Kilo (acq. by Anaconda)
@kilocode
Kilo is the all-in-one agentic engineering platform.
5M+ Kilo Coders. Open source since day one!
227 Following 29.2K Followers
The AI-doom debate is missing some context.
This piece digs into the technology behind the fears and the corporate politics that may be shaping the headlines. 👇
AI apocalypse before GTA VI?!
My first Substack post unpacks the AI-doom debate and what’s really behind the scary headlines.
Hint: probably more corporate politics than Terminator.
Show more
An AI agent told the user "I filed your bug" - but nothing was filed, and the test still passed.
@pandemicsyn wrote a hands-on guide to evals, the tests that catch this kind of thing in AI agents. You work through a small demo agent that fails on purpose, and you fix the checks until they can tell the difference between an agent that did the work and one that only said it did. His coding agent skill can walk you through it if you'd rather not read the whole post.
If your test can't tell those two apart, you don't know what your agent is doing.
Read more here:
Show more
This rooster is trying to tell you something about AI.
Hint:
1/ Four more Ori harnesses: @cline, @kilocode, #ohmypi#, and @Muse Code now run on OpenRouter.
$ ori cline
$ ori kilo
$ ori omp
$ ori muse
Two mathematicians spent a year on a $1m problem, and then OpenAI released proofs on the same day.
Tristan Buckmaster and Levent Alpöge ran every draft of their work through Codex sessions, and after news of their result reached OpenAI, the company produced a proof along the same narrow route within days.
Coincidence? Possibly.
Sovereign AI is a routing decision: if you control which providers see your work, you never have to ask a vendor for a straight answer. Learn more:
Show more
A trio of mathematicians solved a decades-old math problem using Codex.
OpenAI published a proof on the same day.
Coincidence or not - this opens an important discussion about ownership in the age of AI.
Show more
🚨 Ling-3.0-flash-Sante is now available FOR FREE in Kilo Code!
Shoutout to @novita_labs for serving it up. 💪
Sante is a finance-enhanced version of Ling-3.0-flash, developed with financial institutions and domain experts. Try it out and let us know what you think!
Show more
Today, we’re introducing Ling-3.0-flash-Sante — an MoE model enhanced for health and medicine, built on Ling-3.0-flash.
Inspired by the French word “santé,” meaning “health,” Sante is built for real-world healthcare tasks spanning medical reasoning, professional healthcare tasks, deep research, and evidence-based retrieval.
Sante shows competitive results across MedXpertQA-Text, DiagnosisArena-MCQ, AFUMED-Drug, HealthBench Professional, and BrowseComp, with leading performance among open-source models and results competitive with flagship models.
Here’s to better health — Santé! More below ↓
Show more
If the outages today proved one thing, it's why model freedom is important.
Anthropic, OpenAI, and xAI all suffered service disruptions on the same day. If your workflow depended on this small group of providers, today was a frustrating day.
If your AI model can be changed with two clicks, it was just another Thursday.
Show more
AI shouldn't be controlled by a technocracy in SF.
Open source hedges against that, and there's proof in the actions of closed-source tools and providers.
Read more here:
FABLE 5.1 IS WILD! This video is NOT a screen recording of
It's what happened when we pasted a screenshot of X into Kilo Code with Fable 5.1 and said:
"Recreate X (twitter). Use the screenshot for design, and implement all actual functionality."
One prompt, $13.00. All buttons work, and all the X functionality is there: reposts, quotes, polls, settings, suggestions, etc. 🤯
Show more
Qwen3.8-Max landed #4# on Arena's Frontend Code leaderboard — one spot above Claude Fable 5. We ran both on the same 10 UI design prompts, one shot each, to see how close that really is.
Show more
Kilo Code engineers write about 1% of code themselves.
The rest is written by agents, according to Kilo Co-Founder Emilie Schario, who recently spoke on a panel at @VentureBeat Transform 2026.
The rest of the discussion was even better. Brownfield vs greenfield, human-on-the-loop vs in-the-loop, and why "cost per PR" is replacing token spend as the metric that matters.
Watch the full clip:
Show more
Are we ready to call Grok 4.5 a frontier model?
Our experiments suggests that its performance is on par, and at 25x less cost.
Grok 4.5 doesn't just follow the plan — it fixes it (at only 4% of frontier cost).
Handed a plan with a bug, Grok reworked the design to solve it — unprompted.
Claude Opus 5 built the bug its own plan contained.
As an implementer, Grok gave up nothing to the frontier.
Show more
Congrats to the @enkryptai team for joining the @anacondainc family!
Security and governance have been the missing piece for enterprises trying to scale agentic dev, and pairing that with the Anaconda Platform (Kilo's parent company) closes a real gap: teams get to move fast without flying blind on risk.
Excited to see what this unlocks across the platform. 🔐
Show more
Today, Anaconda announced its acquisition of @enkryptai, the platform that finds and fixes the risks hidden within enterprise AI. 🔒
👑Nemotron 3 Ultra (@NVIDIAAI): 67% overall, 80% in knockouts — the sharpest knockout caller in the field. Nailed USA 1-4 Belgium, the only model to call it. 14-pick streak, 3 rare hits.
Show more
We looked at a full year of AI usage on @kilocode (July 2025 to July 2026) to see which lab held the top spot the longest.
@xai @SpaceXAI → LONGEST REIGN
13 straight weeks at # 1, no lab has held it longer. That streak was locked in even before Grok 4.5's benchmark gains had time to fully show up in usage.
Show more
🚨 BIG NEWS: Kilo Code has been acquired by Anaconda (@anacondainc)!
We've grown our agentic engineering platform from zero to a thriving open-source community of 3M developers in only 16 months.
Now, we're joining Anaconda's trusted foundation to cover the full AI-native dev lifecycle. 🐍💛
Read the full article below!
Show more
📍Are you in SF?
Come hang with Kilo DevRel @coldopn tomorrow (Tues, June 30). We're having an in-person event to kick off a free, week-long AI hackathon with @novita_labs!
We'll have pizza, a hands-on workshop, live demos, and a week to build your project for some fun prizes.
Doors at 6pm PT. Come build and network with us!
RSVP on the Luma below 👇
Show more
We gave Grok Build 0.1 one prompt: build a webhook delivery service in TypeScript, Bun, and SQLite.
It planned it, built it, and shipped a working demo.
Total cost: $1.65.
Zero tool-calling failures.
Here's exactly what happened, file by file.
Show more
