AI tool comparison
Goose v1.29 vs Holo3
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
AI Agents
Goose v1.29
The open-source AI agent that uses your Claude, Gemini, or ChatGPT subscription
25%
Panel ship
—
Community
Free
Entry
Block's open-source on-machine AI agent just hit v1.29, introducing Gemini ACP (Agent Client Protocol) support so you can run the full Goose agent stack using your existing Google subscription — no separate API key needed. It also added orchestration for sub-agents, adversarial agent mode to prevent information leaks, delegate sub-agent log display, and macOS sandboxing. With 35k+ GitHub stars and Rust-based architecture, Goose goes far beyond autocomplete: it builds projects, writes and executes code, manages files, and calls external APIs autonomously. The ACP approach means your Goose extensions are passed directly to Gemini, deepening the connection compared to plain CLI usage.
AI Agents
Holo3
SOTA GUI agent VLM — beats GPT-5.4 on OSWorld at 1/10th the cost
75%
Panel ship
—
Community
Free
Entry
Holo3 is a vision-language model built specifically for GUI agents — AI that can see and interact with web browsers, desktop apps, and mobile UIs. Developed by H Company, the 35B-A3B mixture-of-experts variant scores 78.85% on OSWorld-Verified, the most rigorous benchmark for autonomous computer use, edging out GPT-5.4 Thinking and Claude Opus 4.6 while reportedly costing 10x less to run. The model architecture separates GUI understanding from action planning using a sparse MoE design, enabling high accuracy with a much smaller active parameter footprint. It supports point-and-click, scroll, type, and multi-step workflows across all major OS environments. Weights for the 35B-A3B variant are released under Apache 2.0, while a free-tier API is available at hub.hcompany.ai. H Company is a Paris-based AI startup founded by former DeepMind researchers. Holo3 is their bet that purpose-built specialist models will outperform general-purpose frontier LLMs on narrow, high-value verticals — and the OSWorld leaderboard suggests they're winning that bet for now.
Reviewer scorecard
“This is exactly the architecture I want: a local agent that doesn't lock me into one AI provider's billing. The Gemini ACP integration means my Google One subscription now funds actual dev automation. The adversarial agent mode is also clever — finally an agent that polices itself before it nukes your filesystem.”
“Topping OSWorld-Verified while being open-source and cheap to run is a genuinely rare combination. If you're building any kind of browser automation or desktop agent pipeline, this is the model to benchmark against first. The free API tier lowers the barrier to try it immediately.”
“Multi-agent orchestration sounds great until you're debugging a cascade failure at 2am wondering which sub-agent hallucinated first. The 35k stars are real but so is the complexity overhead. Claude Code and Cursor 3 have more polish for day-to-day use — Goose still feels like a power-user project.”
“OSWorld numbers are impressive, but benchmarks and real-world reliability are very different things. GUI agents still struggle with dynamic content, CAPTCHAs, login flows, and anything that deviates from the training distribution. H Company is a small startup — unclear if they can keep pace with OpenAI/Anthropic iteration cycles.”
“The ACP subscription model is the thin edge of a wedge that eventually makes AI provider lock-in irrelevant. When agents can switch between Claude, Gemini, and GPT seamlessly based on cost and availability, the moat moves to the orchestration layer. Block is quietly building that layer in the open.”
“GUI agents are the missing layer for true software automation. A model that can reliably use any desktop app or web interface without APIs is transformative for enterprise workflow automation. The fact that a small European team is leading the OSWorld benchmark signals that vertical AI specialists are a real competitive force in 2026.”
“The MCP Apps and rich UI stuff is interesting for creative workflows, but Goose is fundamentally a developer tool. The learning curve before it does anything useful for non-devs is steep. I'll check back when the Neighborhood Extension for ordering food is the least niche thing it can do.”
“As someone who constantly switches between design tools, browser previews, and CMS dashboards — a reliable GUI agent would be genuinely life-changing. Holo3's ability to handle multi-step UI workflows without brittle selectors or fragile Playwright scripts is what makes this interesting beyond the benchmark numbers.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.