Avatoon: 3D Avatar Lip-Sync in React Three Fiber
Avatoon is an open-source React Three Fiber component that drops a talking, lip-synced 3D avatar into any web or React Native app. Version 1.10.0 shipped July 15, 2026 under an MIT license.
Avatoon is an open-source React Three Fiber component that drops a talking, lip-synced 3D avatar into any web or React Native app. Version 1.10.0 shipped July 15, 2026 under an MIT license.
ReviewFlow is a new open-source extension that moves GitLab code review inside your editor, so you can draft comments and publish merge request reviews without leaving Cursor or VS Code.
Kastra is a runtime authorization layer that checks every shell command, file edit, and API call your AI coding agent makes before it runs.
Condense, a new context-compression proxy for AI coding agents, launched July 3 2026 with a claim aimed at heavy Claude Code users: up to 70% lower token bills with almost no quality loss.
CrossUI Studio is a visual IDE for React that writes every canvas edit back to your source as a precise AST patch with no export step and no lock-in.
Context engineering just got a dedicated workbench. On June 23, 2026, DAI Studio launched a free visual tool that lets you design, see, and version the exact context you feed into a large language model before it runs.
Oak is a new version control system built specifically for AI agents, now in public beta with a Rust core tuned for agent workflows.
Cursor has acquired Continue, the open-source coding assistant that let developers build their own AI pair programmer on any model.
Anthropic shipped Claude Code Artifacts, turning a coding session into a live, interactive web page you can share with one link. It is in beta for Team and Enterprise plans.
GitHub Copilot now routes each task to the best available model automatically and caches repeated prompt context to cut token cost.
VS Code 1.125 adds one-click model provider installs, a live Copilot budget meter, and managed AI policies for teams.
Cursor announced Origin, a Git-compatible forge built for AI agent workloads. It is a direct shot at GitHub, with general availability set for fall 2026.
Zhipu has shipped GLM 5.2, a coding-first model now live across every tier of its Z.ai Coding Plan, led by a 1-million-token context window.
xAI shipped the Grok Build Plugin Marketplace on June 11, 2026, a built-in catalog for its terminal coding agent with six partner plugins, open-source distribution, and commit pinning.
Locaible runs pre-tuned AI coding agents on your own machine and exposes them to Cursor through a local, OpenAI-compatible endpoint, so your code never leaves your machine.
Apple's Xcode 27 ships seven official Agent Skills, and one command exports them into the ~/.agents folder that Claude, Codex, and Cursor already read.
Cohere released North Mini Code 1.0 on June 9, 2026, an open-weights 30B Mixture-of-Experts coding model that runs on modest hardware under Apache 2.0.
Cursor shipped two canvas features on June 4: Design Mode for annotating UI elements directly, and a Context Usage Report that audits where the agent spends its tokens.
Microsoft announces Windows Agent Framework and a new Agent Store at Build 2026, enabling AI agents to control desktop applications natively.
Microsoft unveiled Project Polaris at Build 2026: an in-house mixture-of-experts coding model that replaces GPT-4 Turbo as the GitHub Copilot default in August 2026.
Microsoft published its first-party PostgreSQL extension to Open VSX on June 1, 2026, unblocking Cursor users and bundling a DBAgent MCP server so AI agents read live schema and EXPLAIN plans inline.
GitHub Copilot switches to usage-based billing on June 1, 2026, replacing flat-rate Pro and Business plans with metered completions and premium model requests.
A developer-built tool called claude-code-proxy lets creators and developers route Claude Code through Kimi Code or ChatGPT Plus/Pro subscriptions instead of paying Anthropic API rates.
Cursor shipped auto-review mode today in version 3.6, a new run mode that lets the agent work for longer stretches with fewer approval prompts.