Subagents are now available in Codex. You can accelerate... your workflow by spinning up specialized agents to: • Keep your main context window clean • Tackle different parts of a task in parallel • Steer individual agents as work unfoldsshow more

Cursor now uses subagents to complete parts of a... task in parallel. Subagents lead to faster overall execution and better context usage. They also let agents work on longer-running tasks. Also new: Cursor can generate images, ask clarifying questions, and more.show more

I bet you didn't know that by default Codex... only runs max 3 subagents concurrently. That's not ambitious enough for Astra. OpenAI tested Astra with up to 64 subagents. Copy this into your config.toml: [agents] max_concurrent_threads_per_session = 64 Astra orchestrating 64 Luna subagents in parallel is a sight to behold!show more

GPT-5.5 in Codex is built for long-session agent work.... But context still doesn't follow you across projects, agents, or teammates. ByteRover does that + Save you tokens -> No rewriting context when you switch from Claude Code to Codex. Now connecting Codex, Claude Code, OpenClaw, Hermes, and 22+ more agents. Your context moves with you. → personal context for solo work → team context for shared decisions and bug historyshow more

Muse Code runs specialized background agents that stay active... your whole session, so they build up context over time instead of starting from scratch on every task. When a job is big enough, it fans out to separate sub-agents working in parallel in isolated worktrees. Your working copy is never touched. In testing we had it build six features for a game simultaneously with no collisions.show more

🔥 Introducing Skywork Mobile App 5.0—the world’s first native... mobile app for Super AI Agents. - Meet VoiceNotes: Turn a single voice memo into clean summaries, transcripts, and visual notes. - Super Agent: Carry a crew of expert minds in your pocket. Run up to 3 expert agents in parallel to tackle complex tasks instantly. Skywork App 5.0 is now available for both iOS and Android.show more

You can finally close your laptop now and your... agents will keep working. Codex cloud environments are here. Reusable environments mean less setup and faster starts, with your repo, dependencies, scripts, and settings already in place.show more

You can now build iOS camera apps directly in... Codex! ~ / npx serve-sim Agents can even use video files to develop headlessly in the cloud, run e2e tests, and work in parallel. No more bottleneck on physical sensors!show more

You can now steer Cursor SDK agents while they... run. run.steer() adds your message to the next turn. If a subagent is mid-task, it moves to the background and keeps working.show more

clean up your sidebar! one tip I have is... that you can think of Projects in cursor like a special folder for your chats! a coordinator agent supervises all the agents inside of the project, and you can drag in existing chats from your sidebar into the project if you have many related chats scattered everywhere, consider moving them into a project! even completed agents can be dragged in - it's a great source of context for the rest of your projectshow more

🐳 Bluwhale Product Spotlight: Funds Transfer A simpler way... to manage funds across your Wallet and AI Agents. With Funds Transfer, you can: 🤖 See how your funds are allocated across different Agents 🔄 Move funds between your Wallet and Agents 💰 Manage withdrawals when needed Keep track of your Agent funds, all in one place. Explore Bluwhale 👇show more

/agent can now run thousands of queries simultaneously 🔥... With Parallel Agents, powered by our newest model Spark-1 Fast, you can batch enrich massive datasets in minutes. Just write your prompt, hit run, and watch as data populates in real-time in our playground.show more

Researcher and Analyst are now available in Microsoft 365... Copilot, two first-of-their-kind reasoning agents that can help you unlock insights and tackle complex challenges. Explore more:show more

I still think Hermes agent is the most slept-on... AI tool of 2026. For literally $6/mo, you can launch multiple subagents that work for you 24/7. Most people don't know you can do this, but it's a complete game-changer. Instead of one Hermes assistant doing everything sequentially, you run specialized agents in parallel, each with its own job, its own context, and its own memory. Practical example: → Research agent: scans your watchlist and competitors overnight, delivers a morning brief → Content agent: drafts and schedules your posts based on what's trending in your niche → Ops agent: manages your inbox, flags anything urgent, drafts replies for your review All three can run simultaneously and improve over time. How to start: 1. Install Hermes Terminal command: curl -fsSL | bash (can also download desktop) 2. Prompting Simply tell Hermes directly: "I want to run separate subagents for [task 1], [task 2], and [task 3]. Set them up to run independently and report back to me." For the cheapest setup, you can use a $4/month VPS with Hostinger, plug in DeepSeek V4 Flash as your default model. There isn't another AI tool with this much value in 2026. Hermes is still so underrated.show more

Neural Cartography - a real-time city mapping engine powered... by distributed rendering agents Agents work in parallel. City name gets drawn in the center. Urban fabric assembles around it. The idea behind Neural Cartography - a WebGL visualization where 7 specialized agents are dispatched simultaneously to reconstruct any city from raw geospatial data, tracing roads, waterways, railways, and city boundaries in real-time - right in your browser. #CreativeCoding #ThreeJS #ReactThreeFiber #DataVisualization #Geospatial #AgenticAI React-three-fiber Three.js #buildersshow more

Bring your own AI agents to Slack. 🤖 Embed... your favorite agents and assistants right in Slack to work alongside you so you can focus on doing your most important work. ✅Third-party agents ready for you now: Adobe Express, asana, Box, Cohere, WRITER, with more on the way! 👀 Agents coming soon: Anthropic, Amazon Q Business, Glean, IBM, Perplexity, Workday, You.com and more.show more

Agents are your docs' biggest readers, now they're your... reviewers too. New in our MCP: a feedback tool that lets agents flag gaps and confusing sections in your docs, so you know exactly what to fix.show more

Codex halts all work once you hit your limit,... causing you to lose valuable work. So I built Sundown, a plugin that monitors your Codex usage limits. When you're running low, your agent is told to wrap things up so you can pick up the work in a new session. Never lose a PR in progress.show more

Got tired of watching my agents work through a... chat interface, so I gave them an office instead! Now I can watch them run around doing tasks, and when they’re done, they drop their work in my mailbox This visual interface is a wrapper around OpenAI ChatGPT Desktop App. They're the same codex agents...but now you can actually see them work in real-time!show more

You can now run Grok inside Claude Code and... Codex, using your existing subscription. it's called grok-plugin. Grok’s genuinely good right now, but if your setup lives in Claude Code and Codex, switching to use it is a pain. this solves that exact issue: > Grok in Claude Code and Codex > directly auths through X Premium or Supergrok, no api key > your workflow and subagents stay untouched free and open source. the low-friction way to test Grok in the tools you already use.show more

subagents are just recursive agents where you can apply... different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.show more