# Human-Agent-Society/reef

> Continual learning infrastructure for self-improving agents: connects agent inference, feedback collection, learning, and versioned delivery of updates. Lets you train model weights or improve an agent's harness (prompts, rules, skills).

- Magnitude: 0.8 out of 10 — Cooling
- Stars: 7,758 total · +0 stars measured 2026-10-29, 00:10–04:26 UTC, ≈ 1 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-08-31 · Last push: 2026-10-29
- GitHub: https://github.com/Human-Agent-Society/reef · Homepage: https://reefinfra.ai · Page: https://gitnova.dev/en/r/Human-Agent-Society/reef

## Useful for

- Run Reef as an OpenAI-compatible inference server for an agent
- Build a weight-training loop from response scores via /reef/report
- Improve agent prompts and rules without local training GPUs

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:10–04:26: 7758 → 7758 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +1 stars, using observed gains and the previous day.
- The repository is 59 days old and already has 7,758 stars.
- Top new repositories in the last 4 months: #86.

## 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: 731
- Issues and pull requests: 988
- Watchers: 522
- Average over the last week: 13 per day
- Usual pace: 50 per day
- Stars in the last hour (measured): 0
- Latest release: v0.1.3 (2026-10-14)

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

2026-09-30 … 2026-10-29: 74, 78, 16, 2, 4, 10, 12, 9, 18, 11, 3, 15, 44, 20, 16, 10, 6, 8, 27, 37, 35, 17, 24, 11, 16, 31, 16, 12, 2, 0

## Magnitude by day, last 14 days

10-16 1.7, 10-17 1.5, 10-18 1.8, 10-19 2.4, 10-20 2.6, 10-21 2.3, 10-22 2.0, 10-23 2.0, 10-24 1.5, 10-25 2.1, 10-26 2.2, 10-27 1.9, 10-28 1.7, 10-29 0.8

## Spotted in now

- Top new repositories in the last 4 months: #86

## Similar by description

1. **Prism-Shadow/penguin-harness** — 2.5 · Steady · AI agents · TypeScript · +12 stars measured 2026-10-29, 00:08–04:20 UTC, ≈ 53 by evening
   A framework for agent self-evolution (RSI): the model stays fixed while the harness evolves — prompts, Skills, tools and hooks. Runs as a desktop app, Web App, CLI and SDK with algorithm plugins (OPRO, APE, ACE, AWM) and built-in…
   Full card: https://gitnova.dev/en/r/Prism-Shadow/penguin-harness.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 2026-10-29 04:27 UTC, updated every 30 minutes.