samzong (@samzong_) header
samzong (@samzong_) profile picture

Engineer for AI-native systems, building @dify_ai and the tools I use myself.

Joined July 2013
Photo by samzong (@samzong_)Photo by samzong (@samzong_)Photo by samzong (@samzong_)Photo by samzong (@samzong_)Photo by samzong (@samzong_)Photo by samzong (@samzong_)Photo by samzong (@samzong_)Photo by samzong (@samzong_)Photo by samzong (@samzong_)Photo by samzong (@samzong_)
🌟 Dropped out of high school, but never stopped learning. My career has been a series of actively choosing the “harder path”: - Started with self-taught programming and became a tech evangelist and training instructor - Built a full-channel customer service product from 0 to 1, bootstrapped it to profitability, and successfully got acquired - Developed intelligent e-commerce customer service robots covering all platforms except Taobao (including cross-border) - Pivoted into containerization, and now fully focused on large model training and inference acceleration Continuous learning is my core foundation. My obsession and passion for technology is the only driving force behind every transformation. I’m not a traditional Product Manager — instead, I bring a strong Founder mindset: business-savvy, SaaS builder with deep user empathy, always hands-on in product definition and delivery. I love open source — my GitHub is my real resume. Currently Committer of vllm-project/semantic-router Contributor to Kueue / Karmada / Kubernetes / HAMi and more What I’ve always been seeking are creative, high-challenge projects and people. Because what truly sets my heart on fire is: The hope to make a real difference in this world. If that resonates with you, feel free to DM me directly.
2
10
2,318
使用 Recall 的欣喜时刻, 换了电脑且我只有一个模糊的记忆, 但 Recall 不仅仅快速帮我找到, 同时告诉发生在 codex 和 kimi code 的多个session 聚合 github.com/samzong/Recall
111
宣传下自己的dsh-ee: dsh-ee是企业级的deepseek-harness解决方案,完全开源。 今天发布v0.12版本,已正式支持连接器,skill、专家等企业级功能,感谢支持。 github.com/hikariming/dsh-ee
11
15
3
153
17,337
How I built my Agents system. rd-workflow-atlas.samzong.wo…
2
2
1
14
2,536
最近这几天开始频繁遇到一个问题, 并行开发时, 基本卡在 PR merge 阶段, 代码冲突, 导致了一些问题. 在尝试一个解决方案了, 大家有什么好思路分享吗?
2
239
在我的 duo 方案中, 有一个 land skill 机制, 我目前的想法是, land 在维护一个全局状态列表, 大家可以并行干活, 但是在进入到 land 阶段时需要获得准许.
1
84
cc kyc 最终还是来了, 这个还有救吗? 上中国护照可行吗?
3
1
469
周一上班, 来一口~
5
251
任何产品或项目, 存在的意义都很简单,就是"解决问题", 通常也会带来新问题. 开源是方式,不是目标. 就像代码是方式,不是目标. 好代码是好工艺, 好的工艺能更好地实现目标. AI 让解决问题速度变快了, 它也带来了更多问题. 这很正常. 时代往前走, 就会不断制造问题. 节奏一直是 build and fix++ then make better. 先做出来, 再修, 再变好. 参与开源,或给别人贡献代码, make something better. 这个世界破破烂烂(草台班子), 总需要有人去缝缝补补. 我一直认为, 更重要的其实是创意,时间,执行力. 没灯之前夜晚是黑的. 有人发明了灯,问题就解决了. 油灯,电灯,亮一点,暗一点,颜色多一点. 好不好? 很好. 但最重要的,是灯被定义出来. 千年暗室,一灯即明.
1
5
262
下周会去北京的 gotc2026 看到很多熟悉名字, 推上有大佬去的吗? 欢迎面基, c17. 另外,第一次进京, 有啥要注意的吗?
5
1
11
1,310
samzong retweeted
Kimi K3.1 Pro from @Kimi_Moonshot is now open. It’s a 2.8T multimodal model with 1M context, and it scores 65.7 on Terminal-Bench 4.0 and 92.1 on BrowseComp, up there with the top closed models. NVIDIA NeMo AutoModel now supports fine-tuning it, with FSDP2, EP, PP, CP. We trained the full model on 256 GB200 GPUs. Check out the detailed validation, recipes and loss curve in the PR: github.com/NVIDIA-NeMo/Autom…
1
6
4
21
4,284
试下 ego lite, 一周时间看看我有没有想回到 chrome.
2
235
Rx 正在成为我重要的伙伴, 事实证明自己打造属于自己 Agent 多么重要, 按照自己的思路处理. 上下文如何压缩?skill 如何发现? hook机制如何处理? 在用的过程中不断改造, 也让我不断成长. Rx 会是一个原生支持多 agent 协作(duo) + 聚合多agent sessions(recall)的完整呈现. github.com/samzong/Rx
1
9
892
单从 PR 量的视角, 复盘了一下 duo 给我带来的变化, 也顺便看看我今年一年的成长.
3
5
678
My Shipgrit Wrapped (All time): I'm a Night Owl 🚀 shipgrit.com/dev/samzong/wra…
1
126
分享下, recall remote sync 性能应该算是大幅度提升. 先道个歉, 之前做的不够检点导致磁盘写入的量比较大, 如果是 v0.6.5 建议尽快升级到 v0.6.7
6
333
鉴于磁盘实在太影响我的工作效率, 忍痛加入"尿袋"大军,舒服了.
2
7
927
门禁太严的坏处, 发版流程让 gpt-6.1 sol high fast 跑得好慢....
2
318
昨天 1024, 送给自己一份礼物, Rx 正式提供了内置 Coding Agent. 虽然还很简陋,但是经过1天的使用, 已经替换了 Duo 中 fast 级别的任务了. 以后也要过上左脚踩右脚的日子.
3
6
368
没有什么魔法 核心技术基于 pi-ai, pi-agent-core, pi-coding-agent 提供的mcp 和 skills 发现 提供 acp 接入到 Lody 中使用.
2
3
159