Agent Handoff: watch a task move through four agents... while the handoff log fills in below. the pulse on the working agent is plain css. the card updates a lot during a run, and putting that pulse in motion kept restarting it mid-loop.show more

Self-improving agents are here. 🧙‍♂️ Every agent run creates... a skill.md with reusable learnings. The next agent uses it to do the same task faster, cheaper, and more reliably. Watch the second agent crush it:show more

Devin for Terminal is a local agent that works... with all frontier models, including Opus 4.7, GPT 5.5, and SWE-1.6. You can switch model mid-session, or handoff to Devin in the cloud.show more

Agent Plan: A component to review and the run... the agent plan, designed in Paper, animated with Motionshow more

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS... LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already doshow more

Today we shipped Handoff in the Codex app: a... simpler way to move a thread between Local and Worktree.show more

AGENT ARCHITECTURE ROUTES WORK. IT DOES NOT REMEMBER WORK.... THAT GAP IS WHY YOUR LOOP KEEPS FIXING THE SAME BUG TWICE. these are two different engineering problems. every agent that silently drifts is missing one of them. architecture answers what runs. harness → loop → graph. it defines the tools, the retries, the branching routes, the approval gates. context ops answer what the run knows. write → read → compress → isolate. it defines what gets saved between attempts, pulled in on read, summarized on overflow, and split across sub-agents. for two months i believed a solid harness plus a verifier loop was enough. my coding agent kept re-discovering the same test failure across retries. the loop was working. it just had nowhere to write what it had already learned. here is the decision rule: if your agent forgets across restarts, add write and read. if it stalls on long tasks, add compress. if two sub-agents step on each other, add isolate. architecture without context ops is a well-routed system with amnesia.show more

🤖 Try Autopilot (Preview) in VS Code! With Autopilot... enabled, the agent stays in control of the workflow. It can run tools, retry on errors, and continue working until the task is complete. Learn more:show more

Users can explore how different AI agents analyze the... same market task and compare their outputs through the platform. It is a product experience built around agent performance, task execution, and real usage. AI agents are becoming measurable digital workers.show more

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an... all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!show more

AAA studios spend $200M on a city this good.... Ours cost $1,500 and swapped Miami for SF within a week. An agent did it in a loop while we slept, now he's working on the traffic and pedestrian.show more

What's a meta-agent? It's an agent that manages other... agents mid-task. It can intervene, rewind, fork & audit them as they work – think "git for agents". It's also the emerging layer between you & your agents, a new interface for human-AI interaction! Here's what it unlocks🧵show more

Stripe Cards are now officially live on ClawVault If... you're building agents that need to pay for things — APIs, SaaS, cloud, subscriptions, contractors — your agent can now get its own Visa card. Not a restricted virtual card on limited rails. A real Visa, powered by Stripe, accepted at every merchant on the internet. Spending limits. Merchant locks. Expiry controls. And that's just the defaults — the full rules engine goes deeper. Your agent spends freely within the rules — break one, and the charge gets flagged for your approval before it goes through. No other platform gives your agent a card and keeps you in control at the same time. Every AI agent will need a card. Every card will need a control layer. We built both. Now on Stripe. Your agent gets the card. You keep the control.🦞show more

AI agent usage on SQD Portal is up ~200%... in recent weeks. A dev from our community chat was scraping a wallet UI with Hermes. Mid-task, DeepSeek reasoned its way out of it: "I can use SQD Portal's Hyperliquid fills data directly — much more complete than scraping a UI with infinite scroll." No prompt engineering. The model just chose the better and faster path. This is the loop we wanted: Agents pick SQD because it's faster → devs see agents picking SQD → devs ship faster → more agents pick SQD The picks-and-shovels moment for AI x onchain is here.show more

Stanford researchers did it again. They just built the... agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.show more

Alright, now that we know *what* an agent is,... how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.show more

whoever leaked this has bigger balls than sense Google... Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓show more

A dragon boat glides through jade-like waters in southern... China’s Shunde — poetry in motion, where Chinese aesthetics meets the river’s pulse. 🛶show more

Smol tip: /𝚏𝚘𝚛𝚔 is perfect for mid-task side quests.... It spawns a subagent that inherits the whole conversation, runs in the background while you keep working on your main quest, and comes back with an update.show more

I set a Ralph loop using agent-browser + Parallel... Web Systems to do a ton of market research. Perfect way to have an agent working while I do other things. Decided to setup my iMac for a lot of the looping tasks because it makes it easier to keep the repo clones and work product separated.show more

BREAKING 🚨: Anthropic is working on the Agent Mode... for Claude! "Button in a toggle that changes between classic chat experience and a more complex agent mode experience" And a new pixel style avatars 👀show more