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.
About the project
A memory system for voice agents built on a streaming dual-brain architecture: the left brain stores facts, the right brain handles emotions and persona, with streaming retrieval while the user is still speaking.
Useful for
- Plug VoiceMem into your own voice agent for long-term user memory
- Run the interactive web demo to test streaming retrieval and emotion recognition
- Fine-tune your own VoiceMem model family adapter on the ChatMem-400K dataset
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 75 stars today.
- The repository is 27 days old and already has 1,545 stars.
- Top new repositories this month: #39.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 1,545
- Stars in a day
- 76
- Forks
- 109
- Issues and pull requests
- 12
- Watchers
- 40
- Language
- Python
- License
- Apache-2.0
- Latest release
- v0.0.2 · September 1, 2026
- Created
- August 17, 2026
- Last push
- September 5, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 13, 2026Top new repositories this month: #39
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/xzf-thu/VoiceMem)Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.