Pinned Tweet
Launching my portfolio site: kintacollective.co and the initial blog post in a new series: lnkd.in/g2YnNrf3 if this looks and sounds interesting I am looking for a new devops/platform engineering role, feel free to dm me
Made a little app over the weekend to move my world building info from obsidian, going to eventually merge it into my agent harness orchestrator fork thats specialized for world building.
Hugo Pinheiro retweeted
Yesterday we finished transporting 66 animals from the frontline regions of Ukraine. This was all thanks to our collaboration with the soldiers, volunteers and shelters that took in the cats and dogs.
It was a long and dangerous road, but it was all worth the lives saved 💙
This was a great talk.
i've been to 132 conferences in 11 countries.
this is the best talk I've ever seen in my life.
a coffin on stage
projection mapping
auto-advancing hands-free slides
and fascinating storytelling
@davekiss's talk had it all.
Hugo Pinheiro retweeted
Am I doing slopcore right?
"Back to the Shire" by Merry & Pippin
Grok + Suno + Runway
Hugo Pinheiro retweeted
📌 Day 1,702 of the full-scale war
Yesterday, a further 300 kilograms of dog food and 100 kilograms of cat food were delivered to the “Love and tenderness“ animal shelter in the Odesa region. On 29 September, Russian shelling claimed the lives of 7 dogs and 15 cats, whilst a fire destroyed all their food and medicine supplies.
We also delivered 101 kilograms of pet food to military personnel in the Donetsk, Mykolaiv and Kharkiv regions, who are looking after 14 cats, 7 dogs, 10 kittens and a puppy.
Animals were neutered and microchipped at three shelters:
▫️ at “Pegasus” in the Dnipropetrovsk region — 93 dogs and 116 cats;
▫️ at “Dreams in the Palms” in the Dnipropetrovsk region — 24 dogs and 6 cats;
▫️ at “Novyi Svit in the Mykolaiv region — 34 dogs, 37 cats and 4 nutrias.
UAnimals volunteer Vladyslava Shylo distributed 340 kilograms of pet food and 215 veterinary supplies in the Kharkiv region. We are truly in awe of the courage and big hearts of these people.
We also provided advice on what to do if a pet goes missing.
Thank you to each and every one of you who supports us and helps us carry out our work. Together, we are a force that saves lives ❤️🩹
Hugo Pinheiro retweeted
📌 Day 1,701 of the full-scale war
Yesterday, we delivered a batch of veterinary supplies to the Ray of Kindness shelter in the Kharkiv region. It is home to 52 cats and 8 dogs. We are always happy when we can help ❤️
Hugo Pinheiro retweeted
Google quietly open-sourced an agent that taps Android phones for you. I assumed another demo repo — then I read the README.
ARTEMIS. Apache 2.0, Python 3.12+
github.com/google/artemis
It runs over MCP, so Claude Code, Codex or Cursor drives a real device or emulator: clicks, swipes, text input across apps. Screenshots and Logcat come back with the report.
Two profiles, and the gap between them is the whole story:
Flash — reactive loop, ~3-5s per step, no plan, no safety net
Pro — Planner + Operator + Checker, ~15-40s per step, every action passes a safety net before it fires
99%+ on AndroidWorld, 100+ multi-step tasks. Android only — iOS is on the roadmap, not shipped.
The honest part: this replaces the tapping, not the judgment. You still decide what's worth testing.
#AI #OpenSource
Hugo Pinheiro retweeted
Claude Artifacts are great, until you want to use your own agent.
𝗙𝗹𝗮𝘁𝘀 is an open source project I spotted on GitHub that's an alternative to Sites/Artifacts!
Github: github.com/gosuda/flats
It's a singe Go binary that turns your own machine into a home for what your agents build. You can connect Claude Code, Codex, Cursor, or any other MCP client to it, so you could use it with open source models too.
Your agent can make:
• 𝗪𝗲𝗯𝘀𝗶𝘁𝗲𝘀 - static sites or sandboxed apps, also with their own SQLite database
• 𝗣𝗮𝗴𝗲𝘀 - a single HTML artifact, so like a chart or report
• 𝗗𝗼𝗰𝘂𝗺𝗲𝗻𝘁𝘀 - live Markdown
• 𝗗𝗲𝘀𝗶𝗴𝗻𝘀 - HTML artboards for screens, landing pages and prototypes, etc
Agents save their work as 𝗣𝗿𝗶𝘃𝗮𝘁𝗲 𝗗𝗿𝗮𝗳𝘁𝘀 first. Actually deploying a version needs your approval in the console.
Sharing, though, is where this gets 𝘸𝘢𝘺𝘺𝘺 more interesting to me.
Normally, showing someone an agent-built site or document or dashboard means opening a public tunnel link that anyone can open.
Not very secure 🫠
Flats can serve each flat through a private overlay network instead. With NetBird turned on, every flat runs as its 𝗼𝘄𝗻 𝗡𝗲𝘁𝗕𝗶𝗿𝗱 𝗽𝗲𝗲𝗿, named after its slug, at 𝚂𝙻𝚄𝙶.𝚗𝚎𝚝𝚋𝚒𝚛𝚍.𝚌𝚕𝚘𝚞𝚍.
Your NetBird access policies then decide who can reach it.
So your laptop and phone can open that dashboard from anywhere, a teammate in a specific group can open it too, but nobody else can.
This is a flow we already use in our team, and it's really improved how we work. More on that soon 👀
Hugo Pinheiro retweeted
Day 3 of open sourcing our harness as pi-extensions: pi-durable-disk and pi-transport. We use both to run agents from anywhere. For us, the agent is the workspace. And the workspace lives in @archildata.
With @pidotdev durable, the session DB also lives in the disk. We can mount and unmount it from its sandbox, and run the pi loop from a web browser (w WASM) or a @modal VM with GPUs - sometimes in the same session.
Even easier, with Archil's serverless execution, we can run simpler agents. For example, we have an agent in-process go through 100s of GBs in Claude Code sessions and recall the entire history of a project in seconds.
It's interesting to see that so much of agent factories and chief of staff bot agents patterns were present In gas town a year and a half ago 😂
Hugo Pinheiro retweeted
1/6 🚨Releasing Actor-Gatherer framework, a new paradigm for agent context management developed at UC Berkeley for working with multiple agents in parallel over long sessions. Actor-Gatherer decouples knowing from acting: Actor agents perform tasks and Gatherer sets their context
Hugo Pinheiro retweeted
50 个 coding agent 抢同一条分支,Git 先扛不住了。
gitai 把 Anthropic 内部 Scion 公开过的思路做成了独立开源版:agent 只取自己要改的文件,改动并发落到同一分支;冲突交给模型解,但只有通过你设的验证命令才会合并。
刚发 v0.3.0,MIT,约 2.9K Star。
github.com/feder-cr/git-ai
Hugo Pinheiro retweeted
Phonon from @GradiumAI is an open TTS model in 31M and 40M sizes, perfect for on-device! It’s voice promptable too, via Gradium’s Voice Designer.
I love experimenting with voice and mobile. Here is Little Voices, an app where you can ask the angel and devil on your shoulder anything. It's a @pipecat_ai app in embedded Python on iPhone.
• Apple SpeechAnalyzer for speech-to-text
• Apple Foundation Models for the LLM
• Gradium Phonon 31M for TTS.
• Pipecat running in Python on the iPhone
• Pipecat Audience (for who speaks next. It works out whether you’re talking to the angel or the devil.)
• No network or inference costs!
📖 Repo here: github.com/pipecat-ai/ios-li…
You get sandboxes, I get sandboxes, everyone has sandboxes now, most products are turning into the same thing as everyone else's 🤣
Grafana Managed Sandboxes are in public preview!
Grafana Assistant gets a controlled cloud environment to develop proposed fixes, with a pull request for human review.
🔗: grafana.com/blog/grafana-ai-…
#ObservabilityCON
Hugo Pinheiro retweeted
We're releasing AgentVFS, a virtual filesystem interface for AI agents agentvfs.org/
AgentVFS unifies every service into one interface and replaces the need of calling MCP. Stored data becomes one virtual filesystem across services, described by VFS.md, and actions become virtual CLIs, so the agent no longer calls MCP tools at all. AI agents work on live data across every service through the terminal-like interface they know best. They use the Unix tools they learned in training (ls, grep, jq, pipes, loops) and the terminal workflows they practiced in post-training on agentic coding.
We're also releasing VFS-Bench 1.0 agentvfs.org/benchmark/vfs-b…, the first systematic study and benchmark to compare a virtual filesystem with MCP on the same tasks. Compared with MCP, AgentVFS uses up to 88% fewer tokens and has about a 5% higher success rate on average.
Hugo Pinheiro retweeted
🚨Introducing a new database: PGX 🐘
Postgres for AI agents. In Rust. pgx.dev
One runtime. Thousands of Postgres databases.
⚡ Up to 100× less idle memory
⚡ 1,000 databases in just 659 MB RAM
⚡ Clone a 674 MB database in 85 ms
⚡ ~0.7 MB per idle database
RUST. OPEN SOURCE. FREE.
No containers per database.
No heavyweight instances.
No production baggage.
Real Postgres. Built to be disposable.
xitter.cf/alxshp/status/21100494…
Introducing PGSync 🐘
Real-time PostgreSQL replication. FREE. OSS
Built in Rust. 🦀
Postgres 16 / 17 / 18.
No extensions. No triggers. No complex setup.
→ snapshot
→ replicate
→ stream changes
→ track WAL
→ recover from crashes
→ resume automatically
→ keep databases in sync
~15 MB RAM during streaming.
Built for developers. Built for AI agents.
Open source.
xitter.cf/alxshp/status/21078790…





























