Download Latest Version CodaiPro v3.0.0 source code.zip (2.2 MB) Google Add to Preferred Sources
Home / v3.0.0
Name Modified Size InfoDownloads / Week
Parent folder
CodaiPro-v3.0.0-Portable-Windows.zip 2026-09-08 29.2 MB
0
CodaiPro v3.0.0 source code.tar.gz 2026-09-08 2.2 MB
0
CodaiPro v3.0.0 source code.zip 2026-09-08 2.2 MB
0
README.md 2026-09-08 1.4 kB
0
Totals: 4 Items   33.6 MB 0

CodaiPro v3.0.0 — Codai Pro

The biggest upgrade yet: the desktop GUI is gone. Codai now runs the official llama-server engine with a fast browser chat UI — one process to launch, streaming answers, and a controller that watches and restarts the engine if it ever crashes.

New architecture

  • Real llama.cpp engine: llama-server runs locally, chat streams token by token
  • Browser UI with markdown rendering, code copy buttons, stop button, and conversation memory
  • Controller with health monitoring, auto-restart, hardware-aware tuning (RAM/CPU tiers), rotating logs and crash reports
  • Single portable folder: unzip, add a model, double-click run.bat

In the box

  • Codai.exe (packaged controller), engine\llama-server.exe (official llama.cpp build)
  • run.bat starts everything, waits for readiness, opens your browser
  • kill.bat force-cleans Codai processes and locks

First run

  1. Unzip anywhere writable (not C:\Program Files)
  2. Drop one model into models\ — default is gemma-3-1b-it-Q4_K_M.gguf (0.81 GB); see the model guide
  3. Double-click run.bat and wait for [READY]

System requirements

  • Windows 10/11 (64-bit)
  • 4 GB RAM minimum (2 GB works with the smallest models)
  • ~1 GB free for the app + 0.5–5 GB for one model

Full changelog: https://github.com/Luckyyaduvanshiofficial/Codai/compare/v2.1.2...v3.0.0

Source: README.md, updated 2026-09-08