Kilo (acq. by Anaconda)
@kilocode
Kilo is the all-in-one agentic engineering platform.
5M+ Kilo Coders. Open source since day one!
229 Following 29.3K Followers
Who's going to make the first Kilo-bot with Xiaomi's robotics model?? 🤖
Xiaomi-Robotics-1 is taking on new challenges in real-world environments!
With multi-round post-training and an enhanced Agent framework, the embodied AI system powered by Xiaomi-Robotics-1 has started trial operations at Xiaomi Youth Apartments.
In a 30-minute run, it completed 50+ task chains across 3 rooms, showcasing its ability to handle a range of tasks in a real-world environment.
Xiaomi-Robotics-1 has also received the Leading Science and Technology Award at the World Internet Conference.
#XiaomiRobotics# #EmbodiedAI#
Show more
In the ’70s, a campus prank could scatter your code across the floor.
Today, your AI provider can upend your workflow with a pricing change.
From punched cards to tokens: a story from Colombia 50 years ago is still relevant today:
Show more
Props to @MistralAI for the open-weights release of LE CHONK!
Use it in our new Kilo Desktop app today:
Today, we release the weights of a new and improved Le Chonk, advancing the open frontier for agentic coding and cybersecurity.
💻 Built to build: Le Chonk ranks #1# on @cognition’s FrontierCode among open models, and sets a new benchmark for Pareto efficiency on @artificialanalysis.
🛡 Built to defend: State-of-the-art in cyberdefense, put through the paces by the world's leading cyber vendors, including @CrowdStrike, @cloudflare, @rubrik, @zscaler, and others.
Built for sovereignty: Make it yours. Download the weights on @huggingface , customize it with Mistral Forge, and deploy it wherever you need it.
Read more from our team and customers 👇:
Show more
GMI is now a built in provider in @kilocode
use 300+ models from GMI on Kilo Code without any setup
Cursor is cutting off other models. Kilo was designed around model freedom.
Paying for Cursor? Kilo Enterprise is free for the rest of your Cursor contract, up to a year.
OpenAI models leave Cursor on November 12. Kilo connects to your ChatGPT plan, so your team keeps GPT, with 500+ other models beside it.
Claim the offer below 👇
Show more
"Which model is best?" is the wrong question.
Ask which model is best for this task:
→ Nemotron 3 Ultra plans
→ Nemotron 3.5 Super VL builds and reads screenshots
→ Nemotron 3.5 Lightning runs the small jobs fast
An early build of @NVIDIAAI Nemotron 3.5 Super VL scored 53% on KiloBench, the same as GLM 5.2.
Try it here:
Show more
Kilo is supporting All Day AI on October 22 by giving 5 people $1,000 in Kilo credits.
The event is 15 hours, and has 122 speakers from Microsoft, NVIDIA, OpenRouter, and more. Free, online, and no vendor pitches.
Register and share the event by October 15 to qualify for the credit giveaway!
Show more
Sign in with ChatGPT is available in Kilo NOW.
Use your ChatGPT credentials to sign in or create a new Kilo account, and use your ChatGPT plans to power AI coding across all Kilo surfaces!
BIG NEWS - Sign in with ChatGPT plan usage is now also available to all customers on the ChatGPT Go plan. That is - Customers on Go, Plus and Pro plans can now login to all commercial launch partner apps + open source applications and take their ChatGPT plan usage with them. So much more goodness is yet to come!
Show more
@StepFun_ai just announced Step 5 Preview, and it's FREE in Kilo for a week:
• 600B parameters, 27B active per token
• 1M-token context + vision
• highlights: strong coding and finance performance at lower cost.
Try it and let us know what you think!
Show more
Ling 3.1 flash is here, and it's completely FREE in Kilo Code until October 13th!
Shoutout to @novita_labs for serving it up!
Kilo showed up at two Builders & Brews events last Friday: @jobrietbergen spoke in Amsterdam, @coldopn spoke in NYC.
Builders & Brews is a running series from Nebius and Tavily, part of the Nebius x NVIDIA online hackathon, with solid prizes on the line.
Great to see so many partners from the ecosystem showing up: @jetbrains @LangChain @nebiusai @tavilyai
Builders can use @nebius Token Factory inference inside Kilo.
Show more
Fun times at Builders & Brews in Amsterdam and NYC, with @kilocode @jetbrains @LangChain @nebiusai @tavilyai
Builders & Brews is a running series from Nebius and Tavily, and is a part of the Nebius x NVIDIA online hackathon.
Time to build!
Show more
Most engineers can probably skip this week's AI launches and lose nothing.
A new letter on the Kilo blog argues that testing tools against one slow part of your actual work teaches more than tracking which model tops the leaderboard.
Full post:
Show more
Grok 4.7 versus Opus 5.5 on touching-grass-simulator in Kilo Code 👇
Grok's one-shot result ran 47% cheaper - which version do you prefer?
Both new models are available TODAY in Kilo!
Everyone says I need to touch grass - but I think Grok 4.7 does it best?
I compared Grok 4.7 against Opus 5.5 on a grass-touching simulator in @kilocode.
Grok's price: $3.52
Opus 5.5's Price: $7.35
Show more
🚨 OpenAI was breached by a model upgrade, not a new bug.
Hacktron spent hours failing to exploit a known flaw in an old image library. Claude Opus 5 shipped and they had a working exploit of OpenAI in 3 hours.
This is proof that you can't afford model lock-in when the frontier changes every day.
Read more:
Show more
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
