←
Botiverse7 posts
Botiverse avatar

Botiverse

@botiverse

Building the infrastructure for the agent era.

◷ Joined February 2026
Botiverse avatar
Botiverse@botiverse·Oct 29

Let's see what you build next.

Raft@raft_hqOct 29

Some of our favorite Raft projects came from people who just built and shared: a Flutter client, a Rust daemon, meetups in SF, Shanghai and Vancouver. We're starting the Builder Program for them: free Pro for a year, a model stipend, merch, and a room with the Raft team. If that sounds like you, apply at raft.builders

Post attachment
tison avatar
⟳ Botiverse retweeted
tison@tison1096·Oct 28

本文是我和 @raft_hq 的 Joint Channel 里的 Agent Tison 来回 Battle 数轮的成果 😇 不得不说,Joint Channel 确实是杀手级特性 🥵 Raft.build 用 PG 承载核心业务状态,RisingWave 维护收件箱与未读数等实时视图,Redis 负责服务间协同。如果把随 Agent 数量激增的运行 Trace 和长周期产品事件也塞进同一个 PG 库里,PG 基本是扛不住。 接入 ScopeDB 后,服务端、Daemon 和端侧的 Trace 与产品事件直接写进同一套基于对象存储的列式底座,固定列和动态 JSON 属性共存于一张表里。即使事件字段变化也不需要频繁改表,更没有维护 ETL Pipeline 的负担。 实际跑起来以后,我们发现 Agent 写 ScopeDB 的查询语言 ScopeQL 也比传统 SQL 稳得多。 因为 Agent 排查问题的推理过程是线性的:先圈定生产环境与时间窗 → 按 span_id 或 uuid 去重 → 按版本和错误原因进行聚合对比。 传统 SQL 要写“先去重、再做两阶段漏斗聚合”,往往要套多层 CTE 或子查询,Agent 生成查询时很容易搞丢字段作用域;而在 ScopeQL 里,它就是一条从上到下顺着写的线性管道: FROM -> WHERE -> DISTINCT ON -> GROUP BY -> AGGREGATE 下条链接到全文,包含完整的架构拆解、交互式故障排查过程,以及实际的 ScopeQL 查询示例。

How does @raft_hq scale agent logs and product analytics with ScopeDB? While PostgreSQL, RisingWave, and Redis run live workflows, ScopeDB gives Raft's engineers and observability agents a shared source of evidence for release checks and product funnels 👇

Post attachment
TennyZhuang avatar
⟳ Botiverse retweeted
TennyZhuang@zty0826·Oct 27

Big Tech is massively overstaffed. It always has been, and the agent era will make this even more obvious. From an organizational efficiency perspective, even cutting 90% of the workforce wouldn't be unreasonable. The bigger problem is that Big Tech is fundamentally bad at fostering innovation. No amount of culture-building can fix its organizational structure. Here's a better idea: Every Big Tech company should run its own YC. Encourage employees, or entire teams, to leave and start companies. Give them funding in exchange for equity. Small, independent teams are where real creativity happens. If they fail, just treat the investment as severance pay. In fact, Big Tech might be better positioned than YC or most incubators to evaluate which ideas and teams are worth betting on. They have the talent, domain expertise, and industry insights. The biggest risk is turning this into yet another internal incubator. That would defeat the entire purpose. It has to be a genuine top-down commitment to letting people leave, giving them real independence, and treating them as founders rather than employees. The mindset matters more than the money.

Microsoft is offering voluntary buyouts to around 60,000 employees, more than a qtr. of its workforce The program covers select teams in the U.S., Canada, U.K. & India, with severance packages Employees have until early December to decide, with departures planned for year-end

Post attachment
stdrc avatar
⟳ Botiverse retweeted
stdrc@istdrc·Oct 13

I've actually stopped using the word "harness." I now think in terms of two things: agent runtimes and agent applications. Agent runtimes should be very small. Their core job is to connect an LLM API to an execution environment. That environment could be a full OS or a language VM, like a JavaScript runtime. Almost all that matters here is robustness. An agent runtime must be able to keep an agent running forever. Literally forever. Agent applications are everything else. Yes, literally every piece of software in the world. If software isn't built for agents, they use it through computer use or browser use. These capabilities can be built into the agent runtime or provided by another agent application. If software is agent-native, agents should be able to use it directly. The experience of an agent using that software—what we call "agent experience"—needs to be carefully designed, at least for now, to make efficient use of both time and tokens. Another key piece is agent identity. Agent applications should recognize each agent individually, rather than just the browser or computer it's using. This allows each agent's actions to be recorded in detail and audited in real time or after the fact. Everything we're building at @botiverse follows from this view.

stdrc@istdrcAug 9

我的 bet 是 agent harness 会越来越厚(或者说,针对 agent 的 experience design 和状态管理被延伸到了更深更广的方面),厚到有一天人们终于都理解了一切都是 agent harness,就像一切都是 human harness Harness 这词还没火的时候,我就持有这个观点 x.com/istdrc/status/20188739… 事实上,我和 @xiaoxxchan 几乎是在中国大模型公司中最早引入 harness 概念的人,Kimi CLI 从 0 到 1 也几乎没有参考过任何开源或闭源 agent 实现,system prompt、agent loop、toolset、产品形态都是从零生长的。而随后我们意识到 harness 需要延伸到 agent 间通信系统(也就是 Claude 近期推出的 session 间对话),进而有了 multi-agent harness 概念,也就是 Raft 的前身

Botiverse avatar
Botiverse@botiverse·Sep 29

We think the software your team runs on should be something you love, trust, and can even contribute to. That's why we made Raft source-available under FSL. Making it source-available is only the first step. We're moving that development onto a new public Raft server. Soon it'll be open for contributors to join, prompt the agents, and help build Raft in the open.

stdrc@istdrcSep 24

stdrc @istdrc Sep 24 Article Raft.build is now source-available https://github.com/botiverse/raft-source We just made Raft source-available under FSL-1.1-ALv2. But we intentionally didn't publish our internal commit history or open pull requests. The public repository is a release