domchan
84 posts


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.



English

GitHub 遇到的问题可能比我们想象的还要严重:GitHub 即日起暂停付费开通新的 Copilot Pro、Pro + 和学生订阅,同时缩减 Pro 订阅权益。
GitHub 目前似乎面临非常严重的算力短缺和成本问题,所以不惜得罪用户调整政策,当然 GitHub 也允许用户取消订阅并获得退款,GitHub 将免除四月份使用费。
查看详情:ourl.co/112751

中文

🎁 在Concrete池申购USDT,享受更多奖励!
#币安 钱包理财 Concrete 独家3倍积分加成等你来拿!
📅 从2026年4月2日 早上8:00 起(东八区时间),通过币安钱包理财在Concrete池申购USDT,即可享受额外3倍Concrete积分加成。
已有持仓用户无需重新申购,即可享受积分福利。
立即加入!👇
binance.onelink.me/mL1z/t4zu2wrd?…

中文















