Cline released Cline Desktop, an early open-source Mac app for running open-weight models that brings the company's agent harness to a dedicated workspace with parallel sessions, scheduled tasks, and …
Cline migrated its VS Code extension, used by over 11 million developers, to the new Cline SDK, a move that reduced agent failures by 10x after an initial failed attempt forced a safer rollout strateg…
Cline migrated its VS Code extension, installed by over 11 million developers, to the new Cline SDK, replacing a ~76,000-line monolithic core with a modular runtime. The company reports that the refac…
DeepSeek V4 Flash scored 30/42 on IMO 2026 problems in Cline, clearing the 29-point gold medal cutoff for just $0.12, roughly 140 times cheaper than Claude Fable 5. The benchmark, run by Cline, tested…
Cline, an AI coding assistant, is open-sourcing its evaluation framework for open-weight coding agents, revealing that its requests run 20–30% heavier on tokens than the most efficient harnesses. The …
NVIDIA released Nemotron 3.5 Lightning, a 30B mixture-of-experts model with 3B active parameters, now available in Cline, an AI coding assistant. The model, distilled from NVIDIA's Nemotron 3 Ultra, s…
Moonshot AI released Kimi K3 in July 2026 as a 2.8T-parameter open-weight MoE model with a 1M token context window and native vision support, scoring 88.3 on Terminal-Bench 2.1, close to top closed mo…
Cline achieved an 88.8% SOTA score on Terminal-Bench 2.1 using recursive self-improvement with GPT-5.6-Sol as the leader model, costing $49.80—less than a tenth of Fable 5's $552 run. The single-promp…
Self-hosting open-weight large language models can save millions of dollars compared to using inference providers, according to a practical guide by Cline that analyzes the economics using Kimi K2.6 a…
Cline launched ClinePass, a low-cost monthly subscription pairing its agent harness with curated open-weight models and higher API rate limits, as the performance gap between frontier and open-weight …