shhivv/third-hand
About the project
A small macOS menu bar assistant: focus an app, press Control–Space, and tell it what to do. It reads accessible controls, types, clicks, and checks the result using Accessibility, Apple Vision, and the Jev model.
Useful for
- Automate a search inside an app by dictating a task via Control–Space
- Enter an exact terminal command such as type "ls -la"
- Build and run the app from source using rebuild.sh
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 55 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 1 day old and already has 83 stars.
- Top new repositories this week: #164.
- About 35 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 89
- Stars in a day
- 55
- Forks
- 10
- Issues and pull requests
- 0
- Watchers
- 0
- Language
- Swift
- License
- MIT
- Latest release
- v0.1.3 · September 19, 2026
- Created
- September 19, 2026
- Last push
- September 19, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 20, 2026Top new repositories this week: #156
Similar projects
-
8.8
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.
-
8.2
trycua/cua
Open-source toolkit for computer-use agents: cloud and local desktops, an app automation driver, and benchmarks for training and evaluation. For those giving AI agents control of a computer.
-
8.1
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
-
6.8
latent-spaces/brag
An agent skill (Claude Code, Codex, opencode, etc.) that turns a project you just built into a short launch video with music, motion, and share copy — in one command. Rendering is powered by Hyperframes.
-
6.5
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…
-
6.3
Sac-Y/Jev-cu
Jev-cu connects Computer Use with the Jev model (TypeSafe System One): Jev picks the element, action, completion level and risk from textual UI candidates, while Codex Computer Use reads the interface and executes…