Kimi.ai

🥝 Meet Kimi K2.5, Open-Source Visual Agentic Intelligence. 🔹 Global SOTA on Agentic Benchmarks: HLE full set (50.2%), BrowseComp (74.9%) 🔹 Open-source SOTA on Vision and Coding: MMMU Pro (78.5%), VideoMMMU (86.6%), SWE-bench Verified (76.8%) 🔹 Code with Taste: turn chats, images & videos into aesthetic websites with expressive motion. 🔹 Agent Swarm (Beta): self-directed agents working in parallel, at scale. Up to 100 sub-agents, 1,500 tool calls, 4.5× faster compared with single-agent setup. - 🥝 K2.5 is now live on kimi.com in chat mode and agent mode. 🥝 K2.5 Agent Swarm in beta for high-tier users. 🥝 For production-grade coding, you can pair K2.5 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blogs/kimi-k2-… 🔗 Weights & code: huggingface.co/moonshotai/Kim…

Per Moonshot AI CEO Zhilin Yang at GTC today, this is the "most beautiful image" he's ever seen. 📉 Made possible by NVIDIA H800 clusters. ✨ arxiv.org/abs/2507.20534

📎We've uploaded it to arXiv, enjoy! arxiv.org/abs/2603.15031

Thanks for the reminder 🕚

@_avichawla Impressive work from Kimi

For more details, check out our paper here: github.com/MoonshotAI/Att…

Analysis of training dynamics demonstrates how AttnRes naturally mitigates hidden-state magnitude growth and yields a more uniform gradient distribution across depth.

Introducing 𝑨𝒕𝒕𝒆𝒏𝒕𝒊𝒐𝒏 𝑹𝒆𝒔𝒊𝒅𝒖𝒂𝒍𝒔: Rethinking depth-wise aggregation. Residual connections have long relied on fixed, uniform accumulation. Inspired by the duality of time and depth, we introduce Attention Residuals, replacing standard depth-wise recurrence with learned, input-dependent attention over preceding layers. 🔹 Enables networks to selectively retrieve past representations, naturally mitigating dilution and hidden-state growth. 🔹 Introduces Block AttnRes, partitioning layers into compressed blocks to make cross-layer attention practical at scale. 🔹 Serves as an efficient drop-in replacement, demonstrating a 1.25x compute advantage with negligible (<2%) inference latency overhead. 🔹 Validated on the Kimi Linear architecture (48B total, 3B activated parameters), delivering consistent downstream performance gains. 🔗Full report: github.com/MoonshotAI/Att…

🤗

See you at #NVIDIAGTC 2026!

Kimi K2.5 continues to be my daily driver for all the basic stuff where I don't need PhD-level intelligence. I just need it done quickly. Running it at 200 tps through @FireworksAI_HQ within @opencode is just such a delight.

Tried many AI models with OpenClaw, I found Kimi AI to be the most token efficient, good at coding, also the easiest to set up.

Kimi is in the Top 50 Gen AI Web Products. Keep building, keep shipping.💪

🎁 We've added a limited-time top-up reward to help you get the most out of @openclaw. Grab some bonus vouchers and keep exploring. 🔹20% bonus for $100 – $299 🔹30% bonus for $300 – $999 🔹40% bonus for $1,000+ Ends Mar 8. 🔹Details:🔗platform.moonshot.ai/docs/promotion

🌖 New Kimi Doodle drop: The Dark Side of the Moon's 53rd anniversary Go drop the needle and spin it! Fun fact: Kimi was actually founded on the album's 50th anniversary 🎵 Check it out 👉 kimi.com

> Try it now at: kimi.com/code

Good news: the Kimi Code 3X Quota Boost is here to stay. No expiration. No catch. Just 3 times the power, permanently. From quick fixes to full-scale production, there's a plan for every need. Go build something amazing.

Happy Shipping. 🪄

High performance and low cost are all you need.