AI tool comparison
AI Subroutines vs Goose
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Automation
AI Subroutines
Record a browser task once, replay it 500x at zero token cost
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.
AI Agents
Goose
Block's local-first AI agent in Rust — no cloud, no lock-in, full MCP support
75%
Panel ship
—
Community
Paid
Entry
Goose is an open-source, local-first AI agent framework built in Rust by Block (Jack Dorsey's fintech company). It runs entirely on your machine — no cloud dependency, no data leaving your system, no vendor lock-in. Model Context Protocol (MCP) support means Goose plugs into the growing ecosystem of MCP servers for filesystem access, git, databases, and web browsing without custom integration code. The Rust implementation is a meaningful architectural choice: Goose starts in milliseconds, uses minimal memory, and runs comfortably alongside IDE extensions, local models, and other dev tools without competing for resources. Unlike Python-based agent frameworks that feel heavy even when idle, Goose is a background process you forget is running until you need it. Block built Goose partly to solve internal developer productivity problems — it's real software from a company shipping real financial products, not a research demo from a lab. At 4,900+ GitHub stars without heavy marketing, the organic traction reflects genuine community interest in a capable, no-cloud-required alternative to API-dependent agent tools.
Reviewer scorecard
“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.”
“Rust + MCP is the combination I didn't know I needed. Goose starts instantly, stays out of the way, and connects to every tool in my stack through MCP without any glue code. This is what a production-grade local agent should feel like — not a Python script that takes 4 seconds to import.”
“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.”
“Block is a payments company, not an AI lab. Without a dedicated team maintaining the agent framework long-term, Goose risks becoming a well-starred abandoned repo. The Rust barrier to contribution also means a smaller community can fix bugs and add features compared to Python equivalents.”
“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.”
“Local-first AI agents are the antidote to the API dependency problem. When you own your compute and your data stays on your machine, the threat model for AI-assisted work changes entirely. Goose points toward a future where the 'agent layer' is infrastructure you control, not a service you subscribe to.”
“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.”
“The MCP filesystem and git connectors mean Goose can work with my actual project files without any setup. For creative work with sensitive client assets, running everything locally is non-negotiable — and Goose is the first agent I've seen that makes that genuinely easy.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.