AI tool comparison
Cai vs illumi
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Productivity
Cai
One keyboard shortcut. Local AI. No account, no cloud, no telemetry.
75%
Panel ship
—
Community
Free
Entry
Cai (⌥C) is a macOS utility that runs AI actions on anything — selected text, clipboard content, active app context — with a single keyboard shortcut, entirely locally. It ships with Ministral 3B bundled, so it works offline out of the box with no API key, no account signup, and no network requests. For developers who prefer their own stack, it also connects to Ollama, LM Studio, Apple Intelligence, and OpenRouter. Beyond text transformations, Cai acts as a local automation layer: it can open GitHub issue drafts in your browser, create Linear tickets from selected text, run custom shell scripts, and chain multiple actions together. The whole thing is MIT licensed and open source. The UX is intentionally minimal — no chat interface, no persistent window — just a quick invocation overlay that appears, acts, and disappears. The positioning is clear: Cai competes with productivity tools like Raycast AI and PopClip, but wins on the privacy angle. There's no vendor seeing your prompts, no subscription creep, and no dependency on internet connectivity. For developers, writers, and researchers working with sensitive content who want AI assistance without cloud exposure, Cai fills a real gap that bigger AI apps can't — or won't — fill.
Productivity
illumi
AI workspace that takes you from messy thinking to polished deliverable — and remembers the journey
75%
Panel ship
—
Community
Free
Entry
illumi is an AI visual workspace designed around one thesis: "execution got cheap overnight, but comprehension didn't keep up." The founders argue that modern AI tools accelerate output production but fragment the thinking process — each conversation starts fresh, context gets lost, and knowledge workers spend more time reconstructing mental models than doing actual work. The tool maintains session continuity across work phases: raw notes and messy thinking in early sessions are preserved and connected to the polished deliverables they eventually become. AI assists at each stage — synthesizing scattered notes into structured frameworks, drafting deliverables from frameworks, and flagging when new context contradicts earlier decisions. The workspace is designed to make the evolution of a project's thinking visible, not just its final outputs. illumi launched on Product Hunt on April 21, 2026 with 92 upvotes and sparked one of the more substantive discussions of the week — a thread titled "Is AI making knowledge work harder, not easier?" resonated strongly. A two-founder indie team built it. At this stage it's an early product with a clear POV, targeting knowledge workers who feel increasingly productive but increasingly confused about their own work.
Reviewer scorecard
“I set up Cai with a custom action to take a stack trace from my clipboard and open a pre-filled GitHub issue in 10 minutes. The Ollama backend means I can use a larger local model when I'm at my desk and fall back to Ministral 3B on the go. MIT license means I can fork it and add my team's internal tools.”
“The problem statement is accurate — I have a graveyard of ChatGPT conversations that led to good decisions I can no longer reconstruct. A tool that preserves the reasoning chain from messy brainstorm to shipping decision is worth trying. Whether illumi actually does that at v1 is the real question.”
“Ministral 3B is fine for basic text tasks but it stumbles on anything requiring real reasoning or domain knowledge. Most users will hit its limits quickly and need to set up Ollama anyway — which is a non-trivial setup process for non-developers. The privacy story is genuine but the capability bar is lower than what cloud alternatives offer.”
“'Session continuity' and 'preserved thinking' are features that require deep integration into how you actually work — and most people won't restructure their workflow around a new tool unless it's dramatically better from day one. The 92 PH upvotes suggest interest, not retention. Come back in six months.”
“Cai represents a class of tools that become dramatically more useful as on-device models improve. When Bonsai-scale 1-bit models hit 8B+ quality at 131 tokens/sec locally, Cai's architecture is exactly right — a minimal, composable action layer on top of local inference. The MIT license means the community will build the plugin ecosystem.”
“The 'cognitive overhead of AI' problem is real and growing. We're heading toward a world where AI-generated outputs vastly outnumber human-reviewed outputs — tools that make the thinking process durable and auditable aren't productivity luxuries, they're organizational infrastructure.”
“I've been looking for a way to do quick AI rewrites and tone adjustments in any app — not just in a web browser — without pasting things into a chat interface. Cai works in Figma, Notion, Miro, everything. The local privacy angle matters a lot when I'm working on client content that's under NDA.”
“For content strategists and writers who live in the messy middle of multiple projects, a workspace that connects early ideation to final drafts without losing the 'why' behind every decision addresses a daily frustration. The visual approach feels right for how creative thinking actually works.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.