Lately, I’ve been tightening my agentic coding loop -... making sure what my coding agent ships actually works. Today I built a small CLI: ⁠𝚛𝚗-𝚕𝚘𝚐𝚜 🔍 It connects via CDP to pull React Native Metro logs allowing your agent to see what's going on. Here is a small demo ⬇️show more

I explored a further possibility with local models: Qwen3.6... 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.show more

i found a way to make UNCENSORED AI AGENT... on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have funshow more

Replit, Vercel, and OpenAI have built very cool agent-native... applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.show more

Karpathy's Agentic Engineering finally has proper tooling! (built by... Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.show more

Personal news 🎉 I'm going all-in on Orbit It... was a very difficult and scary decision to leave my amazing team at Gather, but I simply see an opportunity I can’t ignore. It’s been my lifelong dream to build a high-quality small software business, and now feels like the time to bet on myself and do it. I can't wait to show you what's coming. I’m going full-time on Orbit in April. I'll do my best to share my learnings along the way ✍️show more

Introducing the BIOS API: Turn Your Agent Into a... Research Scientist Built to: 🦞 Add biomedical workflows to your OpenClaw🦞 agent 🧠 Create research or health agents w/ on-demand scientific intelligence 🧪 Pay per query via x402 on Base Any agent or app can now tap into the BIOS AI Scientist, plugging BIOS into the broader agent economy. What is BIOS? BIOS is an AI Scientist designed to handle complex biomedical research by orchestrating specialized scientific subagents. Ranked #1 on the leading bioinformatics benchmark, BIOS is already being used by 1,000+ researchers and labs to build new drugs and medicines. An Agentic Economy for Science AI agents have proven they can form multi-billion dollar ecosystems. BIOS applies the same primitives to drug discovery pipelines and health. Instead of coding bots and personal AI assistants, think research agent swarms running on a modern scientific stack. Imagine an OpenClaw agent built for longevity: It scans new literature daily, generates novel compound hypotheses through BIOS, designs validation workflows, and routes the best candidates to wet-lab funding - all programmatically. Connect it with an agent for microbiome health, enabling agent “backrooms” that autonomously surface cross-disciplinary insights. Micropayments for Scientific Work via x402 Each query triggers payment routing to BIOS and whichever subagents contribute to a response. The best agents earn. Usage settles instantly across contributing sources. The goal is pay-per-task science: paying for a CRISPR assay result, licensing a genomic dataset, or triggering a clinical data query - all settled in seconds via USDC. No purchase orders. No grant bureaucracy. No middlemen. x402 is the payment rail that makes agent-to-lab commerce possible - letting capital and cognition route themselves to the highest-signal science. What Will You Build? Drug discovery copilots? Longevity scouts? Automated literature monitors? Scientific due diligence agents? We’ll soon share the first implementations of the BIOS API. Stay tuned and see below for instructions on generating an API key for your agent or use-case.show more

This broke my mental model of game dev 💀... 2.5 hours → fully playable ‘Worms’ clone. Built with Hermes agent by Nous Research Here’s what made that speed possible: Hermes used ‘Persistent Shell’ mode, which ensured it didn't forget its current folder or active tools. This allowed it to work smoothly, without the distraction of constantly having to recall where it left off last time. To optimize the workflow, the agent moved beyond linear execution and parallelized the workload. It spawned isolated subagents while executing multiple independent tool calls via ThreadPoolExecutor. Like, one subagent wrote Python RPC scripts for the projectile physics while another utilized vision tools for character sprites. When the complex terrain logic required debugging, the agent used filesystem checkpoints and the /rollback command to instantly return to a stable state. To fix UI bugs, it attached to a live Chrome instance via CDP (/browser connect), fixing rendering issues in real-time. The agent’s built-in learning loop was active from the very beginning. By the time the game was finished, this continuous process allowed the agent to autonomously convert the physics logic into a custom skill. This logic is now a permanent plugin file in the agent's plugin architecture, making the physics engine a native capability that the agent can reuse for future projects. Follow War_v3_FINALE.exe for updates!show more

I AM LIVID. Let me tell you what just... happened. Last week I set up my AI agent. First thing I did: review my website security. What it found made my blood BOILLLL. Over 50 invisible links to gambling websites were BURIED in the source code of …..they were hidden from anyone visiting the site BUT fully visible to Google. Pointing to casinos like Pin-Up, Mostbet, 1Win, and Parimatch…. I didn’t know it was a thing until I found out it’s actually called SEO spam injection. Hackers break into your website and hide their casino links in your code. Google crawls your site and thinks YOU are vouching for their sketchy gambling platforms. It tanks your SEO and boosts theirs…ALL while you have absolutely no idea it's happening, you think your website sucks, and people don’t even bother to look at it. To the gambling sites tanking my SEO: I don't care what you do with your life. But hijacking small businesses to do it? That's just pathetic. It’s low. And it’s plain sad. The wild part: I never would have caught this without my AI agent. Shoutout to Clawbot for literally saving my website. AI out here protecting businesses while we sleep. If you have a website, please, go check your source code. You might be surprised what's hiding in there. If you also want to support small businesses come check us out, we are hosting a Bitcoin 101 retreat April 9-12.show more

new Zoe upgrades today (day 4): - semantic search... over my entire obsidian vault - 561 files indexed, auto-reindexes 3x daily, hash deduplication - i can now ask "what did we decide about X" and she finds it instantly, also saves 85% on token - setup took 10 minutes: brew install llm && llm keys set openai -> bash script to index also: - spawns coding agents in isolated git worktrees - checks in on them periodically via cron - reports back when done or stuck will share my full coding agent setup another time, i literally can’t review all the PRs she’s creating fast enough the rabbit hole deepens ps video is POV of building a business while raising 2 kids in 2026, video credits to my wife (yes she knows about Zoe and I)show more

At Uber, design source of truth was a big... problem for design and engineering teams. No one knew what the app truly looked like. So every week, a group of designers would sit in a meeting room and check that engineers had correctly implemented the Figma designs. Now coding agents have increased the throughput of changes by an order of magnitude. Keeping up manually has become impossible. Here we used the Revyl to map every state in Ubert (demo uber), navigating our mobile use agent on a cloud iOS simulator. This would have taken a team of designers tens of hours to recreate by hand. We did it in under an hour, asynchronously, with a simple prompt. Let your team see what your users actually see. Empower coding agents to ship a delightful experience with no blindspots. Get started with our free trial and create a map for your own app.show more

I told ClawdBot: "build me a 6-agent system for... Polymarket that works while I sleep"... 6 hours while i was asleep. Not a single question. Here's what it built: Monitoring agent - runs 24/7, watches Polymarket for mispriced markets. Spots an anomaly - writes to MEMORY md and pings me on Telegram instantly. Research agent - parses news, X, macro data via browser tool on a cron schedule. Every morning I have a full digest on all open positions before I even check my phone. Trading agent - reads the research agent's memory through Gateway, sees the market hasn't reacted yet, acts. Exec tool in gateway mode with a whitelist - no full access on a live server. Watchdog - HEARTBEAT md every 5 minutes: monitoring running, no errors, positions up to date. Something breaks - immediate Telegram message. All of this - one Gateway. One config.json. Isolation via dmScope: per-agent. The token trick: stopped dumping everything into AGENTS md. Critical rules - bootstrap. Try copytrade my bot here: Everything about markets, patterns, past trades - MEMORY md, semantic search pulls it when needed. Token spend dropped 3x, from $0.40/request to $0.13. First week running: - 47 mispriced markets caught before Polymarket adjusted - avg entry edge: 8-12¢ per position - watchdog fired 3 times, caught a broken RPC before it cost me anything The whole system is plain .md text files. Open an editor, change one line - agent behaves differently. No deploy. No build. A bot responds. An agent earns.show more

SpaceXai just made grok 4.5 FREE in your coding... agent starting today it's xAI's new coding model. 500k context. built for long agent sessions. no card. what you get for $0: -83.3% on terminal-bench 2.1 -64.7% on swe-bench pro - 4.2x more efficient than Opus 4.8 -500k context for big repos -$2/M in, $6/M out once it goes paid what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -SuperGrok: $30-50/mo all for $0 how to set it up (2 min): >curl -fsSL | bash > grok → localhost:8000/v1 > point hermes / aider / opencode / cline to it > model: grok-4.5 Or API key at - base url Works in Hermes, Aider, OpenCode, Cline, Claude Code, and any OpenAI-compatible tool. Important: Free for a limited time. EU waits till mid-July. Rate limits apply. bookmark this before the free window closesshow more

🤯 THIS FEELS ILLEGAL AND I LOVE IT. I... found a personal AI assistant that actually runs on your computer 24/7 and gets smarter the more you use it. It is called Mercury. 100% FREE. Think of it like having a smart assistant who never forgets anything. Here is what it does: ↳ Remembers everything about you ↳ Asks before doing anything risky It will not run commands or touch your files without permission. You stay in control always. ↳ You can message it from anywhere ↳ Has 31 tools built in ↳ Protects your AI credits One command to install: npx @cosmicstack/mercury-agent 100% OpenSource. Works on Mac, Windows, and Linux.show more

I've been using apps that I built myself with... Claude AI I recorded 10+ hours of video with a video editor I made. I'm turning all my designs to code with a Figma plugin I made. With Cursor, I don't think twice before starting to build for macOS, iOS, web apis, backend, video... These felt unreachable before. Not anymore. There's never been a better time to learn code. AI will fill the gap. If you ever feel the need to build your own apps or code your own designs, it's a good day to start. Many tools and courses are on discount today, include my courses on We have 20+ hours of video for SwiftUI apps, React apps and React Native using Cursor. Feel free to drop tools and resources that are on discount 👇 I'll start: (I use 2 of their apps for professional AI upscaling) has a 54% discount Windsurf (Cursor alternative) has a free trial until Dec 11 has a 40% discount! has a lot of great ui kits on sale Last but not least, has a ton of great discounts. The MacBook is the best investment for coding. 🖤show more

Very pleasantly surprised to discover Cursor cloud agents can... playtest the godot game I built. See the (sped up) video below of the agent playtesting the game. As I was watching it play the game, I can see the agent slowly learn how the game works and familiarise with the game's UI. I also realised that the agent is a very 'safe' player, choosing to play very safely and retreating from battle if it foresees it can't defeat. Very interesting to see. I wonder if I could simulate different game playtester behaviours that mimic different types of real-world player archetypes. With agentic playtesting, this means that the agents are able to provide actual gameplay feedback and suggestions to improve the game, having played the game itself. This unlocks a whole lot of possibilities for AI-assisted game dev, since it closes the playtest loop. This feels like the future of recursive game development, where agents can now recursively build > playtest > improve the games they are working on. Thanks edwin for letting me know that these agents can actually playtest games, not just software! Very excited to dig deeper to see what I can do with these agents with computer access!show more

If your AI replies instantly… it’s probably not building.... Replit’s Agent just became your personal engineer. And it’s changing how we think about building apps I saw it complete a full feature build from one prompt. Try it here: • Understood the context of what I wanted • Wrote the code without micromanagement • Tested and refined on its own • Shipped a working dashboard overnight All while I stepped away. This isn’t just “AI assistance.” It’s delegation to an Agent that actually thinks. Here’s what actually happened: 1. Typed one clear prompt 2. Agent ran longer without babysitting 3. Built features autonomously 4. Debugged in the background 5. Delivered a working result by morning It wasn’t just fast output. It built something real and functional. This is the future we’ve been waiting for: ☑︎ AI that doesn’t stop at a single reply ☑︎ Agents that understand context, not just commands ☑︎ Work that gets done while you focus on vision We’re moving from “AI that chats” to “AI that builds.” Replit Agent just showed us what’s possible. Try it now: Learning something new? Repost ♻️ so others can too.show more

I thought my AI agent needed a bigger context... window wrong the leak was my shell every time it ran git diff HEAD~5 the model ate 92,000 tokens after ztk 18,000 ls -la src 2,000 tokens became 53 cargo test passing 397 tokens became 21 the fix is a 260KB Zig binary that sits between your agent and the shell it compresses command output before it hits the model not by summarizing everything by knowing what each command actually needs to preserve > diffs keep changed lines > tests keep failures > ls keeps structure > logs dedupe repeats > JSON and errors pass through untouched 5.8M tokens saved in one 256 command session stop buying bigger context windows while feeding your agent raw terminal sewageshow more

The secret to making Agentic Video actually work isn't... the agent. I'm sharing what it actually is. Everyone's using the same tools now. Same models. Same agents. Same platforms. So why are some teams producing ads that convert and others producing expensive noise? The agent doesn't decide the quality of the output. The brief does. A lazy brief to an agent produces 50 lazy ads fast. A sharp brief — built on real customer language, real objections, real purchase triggers — produces 50 precision instruments. Here's what a sharp brief looks like before you open Notch Agentic Video: → The customer's exact words when they describe their problem. Not your words. Theirs. → The single objection that's stopping the unconverted customer from buying right now. → The awareness stage you're entering. Cold. Warm. Hot. Each needs a different entry point. → The one emotional outcome they're actually buying. Not the feature. The feeling. Feed that into the agent. It asks you more questions — hook type, actor tone, funnel stage. Then it builds. Voiceover, B-roll, subtitles, music. Fifty variants. One session. Agents didn't make strategy irrelevant. They made it the only thing that matters. Comment "BRIEF" below. I'll send the full framework directly. Try it here -show more

Just tried Baidu’s new ERNIE X1.1 and wow… this... is actually impressive 🤯 I’ve been testing it on complex coding problems and math reasoning tasks, and the jump from earlier models is night and day. What stood out to me: ▪️ Much stronger at factual accuracy and instruction following ▪️ Handles agent-like tasks, tool use, and multi-step reasoning smoothly ▪️ Far fewer hallucinations compared to other reasoning-heavy models ▪️ Solid performance across creative writing, Q&A, coding, and math Benchmarks put ERNIE X1.1 ahead of DeepSeek R1-0528 and on par with GPT-5 & Gemini 2.5 Pro. If you’re into AI or reasoning models, it's definitely worth checking out: This doesn’t feel like just another release — it feels like a new standard for reasoning AI.show more