GTM Agents: a Claude Code plugin marketplace for revenue teams
67 plugins, 92 agents, and 263 skills wired up as Claude Code slash commands for sales, marketing, and growth workflows — with a structured validation pipeline underneath.
Florian Narr
Thoughts on software, AI, and building things.
Latest posts
Zed HelixQL: Syntax Highlighting for HelixDB's Query Language
A Zed editor extension that brings proper tree-sitter-backed syntax highlighting to HelixQL, the graph+vector query language for HelixDB — built as one of ours at floscom.
files-sdk: One API Across Every Storage Backend
files-sdk wraps S3, GCS, Azure, Vercel Blob, Cloudflare R2, and 25 other storage providers behind a single adapter interface, with web-standard I/O and first-class AI agent tooling out of the box.
Zenbu.js: Electron Apps That Ship Their Own Source Code
Zenbu.js is a framework for building Electron apps that users can modify directly — no bundling, no compilation step, source lives in the user's home directory and gets hot-reloaded on change.
HelixDB: one database for graphs, vectors, and everything your RAG pipeline touches
HelixDB is an open-source graph-vector database written from scratch in Rust that lets you define typed schemas and compiled query endpoints — no separate vector store, graph DB, or application layer needed.
TablePro: A Native macOS Database Client Built on a Plugin Protocol
TablePro is a free, open-source macOS database client written in SwiftUI that connects to 18+ databases through a plugin architecture — no Electron, no JDBC, sub-1-second startup.
deepsec: agent-powered vulnerability scanner for large codebases
deepsec runs regex matchers to find candidate files, then unleashes Claude or Codex to investigate them — a two-stage pipeline that separates cheap pattern matching from expensive AI reasoning.
Sandcastle: Orchestrate AI Coding Agents in Isolated Sandboxes
Sandcastle is a TypeScript library that runs Claude Code (and other AI agents) inside Docker, Podman, or Vercel sandboxes, giving each agent its own git worktree and merging commits back cleanly.
codemap: a project brain for your AI agents
codemap gives LLMs instant architectural context about your codebase — hub files, dependency graphs, diff analysis — without burning your entire context window on file dumps.
Go Interview Practice: 30 Coding Challenges with a Self-Hosted Test Runner
A repo of 30 Go coding challenges that ships its own web UI and test execution engine — fork it, spin up localhost:8080, and get automated test feedback without touching any CI system.
ml-intern: Hugging Face's Autonomous ML Engineer
An open-source agent that reads papers, writes training code, and launches GPU jobs on HF infrastructure — all from a single CLI command.
squirrelscan: website audit CLI built for LLM workflows
A CLI that runs 230+ SEO, accessibility, performance, and security checks against any URL and emits LLM-optimized output designed to be piped directly into an AI coding agent.
wrkflw: Run GitHub Actions locally without pushing to find out
A Rust CLI that validates and executes GitHub Actions workflows on your machine, with a full expression evaluator, four runtime modes, and a TUI — so you stop discovering broken CI after the push.
skills-detector: Fingerprint Your Stack, Surface Agent Skills
A CLI from Vercel Labs that reads your project's package.json and config files, detects which frameworks and tools you're using, then fetches matching agent skills from skills.sh.
spawn-agent: Use Any Local Coding Agent as a Vercel AI SDK Provider
spawn-agent wraps locally-installed coding agents — Claude Code, Codex, Cursor, Copilot — as Vercel AI SDK providers over the Agent Client Protocol, so you can drive them programmatically with the same API you use for hosted LLMs.
Open Agents: Vercel's Reference Architecture for Cloud Coding Agents
Open Agents is an open-source template from Vercel Labs that wires together a durable workflow engine, isolated sandbox VMs, and a multi-model gateway into a full coding agent system you can fork and run on Vercel.
dfseo: A CLI That Makes DataForSEO Usable From a Terminal (and an Agent)
dfseo wraps the entire DataForSEO v3 API in a single Go binary with on-disk caching, TOON output, and JSONPath filtering — designed specifically so LLM agents get small, deterministic payloads instead of multi-thousand-token envelope soup.
wpklx: A WordPress CLI that builds itself from the REST API
wpklx discovers your WordPress site's REST API schema at runtime and generates CLI commands automatically — no hardcoded endpoints, no manual updates when plugins add new routes.
Agent Vault: a credential proxy that keeps secrets out of your AI agents
Agent Vault is an open-source HTTP credential proxy from Infisical that intercepts your agent's outbound API calls and injects secrets at the network layer — so the agent itself never sees them.
wterm: A Terminal Emulator for the Web Built on Zig and WASM
wterm is a web terminal emulator that renders to the DOM using a Zig-compiled WASM core for near-native VT parsing performance, with a React component, WebSocket transport, and dirty-row rendering baked in.
X Bookmarks — 2026 KW16: open-agents.dev and the taste problem
A reference platform for cloud coding agents, Peter Steinberger on AI slop without taste, a terminal for React apps, a solo-founder time audit, launch directories, and a Claude Managed Agent on Vercel.
gsc-cli: Google Search Console from the terminal
A fast Go CLI that wraps the Google Search Console API — JSON output, local disk cache, quota tracking, and a built-in agent skill for driving it from LLMs.
Magika: Google's AI-Powered File Type Detector
Magika replaces heuristic-based file type detection with a tiny deep learning model, achieving ~99% accuracy across 200+ content types in milliseconds on a single CPU — and it's already running at Google scale.
Toprank: SEO and Google Ads Skills for Claude Code
Toprank is a Claude Code plugin that wires Google Search Console and Google Ads into your agent — letting Claude read real traffic data, identify waste, and make account changes directly.
RTK: A Rust Proxy That Cuts LLM Token Usage by 80%
RTK is a single Rust binary that sits between AI coding agents and the shell, filtering and compressing command output before it hits the LLM context — turning 2,000-token git status calls into 200-token summaries without the agent noticing the rewrite.
remocn: a shadcn registry for Remotion video components
remocn ships 64+ copy-paste animation components for Remotion — text reveals, scene transitions, full compositions — all installable via npx shadcn add. No runtime dependency, no black box.
Clawchief Turns OpenClaw Into a Founder's Operating System
An opinionated starter kit that layers priority maps, auto-resolution policies, and cron-driven skills on top of OpenClaw to build a persistent AI chief of staff.
TimesFM: Google's 200M Parameter Decoder for Time Series Forecasting
Google Research's pretrained foundation model treats time series forecasting like language modeling — a decoder-only transformer with patched input tokenization, reversible instance normalization, and autoregressive decoding that handles up to 16k context length.
Pretext: Text Measurement Without the DOM
A pure-arithmetic text layout engine that side-steps DOM reflow entirely, handling CJK, bidi, emoji, and soft hyphens across every browser.
GSD Solves the One Problem Every Claude Code Power User Hits
A meta-prompting and context engineering system that prevents quality degradation as Claude Code fills its context window, using spec-driven phases, subagent orchestration, and a four-type gate taxonomy.
Chops: One Native Mac App to Manage Every AI Agent's Skills
A SwiftUI app that scans your filesystem for AI coding agent skills across Claude Code, Cursor, Codex, Windsurf, Amp, and more — then lets you browse, edit, and organize them in one place.
Emdash: Parallel Coding Agents with Git Worktree Isolation
A desktop app that runs multiple coding agents in parallel, each isolated in its own git worktree. The worktree pool pre-creates reserves so task creation is instant.
Marketing Skills Turns Your Coding Agent into a CRO Consultant
A collection of 35 markdown skill files that teach AI coding agents how to do conversion optimization, copywriting, SEO, and growth engineering. The architecture is simple — the execution is surprisingly deep.
Kanban Code: A Native Board for Parallel Claude Code Sessions
A SwiftUI app that turns Claude Code into a multi-agent workflow — cards flow from backlog to done while sessions, worktrees, tmux terminals, and PRs stay linked automatically.
OpenUI: A Custom Language That Makes LLMs Generate UI 67% Cheaper
OpenUI ships its own streaming-first language for model-generated UI — a hand-rolled lexer, parser, and reactive runtime that cuts token usage in half compared to JSON-based approaches.
gws: A Single CLI That Builds Itself From Google's Own API Specs
Google Workspace CLI reads Discovery Documents at runtime to generate its entire command surface dynamically. No static command list — when Google adds an API endpoint, gws picks it up automatically.
Paperclip Orchestrates AI Agent Companies From a Single Node.js Server
An open-source orchestration layer that turns a collection of AI coding agents into a managed company — with org charts, budgets, heartbeats, and governance. 48k stars and moving fast.
itshover: 265 Animated Icons Built on a Single Pattern
An open-source icon library where every icon is a React component with hover animations driven by motion/react — distributed through the shadcn CLI registry and built on one consistent forwardRef pattern.
just-bash: A Full Shell Environment That Never Touches Your Disk
Vercel's just-bash implements a complete bash environment in TypeScript with an in-memory filesystem, recursive descent parser, and AST-based interpreter — built for giving AI agents a safe place to run shell commands.
ChromaDB PHP SDK: Vector Search Without Leaving PHP
A PHP client for ChromaDB's v2 API that wraps the entire vector database surface — collections, items, multi-tenancy, and five embedding providers — into a clean Saloon-based SDK with optional Laravel integration.
Google's diff-match-patch: The Algorithm That Powered Google Docs
A polyglot diff, match, and patch library originally built for Google Docs in 2006. One file per language, zero dependencies, and a Bitap fuzzy matching implementation you won't find anywhere else.
jolt — A Terminal Battery Monitor That Reads Apple's IOKit Directly
A Rust TUI that goes past surface-level battery stats by tapping into macOS IOReport and SMC for real CPU/GPU power draw, then stores everything in SQLite for historical analysis.
Inbound: Programmable Email Infrastructure With Its Own AWS Stack
Inbound gives you programmable email addresses backed by SES, S3, and Lambda — and ships the CDK stack to prove it.
OpenBB: An Open Data Platform That Takes Financial APIs Seriously
OpenBB builds an open-source abstraction layer over dozens of financial data providers, letting you query equities, crypto, fixed income, and macro data through a single Python interface — then serves it all via FastAPI and MCP.
skills CLI: One Installer for Every AI Coding Agent
Vercel's skills CLI installs reusable instruction sets across 40+ AI coding agents — from Claude Code to Cursor to Codex — using symlinks, a custom frontmatter parser, and a provider registry that handles GitHub, GitLab, and arbitrary hosts.
Vercel Agent Skills: Curated Rules for AI Coding Agents
Vercel's open collection of packaged instructions that teach AI coding agents React performance, design audits, and deployment — 69 rules distilled from Vercel Engineering's own playbook.
agent-browser: A Rust CLI That Gives AI Agents a Real Browser
Vercel's agent-browser is a native Rust CLI that speaks Chrome DevTools Protocol directly, giving AI agents fast browser automation through shell commands — no Playwright, no Node.js runtime, just CDP over Unix sockets.
Ralph: A Bash Loop That Turns AI Coding Tools Into Autonomous Workers
Ralph is a 113-line bash script that runs AI coding agents in a loop, feeding them PRD stories one at a time until every item passes. Simple architecture, surprising effectiveness.
Bagofwords: Agentic Analytics That Learns Your Data
An open-source analytics platform that wraps an agentic loop around your warehouse, with a memory system, LLM judge, and instruction registry that actually improve over time.
AutoRedact: Client-Side PII Redaction That Never Phones Home
A browser-first image redaction tool that runs Tesseract.js locally to detect and black-box emails, IPs, credit cards, and API keys — no server round-trip required.