Guanqun

@patrickc That’s what we’ve developed and open sourced at @puppyone_ai : a file-based context drive hosted in the cloud, with Git-based version control, collaborative, MCP and CLI support, and self-hosting.

I want some kind of LLM workflow tool. • Ability to manage a set of input files (Markdown or similar), plus other general-purpose context. • With real-time collaboration. (And maybe some concept of snapshots or VCS integration.) • And the ability to create/manage a inference workflows and a stored set of prompts. • Access to general-purpose coding agents (and not just chat models). • Some concept of compiled outputs/inference results (which ideally can be shared externally). Many projects have this feeling: "there is all this stuff, which I want to process/compute over in this iterated way, with some build artifacts being important/worth saving." GNU Autotools x Notion or something. Is anyone building this?

2026 is 43% complete.

Orchard, Orchard.

@JustJerry121 That’s cool! We’re taking a cloud-native approach here. Puppyone stores the user-authored files in s3; derived indexes (I suppose you’re talking about vector index or semantic index) are stored separately in Postgres.

@realGuantum Useful writeup. Scoped repos matter once agents have different permissions. I’m exploring the local-folder side with BaseHalf: editable context + .bh metadata. Do derived summaries/indexes live in Puppyone too, or only user-authored files? github.com/Pointa-Labs/ba…

Five million users would agree. Resetting the limits tomorrow morning to celebrate. Time to go /fast

@t64_bv @thsottiaux me too

@thsottiaux Fuck yeah. My limits reset in 1.5 hours Gonna spam XHIGH /fast all day

My codex activity map

@imkylelambert @puppyone_ai git-native context drive for AI agents

what is the next GitHub?

@thsottiaux this

Do you still trust benchmarks or do you just listen to your friends? What makes you try a new model?

@shadcn ghosty

got called out for still being on iTerm2. never found a reason to switch tho. what am i missing

@xiongchun007 不知不觉，Fortran 竟然成了 Agentic AI 开发的主流语言

不知不觉，Java 竟然成了 Agentic AI 开发的主流语言。😂

Codex Thursday has exceptionally moved to another day. Friday it is.

Now you can back up OpenClaw’s entire context to @puppyone_ai

After months of shipping, we launched @puppyone_ai 3.0: context infrastructure for multi-agent teams. Most agent teams don’t fail at models first. They fail when agents don’t share a single source of truth for context. What this means in practice: 1️⃣SaaS context is materialized into agent-readable files 2️⃣Each runtime gets scoped access (least privilege) 3️⃣Every write is versioned, auditable, and rollback-ready So your research agent, coding agent, and reviewer agent can work from the same governed workspace - without sharing human admin credentials. If you’re running OpenClaw, Claude Code, Codex, or Hermes, puppyone is designed to be the context layer across MCP, CLI, and API. Try: try.puppyone.ai CLI: puppyone.ai/en/cli Repo: github.com/puppyone-ai/pu… Full launch post——See more ⬇️ #AIEngineering #AIAgents #MCP #DevTools #OpenSource #puppyone30 #context

@thsottiaux Tibo, my godfather, could you please reset our usage limit?

This is completions API only and does not affect Codex.

Team is investigating elevated latencies across the board for API and ChatGPT. Updates will be posted on status.openai.com

If your Codex is doing something like this, you know it’s doing the right thing.

I shoulded turn the 'sync decktop and document folders' on

iCloud ruins my dev environment. It uploads all my project files and marks them as dataless. for all my day, I couldn’t even run 'npm run dev' successfully. @Apple