Agent product updates

OpenAI and Work Louder released kbd-1.0-codex-micro, a compact hardware controller for Codex workflows with mappable buttons, a joystick, status keys, and RGB feedback. Posts from Work Louder and early users describe Codex-focused mappings for multi-agent status, accept/reject actions, six layers, and app auto-switching.

ChatGPT Sites entered public beta for building dashboards, trackers, reports, prototypes, and apps from prompts, files, or rough ideas. It includes preview, published URLs, admin controls, and built-in auth, while one user reported confusing deploy behavior.

OpenAI staff described Work using the Codex harness to inspect Gmail, confirm intent, and produce cleanup lists. The rollout also added in-app code editing and a PR tab, while users questioned how Work, Chat, and Codex differ.

OpenAI launched ChatGPT Work, a Codex- and GPT-5.6-powered ChatGPT agent with a desktop app that can access local files and apps. OpenAI staff said Work and Codex use the same sandboxing with UI changes.

Claude Cowork is rolling out to mobile and web for Max users, with shared Chat navigation and cross-device task review. Scheduled tasks can run while a computer is off, and doubled Cowork limits last through August 5.

Meta launched Muse Image in its apps and previewed Muse Video from the same media-generation family. Meta says Muse Image can reason, search, write code, self-refine, and use test-time compute before generating images.

Cognition introduced Devin Security Swarm, a repo-wide vulnerability scanner built on an Agentic MapReduce architecture that fans out over code shards and verifies findings in sandboxes. In a 50-vulnerability GHSA eval across 14 languages, it found 36 issues at 30% lower cost per finding than the next most accurate alternative.

Letta introduced a desktop agent product that keeps long-term state, rewrites its own skills and wiki files over time, and follows the same identity across local and remote channels. An early practitioner demo showed a Letta agent installing a Mod for Exa-backed web search from Slack, sharpening the launch beyond the announcement thread.

Anthropic shipped Claude Code 2.1.198 with Claude in Chrome, background agents that auto-commit and open draft PRs, and a new eval command with ablation and judge-model options. The release also adds AWS upstream failover and retries transient mid-response network drops instead of aborting turns.

Z.ai released ZCode as its official desktop environment for GLM-5.2, with multi-agent project work, long-running tasks, code review, and clients for macOS, Windows, and Linux. GLM Coding Plan subscribers get a 1.5x quota inside ZCode, while other developers can bring existing subscriptions or API keys.

xAI opened a no-code builder for Grok Voice agents with phone numbers, SIP routing, call recording, MCP and API connections, and 80+ built-in voices. The beta prices audio at $0.05 per minute, plus $0.01 per minute for xAI-provided telephony.

ElevenLabs introduced Procedures in ElevenAgents as packaged playbooks that load only when a conversation matches a defined scenario. Teams can import SOPs from docs, PDFs, or TXT files and turn them into structured or free-form procedures for support and operations flows.

Cognition launched Devin Fusion, a hybrid coding harness that reroutes work mid-task and says it cuts Fable-class cost by 35%. Use it when upfront routing misses late complexity; the router can re-evaluate after investigation starts.

Sakana made Fugu Ultra available through Vercel AI Gateway, while new technical writeups described the trained routing head and multi-step orchestration behind it. The integration matters because teams can invoke Fugu’s model-selection workflow through existing gateway plumbing instead of standing up custom routing.

OpenCode v2 moves its TUI, desktop, and web clients onto a shared backend so sessions stay synced and resource use drops across windows. The beta matters for multi-window agent workflows, though the next build still lacks features.

A day after Gemini 3.5 Flash Computer Use surfaced as a launch story, Google formally opened it through the Gemini API and Enterprise Agent Platform. Explicit user confirmation, automated task stopping, and an Android adb quickstart make the rollout concrete for agent builders.

Google released built-in Computer Use for Gemini 3.5 Flash across browser, mobile, and desktop. Try it for agent workflows, but watch for timeout issues on long design-from-scratch runs.

A day after Claude Tag launched, engineers raised token billing, lock-in, and shared-memory concerns while Anthropic described its agent-identity model. Watch how Claude behaves in shared Slack channels, where it uses its own credentials and scoped access.

Claude Tag puts Claude into Slack as a teammate that can handle threads, use approved tools, and follow up proactively in selected channels. Team and Enterprise users can try it in beta to keep shared channel context instead of restarting from private chats.

Hermes Agent added GUI computer-use support for Windows and Linux through TryCua drivers, extending beyond existing macOS support. Teams running desktop automation across mixed operating systems should test the new coverage.

Sakana AI launched Fugu and Fugu Ultra as OpenAI-compatible orchestration models that route, verify, and synthesize across multiple models. The release matters because Sakana is selling multi-agent coordination as a single endpoint, but it has not fully disclosed model mix or pass-through costs.

Hermes Agent can now self-host Mem0, and the desktop client can attach to headless Hermes instances or start one with the hermes desktop command. The change expands always-on memory and remote control setups outside a laptop session.

Hermes now offers a setup path that starts with only a provider, model, file operations, and terminal access. The smaller base gives users a minimal install they can extend manually.

Claude Code can now turn a live session into a private artifact page for PR walkthroughs, debug timelines, dashboards, and architecture notes. Team and Enterprise users get a persistent review surface that refreshes as the session changes.

OpenAI added Record & Replay to Codex so users can demonstrate a repetitive computer task once and save it as a reusable skill. The first rollout is Mac-only and unavailable in the EEA, UK, and Switzerland, so teams should check access before planning rollout.

HumanLayer opened access to an agentic IDE, collaboration surface, and software-factory building blocks aimed at long-running codebase work. The launch matters because it pairs remote daemon execution and review loops with architecture guardrails instead of optimizing only for raw code generation.

Cursor now lets developers move local agents to the cloud so work can continue after the laptop closes, with mobile as the handoff control surface. The change removes one of the main setup frictions in long-running cloud sessions.

Exa launched Agent, an API that combines its search stack, mixed-model orchestration, and agent harness for deep web research. Exa says it can handle Opus- and GPT-5.5-class browsing tasks at less than half the cost.

Cursor launched Origin, a code storage and Git hosting product built for agent-heavy workflows, with API and MCP extensibility plus conflict-handling for parallel changes. It matters because multi-agent coding shifts the bottleneck from generation to branch, diff, and merge orchestration.

Factory 2.0 expands from coding agents to end-to-end software factories spanning tickets, code, tests, deployments, and incidents. The release makes feedback loops and model routing first-class parts of engineering automation.

Sakana launched Marlin, a Virtual CSO that runs for up to 8 hours, forms hypotheses, browses sources, and returns slide decks plus reports. It turns Sakana’s long-horizon reasoning work into a shipped deep-research product.

Amp reversed its same-day plan to proactively verify user IDs for future frontier-model access and deleted any Stripe verification records. The rollback removes an immediate KYC step, but Amp says governments and model labs could still require identity checks later.

Kilo's Product Week bundle added Agent Manager for isolated git worktrees, Kilo Console beta, REVIEWS.md memory hooks, and a balance-based MiniMax M3 plan. The bundle puts parallel agent runs, browser control, and plan provisioning into one shipped release.

Hermes Agent shipped Telegram Rich Messages support and later added cloning from any existing profile, not just the default. The update expands bot-side messaging and makes reusable multi-profile setups less manual.

Anthropic opened scheduled deployments and environment-variable vaults in Claude Managed Agents public beta, and Dynamic Workflows is now generally available in Claude Code. The update adds cron-style jobs, secret injection, and deeper parallel orchestration for long-running agents.

Anthropic released Fable 5 as its public Mythos-class model and routes some sensitive prompts to Opus 4.8. Independent evals ranked it at or near the top for coding and agentic tasks on day one.

Anthropic says Fable may degrade frontier LLM-development requests via prompt edits, steering vectors, and PEFT, while other sensitive queries fall back to Opus 4.8. Researchers reported false positives on inference code and biology prompts, and ARC Prize paused evals over Mythos data retention.

Hermes Agent added Photon as a gateway channel, letting users bring an agent into iMessage through the hermes gateway setup flow. The integration matters because it extends an open-source agent stack into a consumer messaging surface without changing the core agent runtime.

Kimi Work launched for macOS and Windows with up to 300 local agents, WebBridge browser control, finance data tools, and a memory system. It matters because the app bundles multi-agent desktop automation locally instead of routing the workflow through a hosted IDE.

After Hermes Agent v0.16.0, Nous added a built-in /simplify-code skill and pointed users to hermes --tui as the future CLI surface. The update adds more agent commands and dashboard controls, but remote workflows still need to catch up.

Amp shipped customizable keybindings and a mode switcher that describes each mode, and showed a .amp/plugins plus .amp/settings.json workflow for commit-and-archive macros. The release makes thread management and local customization part of the CLI surface instead of a fixed default UI.

Nous shipped Hermes Agent v0.16.0 with a desktop GUI, a rebuilt browser dashboard, remote auth options, and full Simplified Chinese UI coverage. The release moves Hermes beyond a terminal-only workflow and into a broader admin and desktop control surface.

Cursor shipped Design Mode, letting users point at elements, draw annotations, or speak changes directly against a UI. The feature pushes more frontend iteration into the editor and narrows the gap between interface feedback and code changes.

Cognition said it will fund Devin usage up to $10 million when measured engineering value falls below cost, and published a technical writeup estimating productive engineering hours per session. It matters because the company is shifting agent pricing from tokens to claimed output and extending coding evaluation toward much longer task horizons.

OpenAI expanded the Build iOS Apps plugin so Codex can test apps in an in-app browser, open SwiftUI previews, and hot-reload edits without leaving Codex. It matters because more of the iOS iteration loop stays inside the coding agent instead of bouncing through external simulators and manual preview steps.

Claude Code 2.1.163 adds managed min/max version enforcement, a tool that runs Bash and returns output in-turn, and exact-string replacements for Edit. It matters because teams get tighter CLI fleet control and less error-prone command and file mutation behavior in managed deployments.

OpenClaw 2026.6.1 added a native Windows node host, a Skill Workshop for reviewable agent-learned skills, and Workboard orchestration. The update extends OpenClaw beyond Unix-heavy setups and moves more agent management into built-in tools.

Perplexity opened Personal Computer for Windows to Max and Enterprise Max users on a waitlist. The rollout widens its local agent surface beyond earlier releases, and users should watch for the local-cloud task splitting preview for private or heavier workloads.

OpenAI rolled out Codex Sites, annotations, and role-specific plugins, while weekly users topped 5 million. The release pushes Codex beyond coding into hosted workspace and app workflows for enterprise teams.

Nous Research put Hermes Agent into a native desktop app and added Portal and Ollama-backed setup paths plus a Tailscale remote-connect fix. Hermes now has a local-first desktop surface instead of a terminal-only workflow.