by xzf-thu · Agent Tool · ★ 1.6k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/lang-jiaqi/Voicemem_open.git
pip install voicemem
Taken from the project's README on GitHub. Check the security audit before running it.
Flagged: environment access. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 1,640 |
| Forks | 113 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 61/100 |
| Open Issues | 7 |
| Last Updated | 2026-09-14 |
| Created | 2026-08-17 |
| Platforms | python |
| Est. Tokens | ~19k |
中文 | English 项目主页 🌐 / 技术报告 📖 / VoiceMem Utils 🤗 / VoiceMem Model Families 🤗 / ChatMem-400K 🤗 我们带来 VoiceMem,为语音模型增加最后一个组件:灵魂,让它真正越来越懂你。VoiceMem 建立在「流式双脑」架构之上,提供精准、有情感、懂人格、低延迟且最便宜的记忆服务。本仓库将「永久保持全部开源」。 快速理解 VoiceMem: 左脑:
These tools work well together with VoiceMem for enhanced workflows:
Looking for a VoiceMem alternative? If you're comparing VoiceMem with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Memory library for building stateful agents
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
A memory OS that makes your OpenClaw agents more personal while saving tokens.
One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosyst
This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure whe
A model-driven approach to building AI agents in just a few lines of code.
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: