TencentDB Agent Memory

@kudai_ai @TencentAI_News Thanks for asking! Each task gets its own mermaid graph. A lightweight judge between turns decides: continue, resume an older task, or start a new one. Active context stays small. For more details, see the repo: github.com/Tencent/Tencen…

@TencentAI_News that's some serious optimization, how do you deal with context switching between tasks?

We spent 6 months on one problem: agents losing context in long sessions. Ended up building and open-sourcing an agent memory system. A few things we learned: 🪄compressing stale context mid-session cut token usage by 61% 🪄giving agents a structured task map (mermaid-based) made them way less likely to lose track in 30+ step workflows 🪄persona coherence jumped from 48% to 76% once we added dedicated persona memory repo 👉 github.com/Tencent/Tencen… Agent memory is genuinely hard and we don't have all the answers. Happy to dig into architecture, benchmarks, tradeoffs, whatever. AMA👇 @TencentDBAbxo2 team is here to talk about it.

@truedomchan @TencentAI_News Thanks for reporting! Feel free to file a GitHub issue with the error details — we'll schedule a fix.

@TencentAI_News 装了这个插件之后升级龙虾，这个插件就报错，遇到好几次了。