Head of Product & Engineering @kurrent_io, author of Hands-On Domain-Driven Design with .NET Core. Creator of https://xitter.cf/t.co/EPIgbC0WDQ. Views are my own.
Norway
Joined August 2010
- Tweets7.9K
- Following392
- Followers3.3K
- Likes4.1K
Conductor was nice. HumanLayer was a bit weird. Both gone now. Kcap stays under the radar for many because:
- all our engineers are in Europe and Mauritius, not SF and even not the US. so we "don't exist"
- we aren't very loud and we don't like bullshitting people. also, I don't have a mustache
- the one above also a bit frustrating because we are never happy with what we have and we want to provide more value
- we do a lot more that "orchestrating agents". that one thing alone delivers little value if you really think about Multiplayer AI. surprisingly, people are so willing to put everyone in a little box, and we don't fit
- we are currently invite-only, although invites are easy to get. just DM me.
Check kcap.ai, let me know what you think
I am very excited to share that Conductor is joining Meta!
We have some big, crazy plans for the next interface. If you liked Conductor, you’re gonna love what’s coming.
We’re super excited to work with @natfriedman and @alexandr_wang at MSL to build it. They’ve been on an absolute tear, and I’m convinced MSL has the highest talent density of all the labs.
A huge thank you to our earliest believers @aaron_epstein, @ilyasu, and @nabeel. And to everyone here who tried Conductor, sent us feedback, and prompt requests - you made this so much fun. Thank you ❤️🚂
Choo choo!
Hosted HumanLayer service shuts down in early December. DM me and I will give you an invite to kcap.ai. Local (limited), Cloud or Self-hosted - your agents, your rules.
HumanLayer's Multiplayer AI Manifesto didn't exist when we started building kcap.ai but we embrace the same principles. We are currently invite-only, but you can request one.
Today, @humanlayer_dev is joining Factory.
HumanLayer is a multiplayer coding agent IDE and cloud for running agents locally or in the background.
Together, with @dexhorthy and @0xblacklight we're building the future of software factories for entire engineering teams.
1
1
140
The bottleneck seems to be less PR review and a lot more CI time. Agents almost never delete tests but very happy to add more. My old server rack is worth running again with cloud compute prices going up. Plus, they can warm the house!
3
187
A new session gets the diff but not why it looks like that.
The context window is working memory, not storage. A resume surface has to carry the decisions and the ruled-out paths, or the next session re-tries what already failed.
What does yours hold that a diff doesn't?
tip for @humanlayer_dev on context engineering across sessions, compaction, and handing off to another human who will carry a session or task forward:
For sessions losing context on compact / new session, you should
1. make sure all context/decisions are into a doc in the artifacts (design, research, etc)
2. you can use a `/rpi:iterate-*` skill, e.g. `/rpi:iterate-design-discussion` to tell the agent in a new session to load context from artifacts
2b. You can also just @-mention the artifacts that matter in a new session
But the core approach is "offload all context to artifacts so resume / handoff is really easy" - nothing that matters should ever live ONLY in your context window
1
2
222
As kcap has a remote agent execution capabilities, we used it to add a review flow feature. Ask for an independent review and choose a harness, it spins up a fresh agent, receives a prompt from the implementer, then does the review and reports findings back. Unlike a sub agent, it won’t die at the end. It keeps the context to do consecutive rounds until it reports no findings. I use it all the time for code and specs.
@AnthropicAI session limit on Claude Max gone in an hour, is it new billing or what?
1
233
Can your agent reach out to the collective prior work of the team to find what's relevant and avoid re-exploring everything from scratch? Mine can, for real
149
Agent pipelines get pitched as factory lines: stamp a unit, ship, next one starts clean.
A codebase never resets. Every agent-shipped change is context for the next run. Good patterns get copied. So do bad ones.
Where does the factory metaphor break for agent code?
yes definitely and also when you make a part or a car out of a factory, the quality of any output does not impact quality of future outputs, but if you’re building a codebase, everything you “ship out the door” impacts your ability to/ agility to ship the next thing, or adapt what you’re shipping later
289
I don't really know how "local only" people deal with team knowledge. I was taking over AWS Marketplace stuff from a colleague who left the org. Two things would've made my job a lot harder: (1) previous work was done with Claude on a machine that's not mine (2) that session would've been evicted anyway. With kcap.ai I had no issues, just kept asking questions and got everything done within minutes using the prior art that probably took a lot of time and tokens to figure out.
That can be a good addition to the kcap eval catalogue kurrent.io/features#evals
200
Indeed this is what I personally noticed as engineering leader when we started adopting coding with agents. Collaboration shrank, teams were turning into groups of ICs, each "pairing" with Claude Code or Codex. Then I started building kcap and we begun dog fooding almost immediately. Context awareness of coding sessions increased dramatically. Everything is open by default, private is opt-in. kcap.ai
Fable is great but I still ask Codex to review what Claude Code+Fable produces. So, we added review flows to Capacitor, fully automated back and forth between Claude and Codex for independent reviews. Codex keeps its own context during multi-turn reviews. capacitor.kurrent.io/docs/us…
3
321
I got fed up that colleagues can't take over my Claude sessions, that people don't see how my sessions went and I can't see theirs. That I can't recall Claude session in Codex and get unstuck.
Get out of vendor lock. Allow collaboration. Get back to paid programming and get peers to know why things were done that way and not the other. A small experiment, 100% dog fooding, now open for private preview sign ups:
Kurrent Capacitor capacitor.kurrent.io. Free for now. GitHub only (no Enterprise yet). #ai #claude #codex
2
534
We are hiring an engineer for the Core Database team ats.rippling.com/en-GB/kurre… #csharp #dotnet #hiring
244
I wrote a blog post about new secondary indexes in @kurrent_io (ex @eventstore) work and why would you want to switch from category and event type streams to indexes instead kurrent.io/blog/secondary-in…
Finally, people won't need category and event type projections in #kurrentdb. We are replacing those with indexes! Up to 80% less disk space and almost ten fold faster reads. #eventsourcing #eventstore docs.kurrent.io/server/v25.1…
4
430