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

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

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

I’ve been seeing coding models move beyond simply generating... code, and IQuest-Q1 caught my attention. It’s a large, code-focused model built for developers, with a focus on stable performance across multi-scenario task evaluations. IQuest is evaluating it across four practical scenarios: → Building complex interactive applications through a game demo → 3D scene + spatial generation through a park-navigation style demo → Code diagnosis + repair → Complex work-task execution involving multimodal information + tools The final demo videos for all four scenarios will be available at release. I’m curious to see how IQuest-Q1 performs across these different workflows and what the demos reveal about the model’s capabilities. #coding #LLMshow 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 fx, a tiny, open, native coding agent from... Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑show more

grokbot it's an agent with its own identity, its... own computer, and it stays on when you're not here's what "active AI employee" actually looks like in the demo: - chief of staff agent - checks in on your other agents, reads your calendar, dispatches tasks to the right one automatically - shopping agent - logged into your accounts, books tickets, buys groceries, reports back - marketing agent - signed into your actual linkedin, browses your past posts for tone, then writes and publishes a new one on its own - engineering agents - self-triage bug reports, kick off cloud coding agents, come back with a pull request, a screenshot, and a video of the fix the interface isn't a dashboard, it's a chat - same shape as texting a coworker, no tool calls to babysit the number that matters more than any of the demos: grok 4.6 scored 70.8% on cursor bench at $2.81 a task, fable 5 max scored 70.5% at $17.32 same capability, 6x the cost difference - that's the unlock that makes running a fleet of these actually affordable instead of a noveltyshow 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

you don't need to re-explain your codebase's architecture to... your agent every session. most tools stop at telling you what broke. sentrux is a real-time architectural sensor, it watches your codebase as a live treemap and turns file structure and dependencies into one continuous quality score. the loop is simple: codebase > agent scans structure and dependencies > sentrux scores 5 root cause metrics into one signal > agent sees exactly where risk concentrates > next session starts from a live map instead of a blind grep the binary carries zero built-in language knowledge, all 52 languages live in plugin.toml and tags.scm query files, so a new language needs zero rust code. small catch: it only scores the structure, it won't tell you why the cycle happened, that part's still on you. built pure Rust with no runtime dependencies, specifically so it could sit as one binary between an agent and a codebase without adding friction.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

I made this for Sentry Hackweek. I'll be doing... a deep dive soon, but it's a personal recorder that sends my transcripts to a router that determines if the text is a simply a todo, reminder OR if it's work. If it's work, Pi agents get started in it right away, coding or just doing research. Built using: ESP32-S3: 1100mAh Battery: for all agent work for deterministic workflows, automations to help design the case + a ton of sandpaper to get it smooth. Also a adafruit mic on thereshow more

so tired of wasting my time clicking through terrible... dashboards and UIs i strongly believe that everything should work directly from your agent so we built @lifi/cli for devs and agents who need access to onchain infra without navigating a ui everyone's been shipping mcp servers for onchain actions. and frankly, we did too. but i believe that a cli is even better for many uses cases it's less setup, more token efficient, works in any terminal, container, or ci pipeline and not just claude, codex or cursor. now you can swap, bridge, deposit, and literally anything else onchain from your terminal. ‘npx @lifi/cli chains’ to startshow 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

Own your personal agent, folks. Just built my own... little personal agent with Pi's Pi Durable. I wanted to see how quickly I could build an OpenAI dots clone with open-source tools. I am amazed at how quickly I got this off the ground. It's proactive. It keeps working when you're not watching. It remembers you, runs jobs on a schedule, waits for your approval, and uses its own computer. Pi Durable makes that possible. Every step is checkpointed. I can kill the process mid-task, and My Pi picks up right where it left off. Memory lives in durable documents. What My Pi learns about me in one Space survives a crash and carries over to every other Space. Approvals are durable too. It also has its own computer. Each Space gets a full Linux desktop that My Pi controls with screenshots, mouse, and keyboard. The model runs through OpenRouter, so I can swap models without changing anything else. That's all configurable however you like it. If you've been wanting your own personal agent, now is a great time to build one. I am building this as an experimental ground where I can test new ideas and experiment deeply with proactive personal agents. But I plan to open-source it after testing it a bit and adding more interesting primitives. The goal is to make it customizable and easy to build on, so others can experiment with their own personal agent functionalities.show more

Something just launched that makes VS Code feel ancient.... And im all in for it: Cline Desktop app, an open-source app for open-weight models (and you know how much i love open source) brings its coding agent into a standalone Cline Desktop app for Mac + Windows. Just open a project and tell it what you want to change. No need to open VS Code first. In Cline's demo, it adds priority filters to a task board, works through the code and runs the build. Glad to see the model choice stays open, too. You can bring your own API keys, use supported open-weight models and even switch models halfway through a project!show more