Anthropic makes Code Review generally available
Out of research preview for Team and Enterprise, with reviews about 3x faster and per-repository depth levels.
Out of research preview for Team and Enterprise, with reviews about 3x faster and per-repository depth levels.
Small TypeScript functions that change how Claude Code works, from prompts to custom UI.
First GitHub release (0.5.0) of MiniMax Code, its open-source terminal coding agent, built from public source.
First GitHub release of its agent harness, a pre-release (v0.1.0-rc.7), managing Codex and Claude Code subagent tasks.
Claude Code runs auto mode by default on Pro, Max and Team plans for longer autonomous work.
Claude Code can preview work in progress as a live, shareable interactive artifact.
Codex adds plugins, sites and annotations aimed at analysts, marketers, designers and other roles.
Claude Code can run a task across tens to hundreds of parallel subagents and check its work first.
Coding agents that run in the cloud in parallel, started from the Vibe CLI or Le Chat, with local CLI sessions movable to the cloud.
Codex tasks can be monitored, steered and approved from the ChatGPT mobile app.
The Codex desktop app adds computer use, in-app browsing, image generation, memory and plugins.
Repeatable routines run in the cloud to work a backlog, review PRs and respond to events.
Claude Code makes permission decisions itself, with built-in safeguards.
A team of agents reviews every pull request for bugs; research preview for Team and Enterprise.
Built into Claude Code on the web, it scans codebases for vulnerabilities and suggests patches; research preview.
Xcode 26.3 integrates the Claude Agent SDK for autonomous, long-running coding tasks on Apple platforms.
A desktop app for running multiple coding agents in parallel on long-running tasks.
Coding product for Kimi K2.5 that works in the terminal and integrates with IDEs including VS Code, Cursor and Zed.
Upgrade to its terminal coding agent with custom subagents and slash-command skills, now on Le Chat Pro and Team plans.
Open-source command-line coding agent powered by Devstral, under Apache 2.0, released with Devstral 2.
Tagging @Claude in Slack starts Claude Code sessions that fix bugs and open pull requests.
Agentic development platform where agents work across editor, terminal and browser; free public preview.
First GitHub release (0.33) of Kimi CLI, Moonshot AI's command-line coding agent, later succeeded by Kimi Code.
Delegate coding tasks from the browser to Claude running on Anthropic-managed cloud infrastructure.
Bundles of slash commands, agents, MCP servers and hooks install with one command.
Codex reaches general availability with a Slack integration, Codex SDK and admin tools.
Claude Code gains checkpoints to roll back changes and a native VS Code extension.
The building blocks behind Claude Code, released for developers to build their own agents.
GPT-5-Codex, a version of GPT-5 optimized for agentic coding, available everywhere Codex runs.
Team and Enterprise customers can buy premium seats that include Claude Code.
Jules leaves beta, powered by Gemini 2.5, with higher limits for Google AI Pro and Ultra subscribers.
Open-source command-line tool for agentic coding, released alongside the Qwen3-Coder model.
Open-source AI agent bringing Gemini into the terminal, free with a Google account and 1,000 requests a day.
AI coding assistant for enterprises, built on the open-source Continue project, in private beta for JetBrains IDEs and VS Code.
Claude Code leaves research preview, adding background tasks via GitHub Actions and beta VS Code and JetBrains extensions.
Jules, an asynchronous coding agent, opens to everyone in public beta, free with usage limits.
A cloud-based coding agent powered by codex-1, a version of o3 optimized for software engineering.
A lightweight, open-source coding agent that runs from the terminal on your own computer.
A command-line agentic coding tool, in limited research preview, delegating work from the terminal.
An experimental code agent in a GitHub workflow that tackles an issue, develops a plan and executes it.
No events match these filters.