Giving an AI agent memory is easy. Keeping it true is the hard part.

说明与用途

AI 代理的记忆易于持久化，但其真实性会迅速衰减。通过添加重新检查命令、区分观察与推断以及外部验证，可防止基于过时事实做出决策。

问题

AI agents can store memory across sessions, but the stored facts can become stale or incorrect, leading the agent to act on false information.

结果

By adding re-checks, separating observation from inference, and verifying externally, the agent’s decisions become more reliable and stale memory is quickly identified and corrected.

工作流

• 1. Store each memory fact as a markdown file with a clear claim.
• 2. Add a re-check command that can be executed to verify the claim.
• 3. Separate observed evidence from inferred conclusions in the file.
• 4. Prioritize filesystem state over memory when they conflict.
• 5. Perform external verification of claims (e.g., public API checks).
• 6. If external check fails, investigate the checker before updating memory.
• 7. Regularly review and update memory entries that influence decisions.

证据

In a single working day last week, four separate memory entries turned out to be confidently wrong

来源

Write the re-check, not just the claim

来源

Let files outrank memory

来源