Compare/AI Subroutines vs WUPHF by Nex.ai

AI tool comparison

AI Subroutines vs WUPHF by Nex.ai

Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.

A

Automation

AI Subroutines

Record a browser task once, replay it 500x at zero token cost

Ship

75%

Panel ship

Community

Free

Entry

AI Subroutines from rtrvr.ai are a new automation primitive: you record a browser task once (a form submission, a LinkedIn connection, a CRM update), and that recording becomes a deterministic, callable tool that AI agents can invoke with different parameters — without spending tokens on every run. Unlike Playwright, Browser-Use, or other out-of-process solutions, Subroutines execute entirely inside your browser tab, inheriting your live session cookies, CSRF tokens, and signed headers automatically. The technical approach is clever. During recording, the system captures network requests and DOM interactions, then ranks captured requests to identify the actual API call (filtering out analytics and telemetry). Replay-hostile identifiers are stripped while stable endpoints are preserved. The result is a script that runs in your browser context — no session rebuilding, no key extraction, no proxy rotation needed. The AI handles parameter selection; the script handles execution. The business case is clear for outreach and operations teams: bulk LinkedIn campaigns, CRM mass-updates, scraping pipelines, and form submissions that would cost hundreds of tokens per run instead execute as cheap deterministic scripts. The model positions Subroutines as the "function call" layer beneath AI agents — the actions that don't need intelligence every time they fire.

W

Agent Frameworks

WUPHF by Nex.ai

A collaborative office of AI agents that build and share their own knowledge base

Ship

75%

Panel ship

Community

Free

Entry

WUPHF is a free, locally-run platform for managing multiple AI agents as a collaborative team, each maintaining a shared knowledge base so context is never lost between sessions. Agents support Claude Code, Codex, OpenClaw, and local LLMs via OpenCode, and the system is accessible through a terminal UI, a localhost web interface, or Telegram. Built by Francisco Dias, Oleksandr Pliuto, and Najmuzzaman Mohammad, WUPHF runs entirely on your machine with your own API keys. The key insight is that most multi-agent frameworks treat memory as an afterthought. WUPHF puts it front and center — agents don't just execute tasks, they actively build and maintain a structured knowledge base that other agents can query. This means a coding agent can hand off to a testing agent with full context intact, without the user having to re-explain the project state. As a fully free, locally-hosted solution, WUPHF sits in the sweet spot for developers who want multi-agent capability without the $50-200/month price tag of cloud-based agentic platforms. The Telegram interface is a clever touch for async work — you can kick off an agent team from your phone and check in on progress without opening a laptop. The project is early but addresses a real pain point in multi-agent orchestration.

Decision
AI Subroutines
WUPHF by Nex.ai
Panel verdict
Ship · 3 ship / 1 skip
Ship · 3 ship / 1 skip
Community
No community votes yet
No community votes yet
Pricing
Free tier available (paid plans TBD)
Free / Open Source
Best for
Record a browser task once, replay it 500x at zero token cost
A collaborative office of AI agents that build and share their own knowledge base
Category
Automation
Agent Frameworks

Reviewer scorecard

Builder
80/100 · ship

The 'record once, replay many' pattern solves a real cost problem in agent pipelines. The in-browser execution model is clever — you get auth context for free instead of fighting with session management. This is the kind of tool that drops into existing workflows without requiring a rewrite.

80/100 · ship

Free, local, multi-model, Telegram-accessible — WUPHF checks every box for an indie dev's agent setup. The shared knowledge base is the differentiator that makes handoffs between agents actually work.

Skeptic
45/100 · skip

Browser automation that runs inside your session is exactly the attack surface that malicious sites exploit. Subroutines executing in-tab with full cookie access means a compromised script could do real damage. The 'zero token cost' claim also obscures that you still need LLM calls for parameter selection — the savings are real but overstated.

45/100 · skip

The GitHub repo wasn't findable, which raises questions about maturity and maintenance trajectory. Until the codebase is publicly accessible and documented, this is hard to evaluate or trust for serious use.

Futurist
80/100 · ship

This is the 'compilation' step for agentic workflows — moving from 'LLM decides every click' to 'LLM selects a pre-compiled action.' That separation of concerns (intelligence vs. execution) is how you scale agent operations from one-off demos to production pipelines. The pattern will be widely copied.

80/100 · ship

The model of AI agents that accumulate institutional knowledge over time mirrors how human teams work. WUPHF is an early prototype of the 'living AI workforce' that will become standard infrastructure.

Creator
80/100 · ship

For creators doing outreach, social posting, or newsletter campaigns, this is genuinely transformative. Recording a campaign action once and letting AI handle personalization at scale is the efficiency unlock that makes solo creator businesses actually viable at volume.

80/100 · ship

Running agents from Telegram while I'm away from my desk sounds exactly like how I want to work. The zero-cost barrier means I can experiment with agentic workflows without justifying a subscription.

Weekly AI Tool Verdicts

Get the next comparison in your inbox

New AI tools ship daily. We compare them before you waste an afternoon.

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later