Kilo Code Blog
blog.kilo.ai · Company blog · on HN since 2025
The blog of Kilo Code, an open source AI coding agent, with model benchmarks, product news, and commentary on AI coding tools.
What HN saysHN commenters link it for head-to-head model comparisons, such as DeepSeek V4 against Opus 4.7, and for its post on Claude possibly distilling Qwen.
21HN people shared it
5linked it in comments
31stories submitted
59story points
2 months agolast shared
2025people per year2026
Most-shared posts
- 1Open-Weight Models Are Getting Serious: GLM 4.7 vs. MiniMax M2.13 people · 5 points · first shared 2026 · 1 comments on HN
- 2Was Cline just acqui-hired by OpenAI?2 people · 15 points · first shared 2026 · discussion on HN
- 3We Gave Claude Opus 4.7 and Kimi K2.6 the Same Workflow Orchestration Spec2 people · 3 points · first shared 2026 · discussion on HN
- 4We Tested DeepSeek V4 Pro and Flash Against Claude Opus 4.7 and Kimi K2.62 people · 2 points · first shared 2026 · 1 comments on HN
- 5Kilo Code, fastest growing open source coding agent, raised $8M seed2 people · 2 points · first shared 2025 · discussion on HN
- 6Did Claude Opus 4.8 distill Alibaba's Qwen? Here's what the evidence says2 people · 2 points · first shared 2026 · discussion on HN
- 7The Minimum Every Developer Must Know About AI Models (No Excuses)1 people · 4 points · first shared 2025 · discussion on HN
- 8Benchmarking GPT-5.1 vs. Gemini 3.0 vs. Opus 4.5 across 3 Coding Tasks1 people · 3 points · first shared 2025 · discussion on HN
- 9Claude Fable 5 vs. GPT-5.5: Better Planning, Similar Execution1 people · 2 points · first shared 2026 · discussion on HN
- 10We Wasted 4 Weeks on a $1k/Month AI Agent1 people · 2 points · first shared 2026 · discussion on HN
- 11Stop Looking for AI Coding Spending Caps1 people · 2 points · first shared 2025 · discussion on HN
- 12The GitHub Copilot Bill Came Due. Here's What Engineering Leaders Should Do1 people · 2 points · first shared 2026 · 1 comments on HN
- 13Let's build the best open-source autocomplete, together1 people · 2 points · first shared 2025 · discussion on HN
- 14Next-Edit in Kilo, Powered by Inception Diffusion LLMs1 people · 2 points · first shared 2026 · discussion on HN
- 15Congratulations Cursor on being acquired by SpaceX1 people · 2 points · first shared 2026 · discussion on HN
What HN people wrote when they linked it
DeathArrow · 2026-05-19
>Starting from zero today, how would someone quickly get upto speed with the latest and greatest AI tooling on an extremely limited budget?
Z.AI, Moonshot.AI, Xiaomi, Minimax, Alibaba all have coding plans that allows a massive usage of GLM 5.1, Kimi k2.6, Minimax M2.7, Qwen 3.6 Plus, Xiaomi MiMo v2.5 Pro for cheap.
Pair those coding plans with the harness of choice including Claude Code and you are good to go.
Also, Nvidia is offering free access to top models for free through NIM - but you have 40 RPM limits. https://blog.kilo.ai/p/nvidia-nim-kilo-code-free-kimi-k25
qprofyeh · 2026-04-22
More technical introduction worth reading: https://blog.kilo.ai/p/the-elephant-is-out-of-the-bag-meet
owendarko · 2025-12-14
What a lot of people don’t mention here is the choice of an AI model.
The key word in the OP post is “Claude”. Anthropic has 2 amazing AI models (Sonnet, Opus), however they’re just a part of a much bigger picture.
When using AI for programming, you’re essentially interacting with AI models. The quality of output you get really depends on the model at the end of the day. Claude Code is optimized for models from Anthropic. You also have model-agnostic agents like Cursor and Kilo Code (disclaimer: I work at Kilo) where you can easily switch up models and see which one works the best for you converting an old jQuery + Django project into SvelteKit.
This area is moving at a crazy rate. Just the last 2 weeks alone, there were 3 main AI model versions released (first Gemini 3, then Opus 4.5, then GPT-5.2). I wrote a piece comparing their performance across 3 coding tasks [1]
So my advice is to also experiment a lot with the models because the quality can vary wildly depending on your stack.
[1] https://blog.kilo.ai/p/we-tested-gpt-52pro-vs-opus-45-vs
c0rruptbytes · 2026-06-22
https://blog.kilo.ai/p/did-claude-opus-48-distill-alibabas
it happens to all models…when the internet is increasingly generated, things happen
nl · 2026-05-15
Kilo (the open source coding agent) tested Deepseek v4 Pro and Flash vs Opus 4.7 and Kimi K2[1].
It did ok, but scored substantially less than Opus. It also cost nearly as much, even with the current launch promo pricing for Deepseek.
That cost is interesting - I've seen similar things with Sonnet vs Opus, and in my own benchmarking there are some models that benchmark well, seem to have a good price but use so many tokens they cost just as much as "more expensive" models.
[1] https://blog.kilo.ai/p/we-tested-deepseek-v4-pro-and-flash