# zju3dv/SuperNav

> An agentic navigation system built on a pretrained multimodal model that solves object-finding and multi-target tasks in Habitat-GS and AI2-THOR without navigation-specific fine-tuning.

- Magnitude: 1.7 out of 10 — Cooling
- Stars: 119 total · +1 star measured 2026-10-12, 03:01–04:28 UTC, ≈ 11 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · Created: 2026-10-08 · Last push: 2026-10-10
- GitHub: https://github.com/zju3dv/SuperNav · Homepage: https://zju3dv.github.io/SuperNav/ · Page: https://gitnova.dev/en/r/zju3dv/SuperNav

## Useful for

- Run a navigation agent in the Habitat-GS or AI2-THOR simulator using a bundled experiment recipe
- Compose a custom navigation task by combining tasks, tools, and Skills in an experiment config
- Inspect and evaluate an agent run via saved prompts, logs, and task metrics

## Why it’s here

- Star-counter measurements on 2026-10-12 (UTC), 03:01–04:28: 118 → 119 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +11 stars, using observed gains and the previous day.
- The repository is 4 days old and already has 119 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #197.

## 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: 0
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 26 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-10-08 … 2026-10-12: 25, 49, 31, 14, 1

## Spotted in now

- Top new repositories this week: #197

## More in this category

1. **morluto/rea** — 8.6 · Breakout · AI agents · TypeScript · +9,900 stars measured 2026-10-12, 00:13–04:23 UTC, ≈ 40,524 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. **Fei2411/DeepSeek-Bot** — 7.3 · Early signal · AI agents · JavaScript · +156 stars measured 2026-10-12, 00:13–04:23 UTC, ≈ 638 by evening
   A DeepSeek Harness (DSH) plugin that turns DSH Web and Desktop into a multi-agent collaboration workspace, letting multiple agents communicate, coordinate and run in parallel.
   Full card: https://gitnova.dev/en/r/Fei2411/DeepSeek-Bot.md
3. **rociiu/talorys** — 7.1 · Early signal · AI agents · TypeScript · +22 stars measured 2026-10-12, 00:13–04:23 UTC, ≈ 223 by evening
   A single-user personal AI assistant deployed into your own Cloudflare account, combining chat, memory, tasks, notes and scheduled reminders with no server or database run by the developers.
   Full card: https://gitnova.dev/en/r/rociiu/talorys.md
4. **hugohe3/ppt-master** — 6.9 · Breakout · AI agents · Python · +146 stars measured 2026-10-12, 00:13–04:23 UTC, ≈ 758 by evening
   A tool that turns documents or topics into native PowerPoint decks with shapes, charts, tables, animations and narration, running inside an AI agent on your machine.
   Full card: https://gitnova.dev/en/r/hugohe3/ppt-master.md
5. **zhongerxin/iPhone-use** — 6.3 · Peaking · AI agents · Python · +119 stars measured 2026-10-12, 00:13–04:23 UTC, ≈ 512 by evening
   Lets Codex control a real iPhone over USB via WebDriverAgent: it installs and signs WDA, exposes MCP tools for app navigation, taps, typing and list collection, and shows a live screen widget.
   Full card: https://gitnova.dev/en/r/zhongerxin/iPhone-use.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 2026-10-12 04:34 UTC, updated every 30 minutes.