|
Majordomo: The Control Plane for Your AI Stack
Visibility into every LLM request, attribution for every dollar, and routing across every provider. Hosted cloud or self-hosted in your own VPC.
|
81 % |
|
Instill AI — AI Preferences That Persist Across Every Session
Instill AI is a self-hosted MCP preference server that makes your AI rules persistent across Claude, Cursor, Copilot and any MCP-compatible tool. Free to start.
|
80 % |
|
openrouterr.io · One API for every AI model
One API key, 100+ AI models. Route requests to Claude, GPT, Gemini, Grok and more through a single OpenAI-compatible endpoint. Pay per token, no subscriptions.
|
80 % |
|
ReRouted — one local endpoint. no dead ends.
A local AI router for macOS and Linux. Keep one endpoint while ReRouted handles accounts, routes, quota limits, timeouts, and retryable provider failures.
|
79 % |
|
polyrouter — One endpoint for every model
Open-source, self-hosted LLM gateway. One URL, one key for every model — explicit-first routing, fallbacks, and hard spend limits. Your keys, your box.
|
79 % |
|
kymo — AI visibility analytics, measured not sampled
AI visibility scores are sampled guesses. Kymo logs what ChatGPT, Claude and Perplexity read on your site, the visitors they send, and the sales that follow.
|
78 % |
|
All-in-One B2B Outbound Platform – Replace Apollo, Automate Sales
Replace Apollo, Hunter & more: SignalFire automates B2B outbound—watches, writes, sends, and syncs replies for you. Start your free 7-day trial now—no card.
|
78 % |
|
tokentrace · drop-in LLM observability
Drop-in SDK that traces every LLM call across OpenAI, Anthropic, and Gemini. Token spend, latency, prompt versions
|
78 % |
|
Yoink · switch Claude Code accounts, fast
Switch between Claude Code accounts from your terminal, fast. Snapshot logins into named profiles, swap them in a keystroke, and run open models through the...
|
78 % |
|
AI Subscription Tracker for Vibe Coders | SubHorizon
Track Cursor, Claude Code, ChatGPT, Copilot, Windsurf, and your AI stack in one place. See renewals, catch overlap, and stop paying twice.
|
78 % |
|
TknScope — Token intelligence for LLM work
A transparent LLM proxy that turns provider usage into session timelines, heatmaps, and breakdowns—without recording content by default.
|
78 % |
|
ClawOps - Your Personal AI Assistant
A personal OpenClaw AI assistant that lives on your own server. Connects to Telegram. 300+ AI models, smart switching, ready in minutes.
|
78 % |
|
FlareUp — Cloudflare Burn Rate Monitor
Stop the meltdown before it starts. Real-time Cloudflare cost monitoring for Workers AI, KV, D1, R2 — tracked live, alerted fast, before the invoice arrives.
|
78 % |
|
OpenKlo — hosted AI assistant powered by OpenClaw
OpenKlo is a hosted AI assistant powered by OpenClaw. Handle email, messaging, and routine via Telegram. Connect Gmail, pick an AI mode, and get a dashboard...
|
78 % |
|
Launchpad
Unified control panel for GitHub, Vercel, Supabase, and Claude—repos, deploys, env vars, data, chat, agent tasks, and MCP configs in one dark UI.
|
78 % |
|
averagebuddy.dev — Production-ready AI tools for developers
Self-hosted AI tools built for developers and freelancers. Buy once, deploy in 5 minutes, own it forever. No SaaS. No recurring fees.
|
78 % |
|
The AI Shorts Operator Kit — from scattered scripts to shipped revenue
Everything a solo operator needs to turn AI Shorts into a real business. Playbook, Tracker, 60 scripts, Trend Radar MAS, Batch Producer code, OpenClaw integr...
|
78 % |
|
ModelWatch — Catch silent LLM drift before your customers do
Continuous behavioral drift monitoring for LLM-powered apps. Catches provider-side model updates that quietly break GPT-4 / Claude in production. Bring your...
|
78 % |
|
Fusebox — Every API key gets its own fuse.
Open-source kill switch for runaway AI API spend. Sub-100ms inline blocking. Set a cap, swap one line, never wake up to a $1,400 bill again.
|
78 % |
|
TokenAIRouter — One endpoint for every model
|
78 % |
Detected social media networks