Jacob @jakecodes

Building Kai https://t.co/7FFToZ1tWo howth.run Philadelphia Joined December 2015

Tweets

2K
Followers

3K
Following

814
Likes

7K

Jacob @jakecodes

a month ago

I wrote down where the future of Git is headed and why we're building better for the AI era. 🔗 kaicontext.com/blog/why-git-i…

0 0 1 71 0

View Details

Adam Tal 🚀 @TalAdam

a month ago

I went through every Hacker News "Who is Hiring?" thread since 2019. 83 months. 109,462 listings. A few things stood out 🧵

1 4 10 866 4

View Details

Jacob @jakecodes

a month ago

Git-only teammates see a normal log and their commits flow back into Kai. No disruption. [2/2] #devtools #git

0 0 0 41 0

View Details

In the next version of Kai: Kai–Git bridge makes transitions painless: Kai users keep capturing semantic snapshots and assertions; the bridge writes tidy git commits with Kai evidence in commit trailers.[1/2]

1 0 1 110 0

View Details

Jacob @jakecodes

2 months ago

Shipped 19 releases this week. Kai now has Rust support, 4.4x faster capture, and auto AI authorship detection. v0.9.67: github.com/kaicontext/kai…

0 0 1 76 0

View Details

Jacob @jakecodes

2 months ago

Kai capture just went from 9.2s to 2.1s on a 64K file repo. Replaced JSON zero heap allocations on read. The same approach git uses for its index, adapted for Go. v0.9.58: github.com/kaicontext/kai…

0 0 0 69 0

View Details

Jacob @jakecodes

2 months ago

Kai Weekly #2 — Three Big Changes Built-in Docker registry GCP fully removed (all self-hosted) New, sexier homepage Full write-up: kaicontext.com/kai/weekly/sna… → kaicontext.com

0 0 1 79 0

View Details

Jacob @jakecodes

2 months ago

Shipped 10 releases for Kai this week (v0.9.14→0.9.23). Now: • capture/push = change-aware (not O(all files)) • CI skips unaffected work • tracks AI vs human code You + AI can actually understand your codebase. github.com/kaicontext/kai…

0 0 1 85 0

View Details

Jacob @jakecodes

2 months ago

Next version of Kai: Created a pull-through cache on Artifact Registry, one command, zero Dockerfile changes. First pull hits Docker Hub, everything after is cached.

0 0 1 101 1

View Details

Jacob @jakecodes

2 months ago

In this version of Kai: We open-sourced Kai Server! Also shipped a CI system that deploys itself — all in one week. Kai CI builds and deploys Kai. Hosted: kaicontext.com github.com/kaicontext/kai…

0 0 1 134 0

View Details

Jacob @jakecodes

2 months ago

This release gives you Kai grep. Now I use Kai grep instead of Claude code grep Yesterday, I had Claude refactor. A standard text search made it look safe. But Kai grep flagged a hard dependency in another module. I would have shipped a production bug. github.com/kailayerhq/kai

0 0 2 203 1

View Details

Jacob @jakecodes

3 months ago

@TalAdam incredible! We're in the process of releasing kai server open source today

0 0 0 31 0

View Details

Jacob @jakecodes

3 months ago

Super excited because in a few seconds Kai will be deployed by Kai. Once this is done, Kai Server will be open sourced, and you can do this too on your own hardware or cloud. Your agents will be so happy.

1 0 1 111 0

View Details

Jacob @jakecodes

3 months ago

A few pilot teams told me the same thing after using Kai: “This gives me peace of mind shipping AI-generated code.” AI can generate changes faster than humans can review. Kai gives both the developer and the AI agent a shared understanding of the repo. github.com/kailayerhq/kai

0 0 1 248 2

View Details

Jacob @jakecodes

3 months ago

@_brian_johnson That's so cool! It'd be cool to have that in kai directly, maybe you'd like to contribute.

1 0 0 75 0

View Details

Jacob @jakecodes

3 months ago

Claude Code: 100k tokens, 20 min for my refactor. With Kai: 20k tokens, 2 min. Semantic infrastructure for AI agents. Call graphs, dependencies, impact analysis — structured, not grepped. claude mcp add kai -- npx -y kai-mcp Open source: github.com/kailayerhq/kai

1 0 0 176 2

View Details

Jacob @jakecodes

3 months ago

@mipsytipsy @boristane Testing is the most interesting stage to watch. We’re already asking agents to write tests. The question shifts from “can it generate?” to “how do we validate confidently?” Observability closes the loop after deploy. The next frontier is tightening the loop before it.

0 0 1 112 0

View Details

Jacob @jakecodes

3 months ago

Hours of coding made 10-minute CI feel free. Feedback loop? Not your problem. Agent does it in 5 minutes. Now CI is the feedback loop. Nothing changed in your pipeline. Everything changed in your baseline.