The official implementation of the ICML 2024 paper "MemoryLLM: Towards Self-Updatable Large Language Models" and "M+: Extending MemoryLLM with Scalable Long-Term Memory"
active 2024-05-24 → 2026-05-26 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 733 days from 2024-05-24 to 2026-05-26. Pushes: 36 total, peak 4 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 16 total, peak 2 in a day. Comments: 16 total, peak 2 in a day. Stars: 222 total, peak 10 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| wangyu-ustc | 54 | 37 | 1 | 10 |
| crazyofapple | 2 | 0 | 0 | 0 |
| xiexie123 | 2 | 0 | 0 | 1 |
| yanmenxue | 2 | 0 | 0 | 1 |
| merdft | 1 | 0 | 0 | 1 |
| dcasbol | 1 | 0 | 0 | 0 |
| xzp9999 | 1 | 0 | 0 | 0 |
| maxjeblick | 1 | 0 | 0 | 0 |
| QuantumPlayDev | 1 | 0 | 0 | 0 |
| 958877748 | 1 | 0 | 0 | 0 |
| NielsRogge | 1 | 0 | 0 | 1 |
| ningpengtao-coder | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#14merdft2025-12-30 03:24Discrepancy in LongBench Evaluation Results
- Issue#15xzp99992025-11-13 08:37Update M+'s README.md
- Issue comment#11NielsRogge2025-07-29 19:35Release MemoryLLM checkpoints on Hugging Face
- Issue comment#11wangyu-ustc2025-07-22 02:02Release MemoryLLM checkpoints on Hugging Face
- Issue comment#12wangyu-ustc2025-07-22 02:01基座模型的通用能力有下降吗？
- Issue comment#12xiexie1232025-07-17 03:49基座模型的通用能力有下降吗？
- Issue comment#12wangyu-ustc2025-07-16 03:55基座模型的通用能力有下降吗？
- Issue#12xiexie1232025-07-15 09:03基座模型的通用能力有下降吗？
- Issue#5wangyu-ustc2025-02-15 12:54NumPy dependency
- Issue#10wangyu-ustc2025-02-15 12:54Incorrect transformers version
- Issue comment#5wangyu-ustc2025-02-15 12:53NumPy dependency
- Issue comment#3wangyu-ustc2025-02-15 12:52memoy llm better than Infini-Transformer?
- Issue#10maxjeblick2025-01-13 13:22Incorrect transformers version
- Issue comment#9wangyu-ustc2024-12-31 22:35License
- Issue#9wangyu-ustc2024-12-31 22:35License
- Pull request#8wangyu-ustc2024-11-23 01:24
- Issue#9QuantumPlayDev2024-11-22 08:13License
- Issue#7crazyofapple2024-08-23 08:10How to fine-tuning the MemoryLLM？
- Issue#6crazyofapple2024-08-21 08:29Nice work, how to reproduce the results of model editing evaluations of MemoryLLM?
- Issue#5dcasbol2024-08-21 08:26NumPy dependency
- Issue#4wangyu-ustc2024-08-20 09:40dataset download link has expired
- Issue comment#4wangyu-ustc2024-08-20 09:40dataset download link has expired
- Issue comment#4yanmenxue2024-08-16 12:45dataset download link has expired
- Issue comment#4wangyu-ustc2024-08-16 07:18dataset download link has expired
- Issue#4yanmenxue2024-08-10 17:37dataset download link has expired
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 222 stars here means stars gained during the window, not the repo's star count.