Cline Releases Cline SDK: An Open-Source Agent Runtime Now Powering Its CLI and Kanban, With IDE Extensions Being Migrated
Cline has released its new open-source TypeScript SDK, which serves as an agent runtime for its applications. The SDK achieved a 74.2% score on claude-opus-4.7 in Terminal Benchmark 2.0, outperforming Anthropic’s Claude Code.
Cline has launched a new open-source TypeScript SDK, now powering its CLI and Kanban tools. This SDK is structured into four layers: @cline/shared, @cline/llms, @cline/agents, and @cline/core. It offers native support for plugins, subagents, CRON scheduling, checkpointing, and MCP connectors.
The SDK serves as an agent runtime, which was previously an internal component. Its release as an open-source tool allows for broader adoption and integration.
In performance testing, the Cline CLI, utilizing this SDK, scored 74.2% on claude-opus-4.7 in Terminal Benchmark 2.0. This score surpasses Anthropic's published 69.4% for Claude Code on the same model.
Installation requires Node.js 22+ and can be done via npm install @cline/sdk. IDE extensions for VS Code and JetBrains are currently being migrated to utilize this new SDK.
Related articles
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
CUGA, IBM's open-source Agent Harness, simplifies building agentic applications by handling infrastructure, allowing developers to focus on tools and prompts. It offers pre-assembled components for planning, execution, and state management, significantly reducing development time. CUGA has topped agent benchmarks like AppWorld and WebArena.
OpenAI launches new initiative to help find and patch open source bugs
OpenAI has launched "Patch the Planet," a new initiative in partnership with cybersecurity firm Trail of Bits, to enhance the security of open-source projects. This program aims to assist maintainers in identifying and patching bugs, utilizing OpenAI's AI-powered security tools while reducing the burden on project teams.
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
Baidu has released PP-OCRv6, an advanced optical character recognition (OCR) model supporting 50 languages. Available on Hugging Face, this version significantly improves accuracy and efficiency across various parameter sizes, from 1.5 million to 34.5 million, marking a substantial leap in multilingual OCR technology.