# isair/jarvis

> A private local-first desktop voice assistant: speech recognition, LLMs and speech synthesis run on your own hardware via Ollama or OpenAI-compatible servers, with personal memory and MCP tools.

- Magnitude: 2.2 out of 10 — Steady
- Stars: 2,056 total · +3 stars measured 2026-10-14, 10:58–11:56 UTC, ≈ 12 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · Created: 2025-08-19 · Last push: 2026-10-14
- GitHub: https://github.com/isair/jarvis · Homepage: https://barissencan.com/jarvis/ · Page: https://gitnova.dev/en/r/isair/jarvis

## Useful for

- Run a local voice assistant without sending data to the cloud
- Connect MCP servers for smart-home control or browser automation
- Dictate text into other apps via a hotkey with local transcription

## Why it’s here

- Star-counter measurements on 2026-10-14 (UTC), 10:58–11:56: 2053 → 2056 stars (+3). This is the change over that interval.
- Estimated end-of-day forecast: about +12 stars, using observed gains and the previous day.
- Over the last two days the pace is 2× that of the previous week and a half.
- GitHub Trending Python today: #13, +27 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 404
- Issues and pull requests: 1,091
- Watchers: 23
- Average over the last week: 15 per day
- Usual pace: 9 per day
- Stars in the last hour (measured): 1
- Latest release: v2.7.6 (2026-10-13)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-15 … 2026-10-14: 7, 4, 6, 9, 12, 7, 13, 16, 12, 14, 5, 11, 5, 6, 7, 2, 5, 3, 2, 6, 22, 14, 17, 9, 11, 5, 18, 23, 29, 3

## Spotted in now

- GitHub Trending Python today: #13, +27 stars

## More in this category

1. **morluto/rea** — 8.6 · Breakout · AI agents · TypeScript · +19,065 stars measured 2026-10-14, 00:37–11:46 UTC, ≈ 39,581 by evening
   A reverse-engineering tool that lets AI agents inspect apps and native binaries: it connects agents to Hopper or Ghidra via MCP and CLI, helping explain how a feature works and rebuild it in your own project.
   Full card: https://gitnova.dev/en/r/morluto/rea.md
2. **onehumanbeing/esp32-iphone-agent** — 7.8 · Breakout · AI agents · Python · +397 stars measured 2026-10-14, 00:37–11:46 UTC, ≈ 793 by evening
   Lets an AI model drive a real iPhone via an ESP32-S3: the screen is mirrored over AirPlay while the board emulates a USB mouse and keyboard. No Mac, Xcode, Apple developer account or jailbreak required.
   Full card: https://gitnova.dev/en/r/onehumanbeing/esp32-iphone-agent.md
3. **vercel-labs/skills** — 7.3 · Breakout · AI agents · TypeScript · +338 stars measured 2026-10-14, 00:37–12:03 UTC, ≈ 666 by evening
   CLI for the open agent skills ecosystem: installs, finds and runs reusable skills from Git repositories across Claude Code, Codex, Cursor, OpenCode and 75+ other agents.
   Full card: https://gitnova.dev/en/r/vercel-labs/skills.md
4. **nateherkai/roast-room** — 6.4 · Early signal · AI agents · JavaScript · +63 stars measured 2026-10-14, 00:37–11:47 UTC, ≈ 174 by evening
   A Claude Code tool where seven AI advisors (Bezos, Paul Graham, Hormozi, Gary Vee, Dan Martell, Gino Wickman, Buffett) debate your business decision around a table and hand you a scored verdict with a PDF report.
   Full card: https://gitnova.dev/en/r/nateherkai/roast-room.md
5. **Alishahryar1/free-claude-code** — 6.3 · Breakout · AI agents · Python · +191 stars measured 2026-10-14, 00:37–11:47 UTC, ≈ 495 by evening
   A local proxy and Admin UI that connects 54 model providers (including free tiers) to 10 coding agents such as Claude Code, Codex, Cline and Aider. Lets you run agents with any model from terminal, IDE, browser or messenger.
   Full card: https://gitnova.dev/en/r/Alishahryar1/free-claude-code.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-14 12:04 UTC, updated every 30 minutes.