Tag
Cursor
Cursor is an AI-first code editor and workflow hub, not just autocomplete. Its relevance now spans agentic coding, refactoring, debugging, and MCP or CLI integrations, while model choices, pricing, and security trade-offs shape how teams adopt AI development tools.
24 articles
Codex CLI 让你在终端里写代码
我把知乎这篇 Codex 上手说明拆成可执行流程，整理成终端与 IDE 都能直接用的模板。
$2B Cursor leads vibe coding in 2026
Cursor hit $2 billion in annualized revenue as vibe coding spread, with AI tools now generating more code and changing dev workflows.
6 Devin alternatives at the $20 price point
6 Devin alternatives that beat the $20 Core plan on cost, control, and day-to-day coding value.
Windsurf Pricing in 2026: Plans, Quotas, and Costs
Windsurf’s 2026 pricing swaps credits for quotas, raises Pro to $20, and adds a $200 Max tier for heavy users.
8 AI coding assistants for enterprise teams
8 AI coding assistants compared for context handling, enterprise fit, speed, and pricing across real codebases.
AWS ships Agent Toolkit for coding agents
AWS launched Agent Toolkit for AWS, adding MCP access, curated skills, and audit controls for Claude Code, Cursor, and other agents.
rtk cuts token waste in AI coding tools
rtk adds token-saving config templates for Claude Code, Cursor, Gemini CLI, Codex, and more.
How to Build a Codebase-Aware AI PR Reviewer
Set up a codebase-aware AI PR reviewer that catches team-specific review mistakes before humans do.
Cursor CEO Michael Truell’s rapid rise
Michael Truell turned Cursor into a $60 billion SpaceX deal after starting coding at 11 and leaving MIT for startups.
Cursor vs Windsurf: 4 Tasks, Same Prompts
Same prompts, four tasks, two AI IDEs. Cursor fit the codebase better; Windsurf moved faster but needed more cleanup.
I Tested Devin on 10 Tasks. It Finished 3.
Devin scored 13.86% on SWE-bench and finished 3 of 10 real tasks in one test, showing where AI coding agents still fall short.
Cursor’s Kimi K2.5 Disclosure Miss, Explained
Cursor’s Composer 2 hid its Kimi K2.5 base model. That disclosure gap matters for trust, licensing, and code-data handling.
VS Code vs Cursor vs Windsurf in 2026
VS Code, Cursor, Windsurf, JetBrains, and web IDEs each win on different axes in 2026. Here’s the practical breakdown for teams.
Cursor, Kimi, and the Open Source Bet
Cursor’s new coding model hit near-state-of-the-art performance at one-eighth the price, and its stack points straight to open source.
CrewForm Agents Can Now Act Like MCP Tools
CrewForm now exposes published agents as MCP tools, so Claude Desktop and Cursor can call them directly with one config file.
Cursor CEO warns vibe coding builds shaky software
Cursor CEO Michael Truell says skipping code review with AI makes software brittle, while Cursor keeps engineers in the loop.
Supabase MCP lets AI query your projects
Supabase’s MCP server connects AI tools to projects, databases, logs, and Edge Functions, with read-only mode and project scoping.
RTK cuts Claude Code token spend fast
RTK claims it can cut Claude Code token use by up to 80% by routing work through local shell commands and agents.
飞书开源CLI：AI Agent 直接管办公协作
飞书开源 CLI 提供 200+ 命令和 19 个 AI Skills，让 Claude Code、Cursor 直接操作日历、文档与消息。
Cognition's Devin and the AI coding race
Cognition grew from 40 staff to 200+ after buying Windsurf, as Devin pushes harder into enterprise coding and AI software work.
Cursor’s new coding model rides on Kimi K2.5
Cursor’s Composer 2 is cheaper than Claude Opus 4.6, but it was built on Kimi K2.5 and that changes the story.
Cursor’s Composer 2 started from Kimi
Cursor says Composer 2 began on Moonshot AI’s Kimi base, then added more training. The company says the final model is very different.
Cursor Adds Self-Hosted Agents and Real-Time RL
Cursor shipped self-hosted cloud agents and real-time RL for Composer, with checkpoints updated as often as every five hours.
Cursor's Meteoric Rise Faces Industry Pressures
Cursor, a $30 billion AI startup, faces intense competition from Anthropic and OpenAI, challenging its rapid growth in the AI coding market.