an AI agent (Claude Code, Codex, oh-my-pi, ...) to one directory with a BPF-LSM program, and watch it live over eBPF.
// securityyeet-src/⟨JavaScript⟩★ 41◷ GPL-2.0[ claude ]
🔓
🔓An agent skill enforcing the First-Time Principle: write every change in its final form — no patches, no what-comments, no leftovers, no local/deployed drift…
// skillsnewbanser/⟨JavaScript⟩★ 41◷ MIT[ claude ]
🔓领域无关的多 agent UI 自动化测试编排骨架，用 Claude Code 驱动「探索页面→设计用例→写测试→审查」流水线
// automation569270901/⟨Python⟩★ 40◷ MIT[ claude ]
🔓Remote hands for coding agents: an MCP server that runs OpenCode / Claude Code / Codex work on a remote host over SSH, keeps credentials and the local machin…
// mcp-serversCogFlux/⟨Rust⟩★ 11◷ MIT[ claude ]
🔓100+ reusable skills for Codex and Claude Code. Build Unity games with workflows for planning, coding, testing, UI polish, Blender assets, and AI 3D.
// pluginsfurkantokkan/⟨Python⟩★ 10◷ MIT[ claude ]
🔓Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).
// pluginschrisryugj/⟨Python⟩★ 40◷ NOASSERTION[ claude ]
🔓Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
// mcp-servers00200200/⟨Python⟩★ 10◷ MIT[ claude ]
🔓Reusable AI skills for Codex, Claude Code & Copilot CLI — Markdown-only, safety-first samples for diagnosing bugs, drafting changelogs, and pre-merge checks.
// automationkhadir-syed/⟨Markdown⟩★ 19◷ MIT[ claude ]
🔓Route every coding task to the best AI agent on your machine — Claude Code, Codex, Cursor, Gemini CLI, Aider, OpenCode. Installs as a Claude Code plugin, Gem…
// pluginsJimuelle07/⟨Python⟩★ 15◷ MIT[ claude ]
🔓Claude Skills For Sales Optimization
// skillsSimonTheSalesBooster/★ 40[ claude ]
🔓Персональная система управления здоровьем на Claude Code: 14 AI-врачей, консилиум с обязательным спором, холистический анализ, локальное хранение данных. Не…
// automationalxyrgin/⟨TypeScript⟩★ 38◷ NOASSERTION[ claude ]
🔓Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claud…
// devtoolssup3x/⟨JavaScript⟩★ 39◷ MIT[ claude ]
🔓Give your coding agent a persistent memory. source-of-truth keeps a living docs/ catalog of what exists, why, and what rules apply — so AI stops rebuilding,…
// automationngocquang/⟨HTML⟩★ 40◷ MIT[ claude ]
🔓Fable 指揮官工作流 — 最強模型只做規劃/審查，研究與執行派給你選的模型；maker/verifier 分離的執行迴圈。Commander workflow for Claude Code: plan & review on the top model, delegate research/executio…
// skillsDennisWei9898/★ 35◷ MIT[ claude ]
🔓AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microsecond latency using CEL, IFC, secret sca…
// automationmayankjain0141/⟨Go⟩★ 39◷ MIT[ claude ]
🔓Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.
// mcp-serversAgriciDaniel/⟨TypeScript⟩★ 39◷ MIT[ claude ]
🔓Unofficial open-source study kits for Anthropic certifications: a linked wiki, original practice-question banks, and Claude Code skills that teach, quiz, and…
// automationalexiocassanifm/⟨Python⟩★ 39◷ NOASSERTION[ claude ]
🔓Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clients.
// mcp-serversgeanatz/⟨TypeScript⟩★ 34◷ Apache-2.0[ claude ]