Cline
Cline hits 11,840 tokens per second on one GPU with Nemotron 3.5 Super VL
Cline says it reached 11,840 aggregate output tokens per second on a single GB300 running NVIDIA's Nemotron 3.5 Super VL with 256 concurrent requests. The team published…
Cline adds Jev decision models for fast, cheap agent guardrails and browsing
Cline has built three plugins around Jev, a Decisions model from TypeSafe AI that classifies a given state instead of generating tokens. According to Cline, Jev is…
Vercel's HarnessAgent now accepts image inputs across all harness adapters
Vercel's AI SDK HarnessAgent layer now accepts image inputs across every harness adapter. Developers can pass images together with text using the standard AI SDK message…
Cline harness lifts NVIDIA Nemotron 3.5 Super VL to 61.8% on Terminal-Bench 2.1
Cline reports that NVIDIA's Nemotron 3.5 Super VL scored 61.8% on Terminal-Bench 2.1 when run through the Cline agent harness with thinking mode turned off. According to…