# Fengzdadi/memory-bench-registry

> A structured registry of agent memory benchmarks: one YAML file per benchmark, with every field traced back to its source (paper or official repository).

- Magnitude: 4.1 out of 10 — Early signal
- Stars: 103 total · +1 star measured 2026-10-14, 00:37–02:45 UTC, ≈ 37 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: HTML · License: MIT · Created: 2026-10-11 · Last push: 2026-10-12
- GitHub: https://github.com/Fengzdadi/memory-bench-registry · Page: https://gitnova.dev/en/r/Fengzdadi/memory-bench-registry

## Useful for

- Find agent memory benchmarks by memory type and reproducibility level
- Check which benchmarks ship an official script versus only a paper
- Build a shortlist of benchmarks for evaluating long-term memory in dialogue agents

## Why it’s here

- Star-counter measurements on 2026-10-14 (UTC), 00:37–02:45: 102 → 103 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +37 stars, using observed gains and the previous day.
- The repository is 3 days old and already has 103 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #174.

## 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: 5
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 35 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 4 days (oldest → newest, today is partial)

2026-10-11 … 2026-10-14: 0, 57, 46, 1

## Spotted in now

- Top new repositories this week: #174

## More in this category

1. **lyogavin/airllm** — 6.9 · Breakout · Language models · Jupyter Notebook · +68 stars measured 2026-10-14, 00:37–02:44 UTC, ≈ 619 by evening
   A library for inference and training of large language models on low-VRAM GPUs: it streams weights layer by layer from disk, letting 70B–671B models run on 4–12 GB of VRAM without quantization or distillation.
   Full card: https://gitnova.dev/en/r/lyogavin/airllm.md
2. **prabanta-dev/janas** — 6.8 · Early signal · Language models · C · +11 stars measured 2026-10-14, 00:37–02:44 UTC, ≈ 166 by evening
   Janas is a family of AI tools in C with no dependencies. Janas-LLM runs large MoE models (up to 80B, 48 GB) on a 32 GB laptop by streaming experts from NVMe SSD, and outperforms llama.cpp on all 13 tested models.
   Full card: https://gitnova.dev/en/r/prabanta-dev/janas.md
3. **open-webui/open-webui** — 5.8 · Breakout · Language models · Python · +15 stars measured 2026-10-14, 00:37–02:44 UTC, ≈ 250 by evening
   Open WebUI is a self-hosted web interface for AI models via Ollama and OpenAI-compatible APIs, with RAG, plugins, agents, and team collaboration.
   Full card: https://gitnova.dev/en/r/open-webui/open-webui.md
4. **microsoft/BitNet** — 5.1 · Breakout · Language models · C++ · +5 stars measured 2026-10-14, 00:37–02:45 UTC, ≈ 96 by evening
   Official inference framework for 1-bit LLMs (BitNet b1.58) with optimized kernels for CPU and GPU. Runs ternary models fast and losslessly, including a 100B model on a single CPU.
   Full card: https://gitnova.dev/en/r/microsoft/BitNet.md
5. **composo-ai/DishwasherBench** — 5.0 · Early signal · Language models · TypeScript · +1 star measured 2026-10-14, 00:37–02:45 UTC, ≈ 43 by evening
   A browser game about loading a dishwasher, built on a physical simulation of a real Bosch machine to benchmark language models. Players load dishes, run the Eco 50 programme and score points for items that come out clean.
   Full card: https://gitnova.dev/en/r/composo-ai/DishwasherBench.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 2026-10-14 02:56 UTC, updated every 30 minutes.