A reverse-engineering writeup says ZCode packages your entire working directory, including the .git object store, LFS cache and reflogs, and uploads it to Alibaba Cloud while you are signed in. Here is what was found, and how four coding agents compare on what leaves your machine.
GitHub Copilot Project HydraFusion orchestrates multiple AI models per coding task, drafting cheap, escalating when hard, and reviewing across model families to cut cost up to 67% while matching Claude Opus 5.
Anthropic shipped version 1.30.0 of its ant CLI on September 3, 2026, and the headline addition is a single command. ant apply creates and updates agents, environments, skills, memory stores, and scheduled deployments from plain files in your repository.
Alibaba shipped an upgraded Qwen3.8-Max snapshot on September 2, 2026, post-trained for coding, with its CodeArena web-dev score up 22 points to 1,691 for first place.
Google shipped Gemini 3.8 Flash on September 2, 2026, its most capable Flash-tier model for long-horizon software engineering and agents, at the same low price as 3.7 Flash.
Cursor has decoupled its cloud coding agents from its own servers. A September 2 update lets agents run on infrastructure you control across eight backends including Modal, Vercel, E2B, and Cloudflare.
Multiverse Computing launched Quasar 438B, a GA reasoning and coding model available now via the CompactifAI API and the highest-scoring European model on Artificial Analysis.
OpenAI said on August 29, 2026 that it will wind down Cursor access to OpenAI models, with a hard cutoff on November 12, 2026.
x1, a Y Combinator-backed AI app studio, launched publicly on August 26, 2026 and took the top spot on Product Hunt the same day. It builds native iPhone apps from a rough idea to an App Store submission.
If you want an open-weights coding model you can route an agent to today or pull onto your own hardware, the honest answer in late 2026 is that it depends on what you own and what you trust.
Microsoft shipped VS Code Agent Host and the open Agent Host Protocol, keeping AI coding agent sessions alive after you close the editor window.
Z.ai officially launched GLM-5.3-Flash, the stealth Ox Alpha model that topped OpenRouter, as an MIT-licensed open-weight coding model.
IBM shipped Granite 4.2 on August 25, 2026, a family of open, Apache 2.0 licensed agentic coding models in 3B, 8B, and 30B sizes that you can download and self-host today.
Slack shipped Slack Code on August 20, 2026, a channel type where a team and its AI coding agents work in the same shared thread.
Google shipped Antigravity IDE extensions on August 20, 2026, bringing its agentic coding tool into VS Code, Visual Studio 2026, JetBrains, and Zed.
Z.ai shipped GLM-5.3 on August 14, 2026, reusing the GLM-5.2 base and pushing large coding gains through scaled post-training. It is live via API now, with open weights in about two weeks.
Bullet, a Y Combinator-backed coding agent launched August 13, 2026, ships as a free CLI and macOS app and claims 95.8% on SWE-bench Verified while averaging 119 seconds per task.
Herdr, the open-source terminal runtime for CLI coding agents, relicensed to Apache-2.0 and crossed 25,000 GitHub stars.
Meta launched Muse Code, a terminal AI coding agent on Muse Spark 1.2 for macOS and Linux. Here is how it compares to Claude Code and Codex.
Prime Intellect released Prime Agent on August 5, 2026, an open-source coding harness that rewrites its own instructions while it works. Paired with Opus 5, it beat the human-expert baseline on ARC-AGI-3.
If you code under an NDA or on a private repo, an on-device voice coding tool is the only safe way to talk to your AI agent. SKI, Spokenly, and VoiceMode keep every word local. Here is how the leading voice coding tools compare.
SKI is a free desktop app that lets you talk to Claude Code, Cursor, Codex, and Gemini CLI out loud, with speech-to-text and voice both running fully on-device.
DeepSeek shipped the official production build of V4 Flash on July 31, 2026: an open-weight, MIT-licensed 284B-parameter MoE model with a 1M token context, native OpenAI Responses API and Codex support, and API output at $0.28 per million tokens.
Hubo is an open-source plugin that adds a two-agent implement-and-review loop to AI coding tools like Claude Code and Codex, so every change is critiqued before it reaches you.