Kimi

Moonshot open-sourced Kimi K2.7 Code and says it outperforms K2.6 by 21.8% on Kimi Code Bench v2 while using 30% fewer reasoning tokens. The release includes open weights and API access, so teams can test the 180 tok/s HighSpeed rollout and early Cline/OpenCode support.

Kimi Work launched for macOS and Windows with up to 300 local agents, WebBridge browser control, finance data tools, and a memory system. It matters because the app bundles multi-agent desktop automation locally instead of routing the workflow through a hosted IDE.

Kimi released Web Bridge, a browser extension that lets agents search, scroll, click, type, and save repeatable skills across websites. The bridge works with Kimi Code CLI plus Claude Code, Cursor, Codex, Hermes, and other agents.

A day after Kimi K2.6’s launch, providers and tools opened new access paths including temporary free use in Hermes and Cline plus availability on Replicate, Together, Perplexity, and Tinker. Engineers can test the open model across agent harnesses and hosted runtimes without standing up their own stack first.

Moonshot open-sourced Kimi K2.6, a 1T-parameter MoE with 32B active parameters, 256K context, multimodal input, and larger agent swarms. It now sits near frontier closed models for long-horizon coding and tool use, so teams can try it for agent workflows.

Kimi K2.6 shipped across vLLM, SGLang, OpenRouter, Baseten, Ollama, OpenCode, Hermes Agent, and Droid within hours of launch. That cuts the usual lag between model release and production trials, so mixed-provider agent stacks can test it sooner.

Moonshot says its Prefill-as-a-Service setup makes prefill/decode disaggregation practical across datacenters and mixed hardware by shrinking KV cache with Kimi Linear. The paper reports 1.54x throughput and a 64% drop in P90 time-to-first-token, so benchmark the approach before planning production adoption.