Julie update
local LLMs, CUA, installers and perf gains
Details
- External ID
- 46520784
- Source
- HN
- Company
- —
- Product
- Julie update
- Website domain
- vercel.app
- Launched
- Jan. 7, 2026
- Cohort
- —
- Upvotes
- 8
- Upvotes percentile
- 0.41699604743083
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
The biggest shift is that Julie now supports fully local LLMs and agentic workflows. It’s no longer limited to answering questions about what’s on screen. It can now run writing and coding agents, and optionally take concrete actions on your computer under supervision.What’s new:- Local LLM support. Julie can now run entirely on-device,- Agentic computer use. I added a computer-use mode with demos showing multi-step actions like clicking, typing, and navigation.- Writing and coding agents. Draft, refactor, and iterate in-place without moving into a separate workspace.- Installers are now available, so setup is a lot simpler.- Significant performance improvements across startup time, memory usage, and latency.I also wrote a full walkthrough and demos covering how the agents work and where the boundaries are: https://tryjulie.vercel.app/Repo + installers: https://github.com/Luthiraa/julieThanks for all the support and feedback. From the bottom of my heart, I really appreciate it. I’ve loved building this, and it’s been one of the fastest things I’ve taken from idea to something real that people are actually using. I really love this community.If you enjoyed checking it out, a star on the repo would mean a lot and helps more people find it.
Enrichment
- Theme
- developer tools for AI agents
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- local llm runtime and tools
- Manually corrected
- False
Could you build this?
Partial A basic desktop overlay UI is easy, but local cross-platform Computer Use Agent (CUA) automation and real-time screen capture with low-latency local multimodal models involves tricky OS-level integrations.
What it would actually take: The stack involves an Electron/Tauri or native (Swift/C++) desktop app interacting with OS accessibility and screen-recording APIs, integrated with a local inference engine (e.g., llama.cpp/Ollama) running vision-language models. The difficult parts are real-time coordinate mapping across multi-monitor setups, native input synthetic event generation, and bounding-box detection accurate enough to reliably act on UI elements without breaking OS permissions.
Discussion
5 comments analyzed.
Competitors mentioned: Qwen3-8B (text model), Qwen3-VL-4B (vision model)
Concerns raised: Local LLMs limited for very long-context tasks, Local LLMs weaker for heavy code synthesis, Local LLMs struggle with reasoning over large codebases
Competitors
Other products that read as similar to this one — 58 launches clear the similarity bar, closest 8 shown.
Attention rank: #33 of 59 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 67 days after the earliest competitor.
- Julie Zero · hn · 2026-01-30 · 5 upvotes · similarity 0.47
- Agents, run any coding agent on your subscription not API costs · hn · 2026-05-31 · 6 upvotes · similarity 0.40
- Ardent, a code-first agent for non-engineering work · hn · 2026-09-03 · 10 upvotes · similarity 0.38
- LocalLLM · hn · 2026-04-23 · 16 upvotes · similarity 0.38
- DocMason · hn · 2026-04-04 · 11 upvotes · similarity 0.37
- What is wrong with the current coding agent workflow · hn · 2026-01-13 · 10 upvotes · similarity 0.37
- Cabinet · hn · 2026-04-05 · 16 upvotes · similarity 0.36
- I've implemented multi-repo workspace support in Agent of Empires · hn · 2026-05-11 · 6 upvotes · similarity 0.36
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.