jebi - A supercharged terminal for Mac with built-in local AI
by•
jebi is a supercharged Mac terminal with built-in local AI — no API key, no subscription, no cloud.
After every command, it suggests what to run next. Hit an error? jebi explains it in plain English and tells you how to fix it. Type /ask to chat with AI right in your terminal.
All AI runs on-device with Qwen, Phi-3, and Gemma — your commands never leave your Mac. Beautiful UI, split panes, tabs, custom themes, grain texture, and slash commands like /ls and /ports.
Replies
jebi
Suggest and explain, rather than act, is the right default for a terminal. The terminal is too close to real damage for autonomy-first UX; the product earns trust by making the next step legible and still requiring intent.
jebi
@krekeltronics Exactly this. "Legible and requiring intent" is the right frame — the terminal is the one place where autonomy-first AI would genuinely erode trust rather than build it. Appreciate you putting it so clearly.
local model in the terminal is the right instinct — the cloud round-trip is what kills flow when you just want a quick command rewrite. the quality-vs-resident-size tradeoff is where this gets interesting.
jebi
@qifengzheng Exactly — the round-trip latency is the killer for flow. On the tradeoff: jebi lets you choose from 7 models (Qwen3 4B/8B, Gemma 3, Phi-3, and more) so you can match the model to your machine — pick a lighter 1.1GB model for speed or go up to 5GB for quality. The scope is also narrow enough that you don't need GPT-4 scale — a model that understands shell commands and your session context beats a smarter model with a 2-second cloud round-trip.
the 1.1–5GB ladder is the honest answer — picking the right rung is the per-mac calibration problem most local-AI products quietly punt. narrow-scope-beats-larger-cloud-model is the real wedge when the agent only needs shell context, not world knowledge.@jawahars16
jebi
@qifengzheng Thanks for your input. We're trying to close the gap choosing the right model — the labels (Fast, Balanced, Best quality) against the models on preferences screen is just a start. But updating those labels and auto recommending models based on available RAM could be a wonderful addition.
The restraint is what sells it for me — AI that only speaks up after an error or a finished command beats an always-on copilot stealing focus. With Qwen, Phi-3, and Gemma all running on-device, how do you route between them: is each model pinned to a task (error-explain vs /ask vs next-command suggestion), and what's the rough resident memory footprint with them loaded? On a 16GB Mac that's the one thing I'd want to know before switching my daily terminal.
jebi
@hi_i_am_mimo Great question on the routing — right now jebi uses one active model across all AI features (error explanations, suggestions, /ask). You pick it in Preferences → AI and it serves everything. No per-task routing yet, though that's an interesting direction.
On memory: for 16GB, I'd recommend Qwen2.5 1.5B (1.1GB, fast) or Gemma 2 2B (1.6GB, balanced) — both leave plenty of headroom. If you want more quality, Phi-3 Mini 3.8B (2.2GB) or Qwen2.5-Coder 3B (1.9GB, code-focused) are solid mid-tier options. I run Qwen3 4B on a 24GB machine and it sits comfortably without impacting anything else.
That clears it up — one active model you swap in Preferences is simpler than juggling per-task routing anyway. Quick follow-up on the on-device side: does the selected model stay resident between commands, or unload when idle to free RAM? And switching models in Preferences, is that a warm swap or does it reload weights cold each time?
jebi
@hi_i_am_mimo The model stays resident once loaded — no unloading between commands, so there's no reload latency on each use. On model switching: changing the active model in Preferences triggers a full restart of the AI backend, so it's a cold reload rather than a warm swap. Takes a few seconds but you only do it occasionally, so in practice it's not an issue.
jebi
@marc_vuit About 3 months of evenings and weekends! The terminal rendering (xterm.js + PTY) and getting llama.cpp running reliably on Apple Silicon were the hardest parts. The AI integration itself was actually faster once the foundation was solid.
@jawahars16 nice bro, but mine is an Intel CPU, so I could not try it but already you mentioned that in landing page
jebi
@marc_vuit Thanks for trying it out! Sorry it didn't work — Intel support is on the radar for a future release. Appreciate you giving it a shot!
LoadFast Snippet Expander
The terminal is such an interesting place for this because the cost of a wrong suggestion is higher than in a text editor. Curious how you're thinking about trust: does jebi mostly suggest/explain, or can it also take action directly inside the shell?
jebi
@vidur_saini Really well put — that's exactly the tension we thought about a lot. jebi is strictly suggest-and-explain, never act. It shows next-command suggestions as chips, you click or press ⌘⌥1/2/3 to run — nothing executes without user consent.
Mailwarm
Can you tune how proactive it is or turn suggestions off for certain commands?
jebi
@naimz Yes! Head to Preferences → AI → Advanced — you can toggle command suggestions, error explanations, directory context, and output analysis independently. Turn off just what you don't want.
Trice
@jebi unable to open after installing on mac
jebi
@surenganne Thanks for trying it out.
This is a standard macOS security prompt for apps outside the App Store — jebi is safe to open! To fix it: go to System Settings → Privacy & Security, scroll down, and click "Open Anyway" next to jebi. You'll only need to do this once.
We also have this noted on the website (hover the ? icon in install section)
Looks great! Any plans to implement a quake mode?
jebi
@berkcanucan It's a great idea — a quake-style drop-down terminal would fit jebi really well. Will consider it. Thanks for your input.
Local and no cloud is what sells me. Keeping everything on my own machine beats having the smartest model. Nice work.
jebi
@sllbailuo Thank you, that means a lot! That's exactly the bet jebi makes — privacy and zero latency over raw model power. Glad it resonates!