Pinned Tweet
This is how EACH task gets its own computer for Gemini Agent.
MicroVMs built for AI Agents that can rapidly go from 0 to millions of isolated computers.
Be REALLY AMBITIOUS with your Gemini Agent.
MicroVMs built for AI Agents that can rapidly go from 0 to millions of isolated computers.
Be REALLY AMBITIOUS with your Gemini Agent.
Gemini Agent is built for high-ceiling work where EACH task gets its own computer.
You can choose Gemini 4 Argon or Claude Opus 5.5.
10 things that make it a universal work Agent (read till the end to see what a REAL work agent looks like):
1. One Agent, one API
Chat, and code generation from a single interface. Assign it work, schedule it, or have it respond to events.
2. Coworker agents with their own identities
It creates job-specific sub-agents, each with its own identity, and computer running in parallel for hours or days.
Each Coworker agent gets its own Workspace account: an agent email, calendar, Drive, and presence in your company directory. You mention it in Chat. It acts under its own identity, not yours, and sees only what you share.
3. Everywhere, including headless
Web, iOS, Android, Windows, Mac, command line, Workspace, Microsoft 365, Slack. It also runs as a headless agent with no dedicated interface.
4. Work 24/7 in the cloud
It keeps one set of memories, context, and personalization graph across every device and channel. Work that takes hours or days keeps running after you close your laptop. You never have to re-brief it.
5. Layers of memory that improve over time
- Session: the task in front of it, even when it runs for days.
- Semantic: a structured knowledge base it builds as it reads documents, talks to people, and works with other agents.
- Procedural: how a job gets done, including skills it writes for itself.
- Episodic: everything it has done before.
6. Proactive by design
It does not wait to be prompted. An email asking you for a deck gets flagged as delegatable, one click to hand off. Your inbox ranks by what matters, not by what just arrived, and tells you why.
7. Tools and skills, with company registries
Salesforce, ServiceNow, Jira, Git, Confluence, Microsoft 365, Slack, BigQuery, Databricks, Postgres, Snowflake, your desktop files, and any MCP server inside or outside your network. Teams publish their own tools and skills to a shared company registry.
8. Model Choice so you are not locked in
It runs each job on the model that fits best, running across the Gemini and Claude models from Anthropic today, with other private and open models to come.
9. Governed like an employee
Every agent gets a cryptographically attested identity with least-privilege permissions, and an audit trail attributed to the agent rather than a person. Agents run in a sandbox behind Agent Gateway, an AI network firewall. Write the policy once and it applies to every agent.
10. Costs you can actually cap
Smart Routing puts each workload on the model with the best performance at the lowest cost. Set a hard spend limit in Cloud Billing and that project's agent pauses until you resume it in one click.
Thank you for reading so far. Stay tuned for updates.
We are 100% committed to make it the best Agent for work.
24
12
178
10,449
How always-on AI Agents work is a 45 mins masterclass from @leerob.
Must watch! x.com/leerob/status/…
Must watch! x.com/leerob/status/…
9
7
49
2,958
3 leanings from re-building COMPUTE for AI Agents.
The model will make mistakes. when it does, the sandbox shouldn’t hold anything that an attacker can use against it.
Agents spend most of their time waiting. An idle agent should cost almost nothing and wake up faster than a nt becomes more useful the more it remembers. Its workspace should survive between turns, between days, and between versions of the operating system.
The model will make mistakes. when it does, the sandbox shouldn’t hold anything that an attacker can use against it.
Agents spend most of their time waiting. An idle agent should cost almost nothing and wake up faster than a nt becomes more useful the more it remembers. Its workspace should survive between turns, between days, and between versions of the operating system.
35
12
83
4,561
Google's Ambient quality agent runs 24/7 in LOOP to monitor and fix AI agents in production.
It reads live traces.
Catches silent failures.
Points to the exact line of code to fix.
And it's 100% open-source.
GitHub: github.com/google/adk-rec…
It reads live traces.
Catches silent failures.
Points to the exact line of code to fix.
And it's 100% open-source.
GitHub: github.com/google/adk-rec…
75
34
320
17,477
Super cool and meditative 🧘♂️
this is just ~56 KB HTML file
one shotted with gemini 4 argon using antigravity
this is just ~56 KB HTML file
one shotted with gemini 4 argon using antigravity
39
10
216
13,296
Excaliflow just got multi-canvas tabs and auto-save.
You asked for it on X, so I shipped it.
Added this with Gemini 4 Argon in Antigravity in one session.
It's 100% open-source: github.com/Shubhamsaboo/a…
You asked for it on X, so I shipped it.
Added this with Gemini 4 Argon in Antigravity in one session.
It's 100% open-source: github.com/Shubhamsaboo/a…
This is NOW 100% open-source.
Built with Gemini 4 Argon in Antigravity (plus gemini 4 argon is now available for pro users).
GitHub Repo: github.com/Shubhamsaboo/a…
24
17
258
16,615
This is NOW 100% open-source.
Built with Gemini 4 Argon in Antigravity (plus gemini 4 argon is now available for pro users).
GitHub Repo: github.com/Shubhamsaboo/a…
Built with Gemini 4 Argon in Antigravity (plus gemini 4 argon is now available for pro users).
GitHub Repo: github.com/Shubhamsaboo/a…
40
52
626
72,863
Shubham Saboo retweeted
Gemini 4 Argon, Google's new frontier model is now available on Google Cloud. @SmithaKolan & @Saboo_Shubham_ walk through 10 of the most impressive demos built across Google, from legacy code migration to autonomous Android UI.
Watch the demos → goo.gle/47pqq6u
Watch the demos → goo.gle/47pqq6u
8
13
111
13,057
I wanted an animated Excalidraw so asked Gemini 4 Argon to buid one.
And damm it really cooked. Fully working!!
Will make it 100% open-source.
And damm it really cooked. Fully working!!
Will make it 100% open-source.
46
32
519
85,502
Star the repo to get the drop (plus 100+ open-source agent, skills and apps): github.com/Shubhamsaboo/a…
1
2
36
2,214
Google Gemini 4 Argon just went LIVE today.
10 INSANE things our team built with Gemini 4 Argon.
last one is my favourite.
10 INSANE things our team built with Gemini 4 Argon.
last one is my favourite.
24
12
148
16,094
Watch the full video on YouTube: youtube.com/watch?v=gRhM1h…
3
0
25
6,363
Gemini 4 Argon is now LIVE.
Here's how we are using Argon on our hardest engineering problems:
- Refactored a ~6M line legacy folder in Chrome in weeks
- Ran overnight on ADK and cut session prep time by 40%
- Made Gemma 4 inference 2.85x faster on vLLM
Try it out today and let us know what you think. x.com/sundarpichai/s…
Here's how we are using Argon on our hardest engineering problems:
- Refactored a ~6M line legacy folder in Chrome in weeks
- Ran overnight on ADK and cut session prep time by 40%
- Made Gemma 4 inference 2.85x faster on vLLM
Try it out today and let us know what you think. x.com/sundarpichai/s…
16
7
94
9,897








