MemTensor / MemT-1.0
Official repository for MemT-1.0
Why this job: topics: long-term-memory, memory
What it does
MemT-1.0 integrates dynamic local memory and trainable hyper memory to retain and leverage historical information without accessing original context at inference. Its persistent state remains constant in size, reducing storage by approximately 66× versus full-context KV cache at 128K history length.
Get started
cd inference
uv pip install '.[server]'- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 530
- +14 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 0% closed
- 4 still open
- Pull requests
- 5 merged
- 2 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| tinqiao-oss / engramory | 204 | 4 days ago | MIT | No downloads |
| mtrnix / metronix-memory | 107 | 2 days ago | Apache-2.0 | No downloads |
| unibaseio / membase | 129 | today | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- Shell <1%
Topics
- ai-agents
- deepseek
- llm
- long-context
- long-term-memory
- memory
- memory-augmented-models
- native-memory
- qwen
- sglang
Project record
- JobAgent memory
- StatusNew to our list
- Commits6
- Forks40
- Watching3
- CreatedOct 19, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026