# Gen-Verse/DiscoveryRSI

> An agentic framework for scientific hypothesis discovery: a multi-agent loop builds a research graph, compiles experiments, and trains the DiscoveryRSI-27B model on accumulated experience.

- Magnitude: 4.1 out of 10 — Early signal
- Stars: 118 total · Not enough measurements today
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · Created: 2026-10-15 · Last push: 2026-10-20
- GitHub: https://github.com/Gen-Verse/DiscoveryRSI · Homepage: https://arxiv.org/abs/2610.23839 · Page: https://gitnova.dev/en/r/Gen-Verse/DiscoveryRSI

## Useful for

- Run the local discovery-rsi demo to test the agentic hypothesis loop
- Serve DiscoveryRSI-27B via vllm and point the harness at the OpenAI-compatible endpoint
- Evaluate cumulative research progress across DFM-Bench levels in life science

## Why it’s here

- There are not enough fresh counter measurements for today's UTC day. The gain is unknown.
- The repository is 6 days old and already has 118 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #153.
- Recent forks include notable developers: @0xSojalSec (1,042 followers), @YangLing0818 (647 followers).

## 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: 10
- Issues and pull requests: 1
- Watchers: 1
- Average over the last week: 21 per day
- Usual pace: too little history (under two weeks)

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

2026-10-15 … 2026-10-21: 0, 0, 1, 24, 65, 28, None

## Magnitude by day, last 2 days

10-20 4.2, 10-21 4.1

## Spotted in now

- Top new repositories this week: #153

## Similar by description

1. **Clearailhc/clearai-dsh** — 3.0 · Peaking · AI agents · JavaScript · Not enough measurements today
   A DeepSeek Harness plugin implementing the Epistemic Loop: hypotheses are tested and independently evaluated, and confirmed conclusions accumulate into a growing domain ontology.
   Full card: https://gitnova.dev/en/r/Clearailhc/clearai-dsh.md
2. **Danielxu0208/rsi_eval** — 1.2 · Steady · Language models · Python · Not enough measurements today
   A Python SDK and CLI that evaluates recursive self-improvement methods by running agent benchmark tasks and returning scores, status, and token usage. It lets you plug in your own improvement loop and reuse pinned benchmark tasks for…
   Full card: https://gitnova.dev/en/r/Danielxu0208/rsi_eval.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 2026-10-21 00:15 UTC, updated every 30 minutes.