# MCG-NJU/OneStreamer

> OneStreamer is a streaming video LLM built on Qwen3-VL-4B that keeps textual memory of past events and decides when enough evidence has accumulated to respond. It targets online perception, memory, and proactive response over video streams.

- Magnitude: 3.7 out of 10 — Early signal
- Stars: 57 total · +0 stars today, ≈ 35 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-09-30 · Last push: 2026-10-02
- GitHub: https://github.com/MCG-NJU/OneStreamer · Page: https://gitnova.dev/en/r/MCG-NJU/OneStreamer

## Useful for

- Run the model on a video stream to answer questions proactively as frames arrive
- Build a pipeline with PHCM to keep textual event captions instead of full visual history
- Train a model on the OneStreamer-1M dataset for streaming video QA tasks

## Why it’s here

- 0 stars so far today, about 35 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 3 days old and already has 57 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #193.

## 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: 2
- Issues and pull requests: 1
- Watchers: 2
- Average over the last week: 23 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-03: 0, 0, 0, 1, 2, 54, 0

## Spotted in now

- Top new repositories this week: #193

## More in this category

1. **Niko1221/Strata** — 8.2 · Breakout · Language models · C++ · +0 stars today, ≈ 1,092 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md
2. **StayLameBro/backburner** — 5.2 · Early signal · Language models · Objective-C++ · +0 stars today, ≈ 68 by evening
   A llama.cpp fork that plugs an iPhone into a Mac over USB-C and splits the work: the Mac runs layers 1-40, the iPhone runs 41-64 on its GPU, speeding up prefill and allowing context up to 196k-229k tokens. Aimed at people running…
   Full card: https://gitnova.dev/en/r/StayLameBro/backburner.md
3. **Kutuyyy/Leaked-System-Prompt-AI** — 5.1 · Early signal · Language models · +0 stars today, ≈ 57 by evening
   A repository that collects and documents system prompts, instructions, and tool definitions of major AI models and agent platforms (OpenAI, Anthropic, Google, Cursor, Devin, etc.) for studying their behavior.
   Full card: https://gitnova.dev/en/r/Kutuyyy/Leaked-System-Prompt-AI.md
4. **Vibra-Ingenn/Janus** — 5.0 · Early signal · Language models · Go · +0 stars today, ≈ 29 by evening
   Local LLM server in Go: runs .gguf models via llama.cpp (Vulkan or CPU) and exposes an OpenAI-compatible API with a web UI and built-in tools.
   Full card: https://gitnova.dev/en/r/Vibra-Ingenn/Janus.md
5. **Edge0-AI/Edge0** — 4.4 · Breakout · Language models · Python · +0 stars today, ≈ 108 by evening
   An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run model tiers (35B and…
   Full card: https://gitnova.dev/en/r/Edge0-AI/Edge0.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 2026-10-03 04:42 UTC, updated every 30 minutes.