Tag
coding agent
Coding agents are AI systems that can read a codebase, plan changes, edit files, run tools, and report results inside terminals, IDEs, or cloud runtimes. This tag covers products like Codex, Claude Code, Cursor, and Copilot, plus the tradeoffs around tool use, permissions, and self-hosted deployment.
4 articles
Kimi K2.7-Code Adds HighSpeed Mode, Skips Benchmarks
Moonshot’s Kimi K2.7-Code adds a faster mode and lower token use, but only Moonshot’s own benchmarks back the claims.
MiniMax M3: 中国首个三合一开源模型
MiniMax M3 combines coding, 1M context, and native multimodal support, while MiniMax Code adds an agentic coding layer.
xAI launches Grok Build for terminal coding
xAI’s early beta Grok Build brings terminal-based coding agents, plan mode, parallel subagents, and ACP support to paid subscribers.
OpenAI’s Codex Plugin Lands in Claude Code
OpenAI shipped a Codex plugin for Claude Code on March 30, putting its coding agent inside Anthropic’s terminal tool.