@rywalker

CEO @Tembo • prev founder @Astronomerio

rywalker.com
Joined May 2008
  • Tweets8.5K
  • Following1.9K
  • Followers12.1K
507Media
ry retweeted
ry
@rywalker12h
In 2027 many engineers won't be in an IDE or even a coding agent (directly). They'll run an org of agents, and operate more as a manager. Here's the starter org tree I'd set up...
8
1
13
890
Replying to @rywalker
the tembo team is cooking!
1
2
121
ry retweeted
ry
@rywalkerOct 23
Anyone working on a product like Grok Bot?
88
4
1
206
32,183
ry retweeted
Tembo
@tembo13h
New in Tembo ✨ • Stacked pull requests in Tembo Review • Export any cloud session transcript as Markdown or JSON • Find any session with search qualifiers • The web + desktop app is now up to 2x faster Read the full changelog ↓ tembo.io/changelog#oct-23-20…

Tembo - Run any coding agent in the cloud

Give every change its own computer. Follow agent work, review the result, and see what gets merged with Tembo Insights.

tembo.io
1
1
2
9
1,077
ry retweeted
darren
@darrenjr16h
btw this is by far the best coding agent integration for jira right now and its not even close
Tembo
@tembo17h
Tembo now replies as Tembo in Jira. Connect an Atlassian service account, and comments and updates come from Tembo's own user, not whoever installed the integration. Setup → docs.tembo.io/integrations/j…
A Jira ticket where a teammate asks @Tembo to pick it up, and Tembo replies from its own account that it opened a pull request.

ALT A Jira ticket where a teammate asks @Tembo to pick it up, and Tembo replies from its own account that it opened a pull request.

1
2
8
477
ry retweeted
ry
@rywalkerOct 22
defensive ai is going to be big in 2027 needs to be big now wrote these last Dec: rywalker.com/agentic-defense… and rywalker.com/let-agents-figh… tldr; start spending as many tokens on defense as you do on offense (where offense = code gen)

Agentic Defense: The Missing Half of the Equation

For every unit of AI firepower aimed at building, deploy equal or greater firepower at securing, debugging, and testing. Here is what that looks like.

rywalker.com
2
2
22
1,296
Cloud & Async Agents ▫️ Codegen @codegen ▫️ Cognition @cognition ▫️ Cosine @CosineAI ▫️ Factory @FactoryAI ▫️ Jules @GoogleLabs ▫️ OpenHands @allhands_ai ▫️ Tembo @tembo
1
1
3
148
one thing you don't realize until you try cloud agents is how much battery life you get back i run pretty much everything through tembo now, and my macbook lasts so much longer because all the heavy lifting happens in the cloud such an underrated benefit
2
1
11
992
ry retweeted
ry
@rywalkerOct 11
it can be true that a group of early adopter “regular people” are rolling their own personal software…. and there is still opportunity to build and sell great software mid software would seem to be at risk, but i can’t imagine a u-shaped distribution of software quality… too many ppl building, for there not to be a preponderance of mid
3
1
7
917
ry retweeted
Tembo
@temboOct 9
New in Tembo ✨ - Agent instruction version history: see past versions and roll back to a setup that worked - Browser push notifications for approvals, new PRs, and review requests - Claude Haiku 5.5 - GitLab MR follow-ups now stay in the same conversation Read the full changelog ↓ tembo.io/changelog/agent-ins…

Tembo - Run any coding agent in the cloud

Give every change its own computer. Follow agent work, review the result, and see what gets merged with Tembo Insights.

tembo.io
1
2
1
18
1,537
Replying to @thomaspark_gg
@tembo works with claude + codex + supergrok subs runs any harness you want! claude code, codex, opencode, cursor etc bring a sub and only pay for some of the cheapest vm compute out there
1
2
14
360
ry retweeted
Tembo
@temboOct 5
The fx.sh coding agent by @vercel is now available as a harness in Tembo! Supports all anthropic, openai, and most major open source models.
darren
@darrenjrOct 5
fx.sh v0.0.13 by @vercel running in a @tembo vm! with fully native steering + queuing and mcp support it is super fast!
3
1
4
26
2,151
Replying to @kamathematic @cursor_ai
let me introduce you to @tembo
1
2
9
485
ry retweeted
ry
@rywalkerSep 6
Bring your openai and grok subscriptions to @tembo cloud agents
Silvestro
@zilvestroSep 6
Best Cursor Cloud Agent alternative? Ideally where I can bring my own AI subscriptions
4
1
24
3,131
Replying to @zilvestro
come try @tembo some of the cheapest VMs out there + works with your existing codex sub!
1
16
685
ry retweeted
ry
@rywalkerSep 4
something for the CPU to do, while waiting on LLM responses :)
darren
@darrenjrSep 4
i can play minecraft in 60fps while waiting for my cloud agents to finish
1
1
5
876
btw you can use this to connect to your local machine from tembo’s cloud VMs the locally running agent loop is so dead
Tembo
@temboAug 25
Tembo now supports @Tailscale. Give Tembo VMs and MCP servers scoped access to devices on your tailnet. docs.tembo.io/integrations/t…

Tailscale - Tembo Docs

Connect Tembo sandbox sessions to your private network (tailnet) with on-demand, single-use ephemeral keys.

docs.tembo.io
1
9
835
ry retweeted
Tembo
@temboAug 25
Tembo now supports @Tailscale. Give Tembo VMs and MCP servers scoped access to devices on your tailnet. docs.tembo.io/integrations/t…

Tailscale - Tembo Docs

Connect Tembo sandbox sessions to your private network (tailnet) with on-demand, single-use ephemeral keys.

docs.tembo.io
4
2
16
3,698
Giving a cloud sandbox end-to-end access is the closest thing to AGI I've seen. It can SSH into your machines, read logs, access AWS, query the database, fix and iterate on its own. You stop being the bottleneck and start being the reviewer. Now do this a dozen times in parallel.
2
1
6
340
Everyone's fighting over who has the fastest cloud sandbox start times. The truth is VM start time is irrelevant. Have the VM already running before anyone needs it. Cold starts are a solved problem when you pre-warm.
1
1
1
7
899
Load more