AI 智能体共享状态上下文 [提问/展示][寻找 Beta 测试]
1 分•作者: aperi•6 个月前
嗨，黑客们！
我正在构建 Rice (docs.tryrice.com)。可以将 Rice 想象成一个为具有长期记忆的 AI 智能体设计的托管状态机。
Rice 是一个统一了 AI 智能体长期记忆和短期状态管理的平台。实际上，Rice 解决了即时语境复合问题——通过使用 Rice Slate（我们的状态管理服务），语境消耗降低了 60%。这使得智能体更有效率。状态管理层还允许智能体共享语境，而无需传统的“消息传递”方法，这意味着您可以运行并行的 AI 智能体。
记忆层使智能体能够更广泛地理解数据和关系——为智能体提供大规模的个性化和自动化。
我们的与众不同之处 (https://docs.tryrice.com/rice-vs) 以及我们正在开发的一些很酷的功能。
核心价值主张：
1. 开箱即用的可审计的智能体执行
2. AI 智能体的共享状态（不使用消息传递方法）以实现高效执行
3. 用于历史数据等的持久性记忆
目前处于 Beta 测试阶段，正在寻找 Beta 测试人员。欢迎提出任何想法和测试。
如果您想参与 Beta 测试，请在 tryrice.com 上输入您的电子邮件。
查看原文
Hola Hackers!<p>I'm building Rice (docs.tryrice.com). Think of Rice as a managed state machine for AI agents with long term memory.<p>Rice is a platform that unifies long term memory and short term state management for AI agents. Effectively, Rice solves the context compounding issue in the immediate sense - by using Rice Slate (our state management service), the context consumption was down 60%. This makes the agents more efficient. The state management layer also allows agents to share context without the conventional "message passing" approach meaning you can run parallel AI agents.<p>The memory layer enables the agents to have a broader contextual understand of the data and relationships - personalisation and automation at scale for agents.<p>How we're different (https://docs.tryrice.com/rice-vs) and working on some cool aspects.<p>The core value prop -<p>1. Auditable Agentic executions out of the box
2. Shared state for AI agents (not using message passing approach) for efficient executions
3. Persistent memory for historical data and more.<p>Currently in beta phase, so looking for beta testers. Appreciate any thoughts and tests.<p>Please enter your email at tryrice.com if you'd like to get in the beta.