The team behind the open-source MetaGPT framework has launched Atoms, a vibe coding platform that uses a team of AI agents to handle the entire product lifecycle. Agents include Iris (deep researcher), Emma (product manager), Bob (architect), Alex (engineer), Sarah (SEO specialist), Adrian (ads specialist), David (data analyst), and Mike (team leader), coordinating research, scoping, full-stack development, deployment, SEO, and Google Ads management. Every app comes with Atoms Cloud providing built-in authentication, real-time database, Stripe payments, scalable hosting, and one-click deployment. A Race Mode runs prompts across multiple frontier models to improve accuracy up to 3×, and users retain full code ownership with export to GitHub. Atoms offers a free tier with 15 credits per day and Pro plans starting at $20/month, differentiating itself from Lovable and Base44 by bundling market research and distribution tools into the build workflow.
Databricks released Omnigent, an Apache 2.0-licensed open-source meta-harness that standardizes the interface across terminal coding agents (Claude Code, Codex, Pi) and agent SDKs, turning them into interchangeable components. It adds a shared layer for composition (switching agents with one-line changes), contextual control (e.g., pausing at cost limits, requiring human approval for sensitive git pushes), and collaboration (sharing live agent sessions via URL). The architecture consists of a sandboxed runner with a uniform API and a policy server, and sessions sync across terminal, web UI, and mobile. An OS sandbox (Omnibox) secures credentials by injecting tokens only in approved proxy requests. Two example agents—Polly (a multi-agent coding orchestrator) and Debby (a two-headed brainstorming partner)—illustrate its patterns, and an interactive concept demo shows parallel agent delegation and policy enforcement.
On June 12, 2026, a US export control directive forced Anthropic to disable its two most capable models, Claude Fable 5 and Mythos 5, for all users because it could not filter foreign nationals in real time. The order followed a claim by another company that it had jailbroken Mythos, but Anthropic disputes this as a narrow, non-universal jailbreak. Fable 5's safety system uses classifiers that route risky queries (cybersecurity, bio-chem, distillation) to Opus 4.8 in under 5% of sessions; the model had been publicly available since June 9. All other Claude models, including Opus 4.8, remain unaffected. This appears to be the first government-forced takedown of a publicly deployed frontier AI model.
Perplexity integrated its Deep Research mode into Computer, the company’s multi-model orchestration system. The upgraded feature automatically breaks complex questions into subtasks and routes them across more than 20 frontier models. It uses Search as Code to generate code that runs thousands of parallel retrieval steps, dramatically improving agentic browsing: the BrowseComp benchmark score rose from 40.7% to 83.8%, and Humanity’s Last Exam rose from 36.4% to 50.5%. The system reads user-uploaded files alongside live web sources, cites every claim inline, and delivers finished reports, slide decks, and interactive dashboards. Developers can access the same search stack via the pay-as-you-go Perplexity Agent API with a deep-research preset.
On June 11, 2026, xAI launched the Grok Build Plugin Marketplace, an in-terminal catalog of plugins for its Grok Build coding agent. Each plugin bundles skills, slash commands, agents, hooks, MCP servers, and LSPs into a single installable package. The initial catalog includes six partner plugins: MongoDB, Vercel, Sentry, Chrome DevTools, Cloudflare, and Superpowers. Security relies on a commit SHA pin per plugin, verified at clone time to prevent supply-chain tampering. The marketplace is open on GitHub with a PR-based contribution model, but xAI does not verify third-party plugin behavior. Access requires a SuperGrok or X Premium Plus subscription.
Marktechpost’s 2026 roundup compares a range of AI coding agents and development platforms, with Atoms highlighted as a featured multi-agent platform that deploys a coordinated team of product management, architecture, and engineering agents to build deployable, full-stack apps from plain-language prompts. The guide also covers Devin (autonomous engineer), Windsurf (agentic IDE), Cursor (AI-first editor), Warp (terminal-native agents), Galileo (agentic evaluation), and others. A discount code MARKTECHPOST10 is provided for Atoms. The tools are described as having evolved beyond autocomplete to handle planning, multi-file editing, testing, and shipping with limited supervision.