Agent Product Launch

Fresh hands-on reports show Codex controlling minimized apps via macOS APIs, using a DOM-aware browser comment mode, and running for day-long sessions in the desktop app. That gives OpenAI stronger evidence that computer use is usable for daily development, though the rollout remains macOS-first and brittle around working-state changes.

Ollama 0.21 added native Hermes Agent support through the ollama launch hermes command. That makes a self-improving local agent loop available without a hosted inference stack, with memory and skills running on top of Ollama’s model serving.

OpenAI expanded Codex with background Mac computer use, an in-app browser, image generation, memory preview, automations, and 90+ plugins. The release moves Codex from terminal coding toward long-running UI and ops workflows, though some features remain macOS-first or alpha.

Claude Opus 4.7 is now generally available across Claude, the API, and major clouds with xhigh effort, higher-resolution vision, and Claude Code review upgrades. Prompt behavior, tokenization, and effort defaults changed enough that existing harnesses may need retuning.

Windsurf 2.0 launched with Devin embedded into the product, combining local agents with cloud agents that can continue across codebases after you close the laptop. The IDE now acts as a handoff layer between interactive edits and long-running remote execution.

Anthropic introduced Claude Code Routines, a cloud-run automation layer that can execute on schedules, API calls, and GitHub events. The rollout moves scheduling from local runs to hosted, persistent automation and adds new trigger surfaces for plan-wide use.

Anthropic rebuilt Claude Code on desktop into a drag-and-drop multi-session workspace with file editing, HTML and PDF preview, and sidebar session management. The same rollout also shipped 2.1.108 features, including an optional 1-hour cache TTL, recap, and new built-ins that affect cost and session handoff.

Nous Research shipped Hermes Agent v0.9.0 with a local web dashboard, new monitoring APIs, and broader platform updates. Teams using multi-agent workflows should test the new controls for profile cloning and long-running dashboard-managed sessions.

Cursor 3 adds split-agent panes, tighter cloud-agent controls, voice input fixes, and an 87% reduction in dropped frames during large edits. The update makes the IDE easier to use as a mixed local-cloud agent workspace, while keeping editor navigation and diff review intact.

Open Agents open-sources a browser-based cloud coding platform that keeps sessions running in parallel after a laptop closes. Use the reference stack if you want sandboxed VMs, model routing, and durable execution for internal coding-agent systems.

Hermes Agent shipped automatic OpenClaw migration, pastebin log sharing, and a reported 20% improvement in loading the right skill. Use the new import path and debug sharing to simplify setup across the official and community add-ons now covering support, web UI, workspace boards, and chat front ends.

Nous said Hermes became the top coding app on OpenRouter while shipping an OpenClaw migration patch, Telegram agent-to-agent messaging, and new memory controls. If you run long-lived agents, watch the migration path and memory settings before moving chats or skills hubs.

Codex 0.120 introduced per-project memory extension files and Realtime V2 progress streaming for background agents. Separate app findings also showed an unreleased Scratchpad view that can start parallel Codex chats from a task list, which may change how teams queue work.

Anthropic launched /ultraplan, moving Claude Code planning into a web review flow with cloud execution or terminal handoff. Claude Code 2.1.101 also adds OS certificate-store trust by default, a command-injection fix, and new prompt rules for browser validation and prompt caching.

Qwen Code added phone-based control via Telegram, DingTalk, and WeChat, scheduled agent loops, per-subagent model selection, and a planning mode before execution. The release also centers Qwen3.6-Plus, which Alibaba says offers 1M context and 1,000 free daily requests, while Vals ranked the model #17 overall and #11 multimodal.

OpenAI added a $100 ChatGPT Pro tier with 5x more Codex usage than Plus and kept the $200 tier as the highest-capacity option. The new tier resets Codex limits again and temporarily doubles Pro usage through May 31.

Anthropic added a beta advisor tool to the Messages API so Sonnet or Haiku can call Opus mid-run inside one request. Anthropic says Sonnet plus Opus scored 2.7 points higher on SWE-bench Multilingual while cutting per-task cost 11.9%.

Anthropic put Claude Managed Agents into public beta with hosted sandboxes, vaults, memory filesystems, and long-running sessions. Use the managed setup if you want explicit controls for tools, credentials, and completion criteria instead of custom harness code.

Providers and agent platforms added GLM-5.1 endpoints across Modal, Together AI, Letta Code, Tembo, and Tabbit, with free trials, no-key access, and 99.9% SLA options. Use the new hosting options to test the model for coding and long-horizon agent workloads without waiting on self-hosting.

Hermes Agent v0.8.0 added remote code-execution backends, Browser Use cloud browsing, prompt caching, shared sessions, and CLI workflow upgrades like `hermes -w`. Try the new browser-backed and parallel execution paths if you need more persistent, multi-provider agent runs.

Z.ai released GLM-5.1, a 744B open model built for long-horizon agentic coding and ranked first among open systems on SWE-Bench Pro. Day-0 support in OpenRouter, Ollama, SGLang, vLLM, OpenCode, and local quantization paths makes it ready to test in existing stacks.

OpenAI said Codex reached 3 million weekly users and reset usage limits, with another reset planned for each additional million users up to 10 million. ChatGPT-sign-in Codex will also retire the gpt-5.2 and gpt-5.1-era lineup on April 14, so teams should watch for model-default changes.

Nous Research added MiniMax M2.7, Xiaomi’s MiMo V2 Pro, a SuperMemory plugin, and expanded Manim support to Hermes through partner integrations. The additions give users new hosted model options, a shared memory backend, and more complete technical-animation tooling to try in workflows.

Nous released Hermes Agent v0.7.0 with an extensible memory plugin system, rotating credential pools, Camofox browser support, and inline diff previews. The update pushes the framework closer to production use, so teams can test the new failure handling and interface split before adopting it.

Cursor 3 introduced a separate agent-first workspace that can run agents locally, in worktrees, over SSH, and in the cloud while keeping the editor available. The release gives teams a path to multi-agent orchestration without giving up the traditional IDE surface.

Z.ai released GLM-5V-Turbo, a multimodal coding model for screenshots, video, design drafts, and GUI-agent tasks. It keeps text-coding performance steady while adding native vision support, so teams can test visual workflows without swapping models.

Claude Code 2.1.90 adds an experimental NO_FLICKER fullscreen renderer with mouse support and virtualized scrolling. The release also fixes rate-limit loops and resume regressions, so update if you want the new UI while watching for selection and table-rendering bugs.

Rivet introduced agentOS, an embedded agent runtime built on WASM and V8 isolates with backend embedding, mounted filesystems, and built-in orchestration. If you run agents in production, compare it against separate sandbox infrastructure.

Anthropic put computer use directly into Claude Code, letting the CLI open apps, click through GUIs, and verify work on screen. Try it if you want Claude Code to handle end-to-end UI tasks beyond file edits, but note it is rolling out as a research preview on Pro and Max plans.

Nous Research shipped Hermes Agent v0.6.0 with multi-agent profiles, a published changelog, and new OpenWebUI tool-call streaming support. Upgrade if you use Hermes as a local agent, since the release turns it into a multi-profile workspace with a growing plugin and UI ecosystem.

OpenCode says all Go models now run under zero-data-retention agreements and that hosted requests use the same upstream providers as direct access. That tightens the privacy boundary for hosted coding agents, but operators still need to watch RAM use, rapid updates, and plan economics.

Hermes Agent v0.5.0 adds 400+ models via Nous Portal, Hugging Face access, Exa support, GPT-5.4 behavior tweaks, and a published changelog. The release broadens provider coverage and hardens the runtime without changing the terminal-first workflow.

Z.ai said GLM-5.1 is now available to all GLM Coding Plan users and highlighted a 5am to 11am PT switch window. The update broadens access beyond the initial rollout, though early practitioner tests reported weaker Repo bench and tool-calling behavior than 5.0.

Claude Code can now run recurring prompts and background pull-request work on Anthropic-managed cloud environments from the web, desktop, or `/schedule`. That makes long-running repo tasks less dependent on a local machine, but users report task caps and restricted egress.

Z.ai made GLM-5.1 available to all Coding Plan users and documented how to route coding agents to it by changing the model name in config. Early harness benchmarks place it near Opus 4.6 on coding evals, but BridgeBench users report much slower tokens per second.

Composio shipped Universal CLI as a shell-first interface to its integrations, moving install, search, and agent workflows out of MCP setup. The release targets users who want simpler agent tool access after complaints that MCP stacks are harder to install, slower, and less stable.

OpenAI published a Codex use-case gallery with one-click workflows, and shadcn/ui and Box shipped official plugins. Teams can now install reusable app and web workflows directly instead of wiring each integration by hand.

Hermes Agent now treats Hugging Face as a first-class inference provider and surfaces 28 curated models in its picker, plus a custom path to the broader catalog. That broadens model choice for a persistent local agent workflow without requiring users to wire a provider manually.

OpenCode shipped terminal, desktop, and `opencode serve` workflows for an open-source coding agent with LSP support, plugins, and more than 75 providers. Users should look at the multi-backend web sessions, IPC plugins, and sandboxed local setup as the main differentiators.

OpenAI rolled out Codex plugins across the app, CLI, and IDE extensions, with app auth, reusable skills, and optional MCP servers. Teams should test plugin-backed workflows and permission models before broad rollout.

Cline launched Kanban, a local multi-agent board that runs Claude, Codex, and Cline CLI tasks in isolated worktrees with dependency chains and diffs. Teams can use it as a visual control layer for parallel coding agents on repo chores that split cleanly.

Every opened Plus One, a hosted OpenClaw that lives in Slack, comes preloaded with internal skills, and works with a ChatGPT subscription or other API keys. It lowers the ops burden for deployed coworkers, so teams can test packaged agents before building their own stack.

Rork added Max Publishing to generate icons, screenshots, listing text, review metadata, and submission steps for App Store releases, and also shipped an App Store MCP. Use it first on non-critical apps and keep a manual review gate.

Claude Code 2.1.84 adds an opt-in PowerShell tool, new task and worktree hooks, safer MCP limits, and better startup and prompt-cache behavior. Anthropic also documented auto mode’s action classifier and added iMessage as a channel, so teams should review permissions and remote-control workflows.

GPT-5.4 mini and nano bring 400K context, multimodal input, and the full GPT-5.4 reasoning-mode ladder at lower prices. Early benchmarking suggests nano is the strongest cost-performance tier for agentic tasks, but both models spend far more output tokens than peers.

OpenClaw 2026.3.24 adds native Microsoft Teams, OpenWebUI sub-agent access, Slack reply buttons, and a control surface for skills and tools. The release expands where the runtime can plug into enterprise workflows, while also increasing the surface area teams need to secure.

OpenClaw shipped version 2026.3.22 with ClawHub, OpenShell plus SSH sandboxes, side-question flows, and more search and model options, then followed with a 2026.3.23 patch. Teams get a broader plugin surface, but should patch quickly and review plugin trust boundaries as the ecosystem grows.

Claude can now drive macOS apps, browser tabs, the keyboard, and the mouse from Claude Cowork and Claude Code, with permission prompts when it needs direct screen access. That makes legacy desktop workflows automatable, and Anthropic is pairing the push with more background-task support for longer agent loops.

Agent Computer launched cloud desktops that boot in under half a second and expose persistent disks, shared credentials, SSH access, and ACP control for agents. It gives coding agents a faster place to run tools and reuse auth, but teams still need to design safe session and credential boundaries.

PlayerZero launched an AI production engineer and claims its world model can simulate failures before release, trace incidents to exact PRs, and beat existing tools on real production test cases. If those numbers hold, the interesting shift is from code generation to debugging, testing, and observability after code ships.