Pavitra Bhalla

252 posts

Pavitra Bhalla banner
Pavitra Bhalla

Pavitra Bhalla

@pavitrabhalla

Founder @superserve_ai. Building composable cloud computers for agents

شامل ہوئے Temmuz 2010
431 فالونگ194 فالوورز
fks
fks@FredKSchott·
@pavitrabhalla @flueai Same! check the GitHub issues, there was a reason it had to be pulled, can’t remember off top of my head
English
1
0
0
158
fks
fks@FredKSchott·
npm downloads for @flueai
fks tweet media
English
5
3
95
14.3K
Pavitra Bhalla
Pavitra Bhalla@pavitrabhalla·
Persistent sandboxes + Versioned filesystems Our partnership with Mesa brings us one step closer to making Superserve a natural compute substrate for long-running background agents. It's been amazing to work with @olvrgln and the team @mesa_dot_dev.
Mesa@mesa_dot_dev

Sandboxes don't need to be ephemeral anymore. Today we're announcing our partnership with @superserve_ai to bring your agents lightning-fast sandboxes with persistent, versioned, state built in.

English
0
0
3
85
Pavitra Bhalla ری ٹویٹ کیا
Oliver
Oliver@olvrgln·
Agents need state. Most compute is stateless. It is inevitable that most compute providers start offering persistent, versioned filesystems built in. It's been great working with @pavitrabhalla and the @superserve_ai team to bring Mesa to their sandboxes
Mesa@mesa_dot_dev

Sandboxes don't need to be ephemeral anymore. Today we're announcing our partnership with @superserve_ai to bring your agents lightning-fast sandboxes with persistent, versioned, state built in.

English
0
1
14
1.7K
Supriya Kashyap
Supriya Kashyap@Supriyaa27·
@Cursor built a $4B ARR by being the best orchestration layer for code: composer, agent loops, multi-file context. But its models were borrowed and now with the $60B @SpaceX acquisition, they break that dependency. Lesson I am taking: Great UX + orchestration can take you surprisingly far on the borrowed inference. But at the frontier, you eventually have to own your compute stack. The merging of Cursor's application layer with the Colossus infrastructure is an example of how the app layer and compute layer are collapsing into each other.
English
1
0
1
62
Nous Research
Nous Research@NousResearch·
In partnership with @stripe, Hermes Agent now supports a full suite of Stripe skills. Your agent can buy things, pay per-call APIs, and provision its own SaaS, with configurable safety limits on every action.
Nous Research tweet media
English
197
364
4.7K
431K
Nick Launches
Nick Launches@nicklaunches·
Free traffic thread. What are you working on this week 👇
English
125
1
61
13.4K
Pavitra Bhalla
Pavitra Bhalla@pavitrabhalla·
@jhleath @acoyfellow @ankrgyl Superserve already does this with native pause and resume backed by full-memory snapshots. Is there something I'm missing here? #pause" target="_blank" rel="nofollow noopener">docs.superserve.ai/sandbox/lifecy…
English
1
0
0
53
Hunter Leath
Hunter Leath@jhleath·
@acoyfellow @ankrgyl whoever lets me start a sandbox but only bills me when it’s actively doing work, which might be… Vercel?
English
3
0
1
99
Ankur Goyal
Ankur Goyal@ankrgyl·
sandboxes are the convergence of servers and serverless
English
11
2
56
14.5K
Pavitra Bhalla
Pavitra Bhalla@pavitrabhalla·
@sidpalas Agreed! Our sbx.pause() takes a full memory snapshot and restores from it in under 500ms
English
0
0
0
33
Sid Palas
Sid Palas@sidpalas·
@pavitrabhalla Nice -- `sbx.pause()` is key for keeping costs low in this use case
English
1
0
0
67
chronark
chronark@chronark·
Why does it matter if sandboxes start up in 0.0001 nanoseconds if I then spend the next 20s downloading the git repo?
English
49
4
733
256.4K
Superserve
Superserve@superserve_ai·
We're excited to announce that we have partnered with @AnthropicAI to integrate Superserve sandboxes with Claude Managed Agents. Thanks @phaser_, @getlindy, @mesa_dot_dev, and sprag.ai for sharing your story with us! Integration guide and recipes linked in 🧵
ClaudeDevs@ClaudeDevs

Claude Managed Agents can operate in a sandbox you control, on your own infrastructure or with any provider you choose. Today we added new guides for @blaxelAI, @e2b, @googlecloud, @namespacelabs, and @superserve_ai, so you can choose the best fit for your use case.

English
10
8
32
7K