# mariagorskikh/open-instinct

> An open-source personal AI agent you text on iMessage: it runs in its own microVM with a Linux desktop, connects apps via Composio, and coordinates with agents of people you trust.

- Magnitude: 5.5 out of 10 — Early signal
- Stars: 115 total · +11 stars measured 2026-10-06, 01:42–03:47 UTC, ≈ 92 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-10-03 · Last push: 2026-10-05
- GitHub: https://github.com/mariagorskikh/open-instinct · Page: https://gitnova.dev/en/r/mariagorskikh/open-instinct

## Useful for

- Deploy the agent on Maritime and connect your own iMessage number via Inkbox
- Configure access tiers so a partner's agent can read your calendar while strangers are denied
- Connect Notion or another Composio app and ask the agent to send a PDF brief over iMessage

## Why it’s here

- Star-counter measurements on 2026-10-06 (UTC), 01:42–03:47: 104 → 115 stars (+11). This is the change over that interval.
- Estimated end-of-day forecast: about +93 stars, using observed gains and the previous day.
- The repository is 3 days old and already has 115 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #145.
- About 43 forks a day — people are taking the code.

## 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: 21
- Issues and pull requests: 8
- Watchers: 1
- Average over the last week: 52 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 6

## Stars per day, last 10 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-06: 0, 0, 0, 0, 0, 0, 0, 13, 104, 11

## Spotted in now

- Top new repositories this week: #145

## More in this category

1. **lexmount/moli** — 7.9 · Breakout · AI agents · Rust · +336 stars measured 2026-10-06, 00:17–03:47 UTC, ≈ 1,685 by evening
   Moli is a headless browser written in Rust for AI agents, combining a full browser runtime with on-demand layout and rendering to keep resource use low. It fetches and extracts web pages, searches the web, and automates browser tasks via…
   Full card: https://gitnova.dev/en/r/lexmount/moli.md
2. **nykooi1/vibe-wise** — 7.2 · Breakout · AI agents · Python · +86 stars measured 2026-10-06, 00:17–03:47 UTC, ≈ 663 by evening
   A Claude Code plugin that makes the AI ask for your approach first, discuss tradeoffs, and explain unfamiliar concepts, writing code only after your confirmation. For anyone who wants to learn design while AI writes the code.
   Full card: https://gitnova.dev/en/r/nykooi1/vibe-wise.md
3. **odysseus-dev/odysseus** — 7.1 · Breakout · AI agents · Python · +191 stars measured 2026-10-06, 00:17–03:47 UTC, ≈ 913 by evening
   Self-hosted AI workspace combining chat, agents, deep research, documents, email, notes and calendar in one Docker deployment. Aimed at users who want local and API models plus personal data on their own server.
   Full card: https://gitnova.dev/en/r/odysseus-dev/odysseus.md
4. **elstongun/leviathan** — 6.9 · Early signal · AI agents · Rust · +89 stars measured 2026-10-06, 00:17–03:47 UTC, ≈ 425 by evening
   Leviathan is a single Rust binary that turns records (JSONL, JSON, CSV/TSV, SQLite, or any database CLI output) into a ranked full-text index, so agents get short cited result cards instead of reading raw data.
   Full card: https://gitnova.dev/en/r/elstongun/leviathan.md
5. **thedotmack/claude-mem** — 6.5 · Breakout · AI agents · TypeScript · +57 stars measured 2026-10-06, 00:17–03:47 UTC, ≈ 414 by evening
   Persistent memory system for Claude Code and other agents: it captures agent actions via lifecycle hooks, compresses them into semantic summaries, and injects relevant context into future sessions.
   Full card: https://gitnova.dev/en/r/thedotmack/claude-mem.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 2026-10-06 03:59 UTC, updated every 30 minutes.