xzf-thu / VoiceMem
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
Why this job: topics: long-term-memory, memory
What it does
- Accurate. Reaches 91.2% on LoCoMo, compared with 61.68% for Mem0, using only Top-5 memories.
- Emotional & Personal. Remembers not only what the user said, but also who the user is and how they feel. Reaches 69.44% on PersonaMem.
- Multimodal. Remembers speech, speakers, sound events, multi-speaker conversations, and music from real-world audio.
- Fast. Responds in 134 ms, compared with 1,440 ms for Mem0, with streaming retrieval inside the voice turn.
- Low Token Usage. Uses only 430 memory tokens, compared with 6,956 for Mem0 and 1,899 for EverMemOS.
Get started
pip install -U huggingface_hub
hf download zhifeixie/VoiceMem_Default_Models_Env --local-dir ./models - Maintenance
- Active
- Last commit 57 days ago
- Stars
- 2,896
- +26 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.0.2
- Released 2 months ago
- Built with
- Python
- 85% of the code
Is it looked after?
- Contributors
- 5
- Last 90 days
- Issues
- 0% closed
- 7 still open
- Pull requests
- 4 merged
- 0 waiting
- Releases
- 2
- 2 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| mem0ai / mem0 | 68,717 | 4 days ago | Apache-2.0 | No downloads |
| MemTensor / MemOS | 12,337 | yesterday | Apache-2.0 | No downloads |
| zjunlp / LightMem | 1,219 | 4 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 85%
- HTML 14%
- Shell <1%
- JavaScript <1%
Topics
- ai
- ai-agents
- ai-tools
- application
- audio-streaming
- genai
- llm
- long-term-memory
- memory
- memory-management
- python
- voice-agent
Project record
- JobAgent memory
- StatusFeatured
- Commits78
- Forks268
- Watching155
- Stars in 28 days+402
- CreatedAug 17, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026