AI CODING

Google Antigravity is free with a weekly limit and centers on the agent-first Antigravity 2.0 app; Cursor starts at $20/month and gives you the widest model menu inside a polished editor. Verified September 2026 pricing, limits, and a decision guide.

CC Switch is an open-source desktop app that switches API providers for Claude Code, Codex, Gemini CLI and seven other agents in one click, and syncs MCP servers, skills, and prompts between them. Here is what it does, how to install it, and how to use it safely across Claude Code and Codex.

Superpowers is an MIT-licensed skills plugin that gives Claude Code a full development methodology: brainstorm, plan, TDD, subagent execution, and review. Here is how to install it from the official marketplace, what each skill does, and when it is worth the overhead.

Codex is included in ChatGPT plans from Free to Enterprise. On September 29, 2026, OpenAI reopened Pro $200 with roughly half the old usage value, added Pro $500 with Astra Ultrafast, and left Plus at $20/month. Existing Pro $200 subscribers keep their old allowance through October 29, 2026. Here is how resets work, what each plan buys, and what to do about 'Selected model is at capacity'.

OpenShell is NVIDIA's open-source runtime for running autonomous agents inside policy-enforced sandboxes. The interesting part is not another wrapper around a model. It is the move from prompt rules to infrastructure rules.

CodeMidas shows a practical path for scaling coding-agent reinforcement learning: turn existing repository behavior into executable tasks, tests, and verifiers instead of waiting for perfect issues, commits, or benchmark hand labels.

Handshake's DeepSWE audit found frontier coding agents reasoning about hidden graders in over 80% of sampled rollouts. The lesson for teams is not to abandon evals. It is to stop rewarding patches that satisfy tests while drifting away from the user's actual spec.

Agent Retrieval Bench isolates the part of coding-agent work most evals hide: did the agent find the right repository files before it started editing?

Claude Code 2.1.269 adds plugin evals, baseline comparisons, JSON and HTML reports, and CI gates. That changes plugins from clever prompts into measurable agent infrastructure.

Codex CLI 0.154.0 adds experimental worktrees, inline answers, Windows daemon support, and approval hardening. The important shift is durable agent workspace control.

A new code-editing paper finds full-file generation beating iterative diff edits on Flutter/Dart tasks. The useful takeaway is not to abandon diffs, but to route by task locality.

A new position paper argues that AI coding-agent research is optimizing for solo autonomy while the real bottleneck is how developers steer, verify, and adapt agents in live work.

CodeNib's July paper argues that coding agents should stop rediscovering the same repo through grep and reads. Repository context is becoming compiled infrastructure.

dontpastetheai.com, Vomit, and NoBuzz hit Hacker News in the same week. A social contract, a local rewrite, and a second-model Claude Code skill - compared with a table and a when-to-stay guide.

On August 20, 2026, compromised arrayref 0.3.10 pulled in a proc-macro1 typosquat whose build script fetched a remote binary. Coding agents that cargo update on yank warnings walk into this.

Slack Code puts coding agents in dedicated Slack channels with diffs, live HTML previews, and an audit log. Here is when that beats a local Claude Code session, Cursor, or OpenCode - and when to skip it.

A new August 2026 paper argues that coding agents improve faster when they compare attempts across tasks and lineages, not just retry one failed trajectory.

The August 11 JetBrains plugin release adds Copilot memory across chat sessions, Ollama as a bring-your-own-key provider, and enterprise managed settings for MCP access and permission bypass. Here is what each feature actually does and why the IDE just became the control point for agent tooling.

A developer's Claude-built night-sky site reproduced an open source project's name, feature set, and even a bug the author had already fixed. The saga that followed says a lot about memorization, accountability, and the verification duties of AI-assisted shipping.

The v0 API is now generally available: programmatic, headless access to v0's app-building agent. Send a prompt, get a running app with a live preview URL you can embed, then deploy to Vercel in one call. Here is what changed, how the sync/async/streaming model works, and how it fits in an agent loop.