概览
主要功能
- 结构化的 Markdown 记忆格式
- 基于 PGP 的加密与解密
- 身份和性格的持久化
- 跨平台代理可移植性
- 可版本控制的代理状态
- 与工具无关的集成
价格
- 模型
- Free
- 分类
- Memory
- 评分
- 4.7 / 5 (6)
使用场景
长期运行助手的持久记忆
通过在每次实例化代理时重新加载结构化的 Markdown 文件，为聊天机器人和 AI 助手提供跨会话的持久记忆，从而保留性格和历史。
跨设备的安全代理状态同步
使用 PGP 加密安全地在机器或团队成员之间存储和同步代理记忆块，避免泄露私人上下文或敏感知识。
跨模型与平台的可移植身份
使用与工具无关的 Markdown 格式，在不同 LLM 提供商或框架之间迁移代理的性格和知识，避免被单一厂商锁定。
版本控制的多代理系统
在 Git 中追踪、审计和回滚代理状态，以支持自治或多代理设置，将身份文件视作仓库中其他代码制品进行管理。
优点 & 缺点
优点
- 为 AI 代理提供跨会话的持久记忆
- PGP 加密保护敏感的代理数据
- 可移植的 Markdown 格式易于阅读
- 可在不同模型和平台上运行
缺点
- 需要熟悉 PGP 密钥管理
- 相比托管记忆服务，需要手动设置
- Markdown 文件随时间可能变得庞大
评测
6 个评分的平均值。
登录以留下评测。
Solid for our team
We rolled this out across the team last quarter and portable Markdown format is human-readable. PGP-based encryption and decryption fits neatly into how we already work, and pGP-based encryption and decryption removed a step we used to do by hand. Markdown files can grow large over time, which is the main caveat, but it has held up under daily use.
Years in this space
I've evaluated a lot of these over the years. What stands out here is pGP-based encryption and decryption — handled better than most — and works across different models and platforms. Worth the time if this is your use case.
Skeptical, then convinced
I went in skeptical — most tools in this space overpromise. It actually delivers on cross-platform agent portability, and gives AI agents persistent memory across sessions caught me off guard. Manual setup compared to hosted memory services is why this isn't a perfect score, still, I'd recommend giving it a real trial.
Compared a few options
Evaluated this against two competitors. Where it wins: cross-platform agent portability and works across different models and platforms. Where it lags: markdown files can grow large over time. On balance the feature set — especially pGP-based encryption and decryption — justifies the 4 stars for our use case.
Use it every day
Honestly didn't expect to like it this much. Tool-agnostic integration is exactly what I needed, and portable Markdown format is human-readable. but I reach for it almost every day now and it just clicks.
Does the job
Pretty happy overall. Cross-platform agent portability just works and gives AI agents persistent memory across sessions. Manual setup compared to hosted memory services can be annoying, but no dealbreakers — I'd recommend it to a friend without hesitating.
问答
How does EternalSoul.md integrate with my existing AI stack?
It's tool-agnostic and file-based, storing agent state in a structured Markdown file you load when instantiating an agent. This means it works across different models and platforms without requiring a specific SDK, fitting into familiar developer workflows like Git for versioning and auditing.
What are the main use cases for EternalSoul.md?
It's designed for developers building long-running assistants, autonomous agents, or multi-agent systems that need verifiable continuity. Typical uses include persisting personality, knowledge, and history across sessions, migrating agents between platforms, and securely syncing or sharing agent state.
What's the learning curve and are there any limitations?
You'll need familiarity with PGP key management, and setup is manual compared to hosted memory services. Additionally, Markdown memory files can grow large over time, so teams should plan for maintenance, pruning, or versioning strategies as agent history accumulates.
