We open-sourced iron-proxy yesterday: a default-deny egress proxy for... untrusted workloads. CI is a natural place for this. GitHub Actions runners have unrestricted outbound network access by default. Every dependency, every post-install script, every agent tool call can reach any endpoint on the internet. iron-proxy sits between the runner and the network. Allowlist what should talk to the internet. Log everything. Block everything else. Repo: Walkthrough 👇show 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

Introducing the Agent Virtual Machine (AVM) Think V8 for... agents. AI agents are currently running on your computer with no unified security, no resource limits, and no visibility into what data they're sending out. Every agent framework builds its own security model, its own sandboxing, its own permission system. You configure each one separately. You audit each one separately. You hope you didn't miss anything in any of them. The AVM changes this. It's a single runtime daemon (avmd) that sits between every agent framework and your operating system. Install it once, configure one policy file, and every agent on your machine runs inside it - regardless of which framework built it. The AVM enforces security (91-pattern injection scanner, tool/file/network ACLs, approval prompts), protects your privacy (classifies every outbound byte for PII, credentials, and financial data - blocks or alerts in real-time), and governs resources (you say "50% CPU, 4GB RAM" and the AVM fair-shares it across all agents, halting any that exceed their budget). One config. One audit command. One kill switch. The architectural model is V8 for agents. Chrome, Node.js, and Deno are different products but they share V8 as their execution engine. Agent frameworks bring the UX. The AVM brings the trust. Where needed, AVM can also generate zero-knowledge proofs of agent execution via 25 purpose-built opcodes and 6 proof systems, providing the foundational pillar for the agent-to-agent economy. AVM v0.1.0 - Changelog - Security gate: 5-layer injection scanner with 91 compiled regex patterns. Every input and output scanned. Fail-closed - nothing passes without clearing the gate. - Privacy layer: Classifies all outbound data for PII, credentials, and financial info (27 detection patterns + Luhn validation). Block, ask, warn, or allow per category. Tamper-evident hash-chained log of every egress event. - Resource governor: User sets system-wide caps (CPU/memory/disk/network). AVM fair-shares across all agents. Gas budget per agent - when gas runs out, execution halts. No agent starves your machine. - Sandbox execution: Real code execution in isolated process sandboxes (rlimits, env sanitization) or Docker containers (--cap-drop ALL, --network none, --read-only). AVM auto-selects the tier - agents never choose their own sandbox. - Approval flow: Dangerous operations (file writes, shell commands, network requests) trigger interactive approval prompts. 5-minute timeout auto-denies. Every decision logged. - CLI dashboard: hyperspace-avm top shows all running agents, resource usage, gas budgets, security events, and privacy stats in one live-updating screen. - Node.js SDK: Zero-dependency hyperspace/avm package. AVM.tryConnect() for graceful fallback - if avmd isn't running, the agent framework uses its own execution path. OpenClaw adapter example included. - One config for all agents: ~/.hyperspace/avm-policy.json governs every agent framework on your machine. One file. One audit. One kill switch.show more

i just open sourced the workflow behind $2M AI... video productions... i built 7 skills that run the pipeline end to end, built for Seedance 2.5 and they work in Claude Code, Codex, Hermes or any harness (works best with 1080p using Higgsfield CLI) here's how to use them, in order: /setup writes which image and video models you run into your project, once, so every skill reads the same stack /studio-init scaffolds the whole studio as a file tree from one question, the project name /film-breakdown walks your script scene by scene and writes a 22-field card for every shot /reference-board locks your references into a visual bible, a caption on every image and a ban list for the rest /asset-passport writes the exhaustive descriptor every later prompt will quote word for word /stress-test combat-tests each asset and flips it to locked only at 10 out of 10 repeatability /shot-prompt refuses to run until everything in frame is locked, then writes the 15-block prompt and logs every attempt get access to the skills and full breakdown of the pipeline in the article below:show more

On August 2, the EU’s strictest AI rules came... into full force. Any artificial intelligence used for hiring, credit, medical devices, or critical infrastructure must now be transparent, accurate, and open to human review. Fines can reach 7% of global revenue. Banks have to explain every loan refusal made by an algorithm. Hospitals must log every diagnostic suggestion an AI offers. Job applicants filtered out by a machine can now demand a real person look at their file. The era of unaccountable AI is closing, and the rest of the world is already copying the blueprint.show more

EVERYONE'S TRYING TO SOLVE AI TEAM MEMORY WITH SERVERS,... VECTOR DATABASES, AND ORCHESTRATION PLATFORMS. THIS OPEN SOURCE TOOL DOES IT WITH ONE FOLDER IN YOUR REPO. Every dev on your team runs Claude Code. When one agent screws something up, the rest have no idea. They just repeat the mistake next week. It's called teamlore. When your agent gets corrected or breaks something, it writes a small lore file into a .lore/ folder. That file ships with your PR, gets reviewed like normal code, and after merge every teammate's agent automatically recalls it when they touch that part of the repo. No server. No datab No accounts. No SaaS bill. Just a folder in git. Which means code review catches bad lessons before they poison the team, git blame tells you when a rule was added and why, and the whole thing works offline. One command to install: npx teamlore init Companion command: npx teamlore scarmap. Turns your team's history of mistakes into a visual heat map of the codebase. Every red zone is a place your team has been burned before. Which means every red zone is a place your agents should slow down. Here's the wildest part. The teamlore repo's own .lore/ folder contains every mistake Claude made while building teamlore itself. Dogfooded end-to-end. You can literally open the folder and read the receipts. The author's public invitation: "Would love for someone to try and break it." Available on npm. Repo just launched. 100% open source. (link in the comments)show more

A massive repository with end-to-end examples of AI applications... with React! Together with MCP and A2A, the Agent-User Interaction Protocol (AG-UI) is the third piece that will help you build user-facing AI agents. This GitHub repository will give you access to a bunch of examples showing you how to build the following: • Real-time updates between AI and users • Shared mutable state between agents and users • Tool orchestration • Security boundaries • UI synchronization In every one of these examples, you'll get the following: • Client sends a POST request to the agent endpoint • Then listens to a unified event stream over HTTP • Each event includes a type and a minimal payload • Agents emit events in real-time • The frontend can react immediately to these events • The frontend emits events and context back to the agent Check the link in the next post:show more

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic... shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.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

🚨 Alibaba just open sourced a GUI agent that... lives inside your webpage and controls it with natural language. It's called Page Agent and it's not a browser extension. It's pure JavaScript no Python, no Puppeteer, no headless browser, no screenshots. Just one script tag and your web app understands natural language. Here's what it actually does: → Embed it with a single tag or npm install → Control any web interface with plain English commands → Text-based DOM manipulation no OCR, no vision models needed → Bring your own LLM (GPT, Claude, Qwen, anything) → Ships a built-in UI with human-in-the-loop support → Turn 20-click ERP/CRM workflows into one sentence → Optional Chrome extension for multi-tab agent tasks → Works on any web app SaaS, admin panels, internal tools Companies are charging $30/month for AI copilots built on this exact idea. This is 3 lines of code. Your users. Your interface. The AI copilot layer for every web app just got open sourced. 1.6K stars. 100% Open Source. (Link in the comments)show more

The Visual Studio Code insiders version that just shipped... and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.show more

🚨🚨BREAKING NEWS 🚨 🇾🇪🇸🇦 Houthis Hit Saudi Soil Hours... After Riyadh Strikes! Tehran’s Proxy Message Just Got Louder Houthi forces claimed responsibility Saturday for a missile attack on Jizan in southern Saudi Arabia, hours after Saudi-led strikes hit Houthi sites in Hodeidah and Kamaran Island. Saudi authorities briefly issued emergency warnings for Jizan and Yanbu before lifting them. The Iran-backed group said the attack caused fires and framed it as direct retaliation. This is not just another Yemen exchange. It is Tehran testing how far it can push Riyadh through its most active proxy while the wider regional conflict continues. The Houthis have already targeted shipping and threatened Saudi ports. Striking Saudi territory itself raises the cost of any restrained response from Riyadh. For the United States and Israel, the pattern is familiar: Iran avoids direct confrontation while using proxies to stretch adversaries, complicate coalitions, and keep pressure on energy routes. Every successful Houthi strike reinforces that strategy. The question now is whether Saudi Arabia absorbs the hit or decides the proxy pressure has gone too far.show more

Why the internet needs Grokipedia? ➤ Wikipedia isn’t the... neutral source of truth it once was. It’s been taken over by far-left activists and often used as a propaganda tool, not an unbiased encyclopedia. ➤ A lot of AIs today get their info from the internet, but the web is full of unfair views, wrong facts, and tons of junk. ➤ Grokipedia will be an open-source encyclopedia focused solely on TRUTH. ➤ Grokipedia won’t be controlled by any activist or political bias. ➤ It will be open-source and free for all to use, a truly public resource without limits. ➤ xAI’s ultimate mission is to understand the universe, and that requires honest, unfiltered information. Grokipedia is a crucial step toward that goal, because you can’t build a truthful AI on biased information. ➤ The vision is for Grokipedia to become the global standard for knowledge. One day, every person and every AI system could rely on it as a trusted source of truth. ➤ Seeking truth is the greatest mission of all and that’s what Grokipedia stands for. Grokipedia is coming.show more

How ICP Token Holders Can Literally Vote To Upgrade... The Internet Computer? Most blockchains rely on developers and node operators to coordinate when the protocol needs a major upgrade. The Internet Computer (DFINITY Foundation) takes a different approach. Its Network Nervous System, or NNS, puts governance directly onchain. Here is how it works: 1. ICP HOLDERS LOCK TOKENS INTO NEURONS internet-computer:native holders can lock their ICP into a “neuron.” A neuron is essentially a governance position that gives the holder voting power over NNS proposals. Voting power depends mainly on: • The amount of ICP locked • The neuron’s dissolve delay • The age of the neuron The longer a holder commits their ICP, the greater their potential voting power. 2. NEURONS VOTE ON NETWORK PROPOSALS The NNS allows neuron holders to vote on proposals affecting the Internet Computer. These can include: • Protocol upgrades • Subnet changes • Network configuration • Node provider decisions • Governance parameters • Changes to the network’s underlying software This is where the system becomes particularly interesting. NNS governance is not simply deciding how a community treasury should spend money. Some proposals can directly affect how the blockchain operates. 3. VOTING CAN TRIGGER ACTUAL PROTOCOL CHANGES A successful proposal can instruct the network to adopt an approved change. For example, NNS proposals can be used to upgrade the replica software running across Internet Computer nodes. Once the proposal is approved, the NNS can coordinate the upgrade across the network. That means token holder voting can ultimately result in the protocol itself changing. 4. HOLDERS DO NOT HAVE TO VOTE ON EVERYTHING The NNS also uses a system known as liquid democracy. Neuron holders can choose to follow other neurons for particular proposal categories. When the followed neuron votes, the follower can automatically vote in the same direction. This creates a delegation system without requiring users to give up ownership of their ICP. In simple terms: • Stake ICP • Create a neuron • Choose your voting preferences • Vote yourself or follow another neuron • Earn rewards for participating 5. GOVERNANCE PARTICIPATION CAN EARN REWARDS The NNS gives users an economic incentive to participate. Neurons can accumulate maturity through governance participation. That maturity can later be used to generate new ICP. This turns governance participation into more than just a voting mechanism. It becomes part of the network’s economic design. 6. THE NNS IS ITSELF PART OF THE INTERNET COMPUTER This is arguably the most important part. The NNS is not simply a website where the community discusses proposals. The governance system itself runs on the Internet Computer. Its rules, proposals, neurons and governance decisions are handled through onchain infrastructure. That allows governance decisions to become executable actions. 7. WHY THIS MATTERS FOR PROTOCOL UPGRADES Traditional blockchain upgrades can require significant coordination. Developers may need to release new software. Node operators need to install it. Validators or miners need to support it. Exchanges and infrastructure providers may also need to update their systems. If coordination fails, competing versions of the blockchain can emerge. The NNS is designed to reduce some of that coordination problem. The community can approve a proposal through onchain governance, and the network can then execute the approved change. 8. IT IS NOT ONE ICP TOKEN, ONE VOTE Simply holding ICP does not automatically give someone governance power. Users need to commit their tokens through a neuron. And voting power is not based solely on the number of ICP held. Factors such as dissolve delay and neuron age also influence voting power. This means the system rewards committed participation rather than treating every wallet as an identical vote. 9. SO WHAT MAKES THE NNS DIFFERENT? The key difference is that governance is built into the protocol itself. On many blockchains, governance can look like: Community discussion → Vote → Developers implement the decision. The Internet Computer aims for something closer to: Stake ICP → Vote through NNS → Proposal passes → Network executes the change. The NNS is designed to make governance part of the Internet Computer’s operating machinery. ICP holders therefore have a direct role in deciding how the network evolves. Under the right proposal, their votes can ultimately determine which software the network runs.show more

It’s come to our attention that another community host... has decided to ban players for competing in 6ix Arena. We want to make our position clear: we will never punish players for where they choose to play. Competition makes everyone better — players, leagues, and the community as a whole. Every player is free to compete in 6ix Arena and anywhere else, at the same time, with no conditions. That will never change. To any player affected by this decision: our doors are open. You’ll always have a home here. We wish EVERY league and EVERY player success. The community is big enough for all of us as it has been for the last 10 years. -Dangershow more

$35 OF FREE CLAUDE OPUS 5 CREDITS FOR A... WEEK, NO CARD ANYWHERE • the credit > Sign up with Google and the trial activates on its own, nothing to claim manually: > Opus 5 sits alongside Opus 4.8, Sonnet 4.6 and Haiku on the same key. > The window runs a week from activation. • wiring it up > base url: > model id: claude-opus-5 > In OpenCode Desktop hit Ctrl+, and add a custom provider with the id aerolink. > The same key drops into Codex, Cursor and Claude Code with nothing else changed. One key, not locked to one client -> every tool that takes a custom OpenAI-compatible endpoint reads it the same way. It routes through a third-party proxy rather than an official Anthropic channel, so keep client work off it ↓show more

I think Covid broke everyone’s brains. The government got... caught in the biggest coverup/crime of all time, and now the most retarded people on Earth have been emboldened to claim EVERY SINGLE THING is a conspiracy theory. Just as bad as the MSM that we were supposed to replace. Every time you shitbirds make a bullshit conspiracy theory where there isn’t one, you discredit the ACTUAL conspiracies and crimes that are taking place, as well as the ACTUAL journalists who are reporting on the facts. Have some discernment and stop fucking up everything else for the rest of us.show more

this Hermes agent finds business owners asking for help... on Facebook and builds each one exactly what they asked for, on autopilot... Facebook is a goldmine, one google search string surfaces every owner asking for it. here's how agencies & freelancers can land clients: - watches facebook for owners asking for help, any phrasing - one google search string pulls every match, city by city - reads what that owner actually needs, then sources it - grabs their real photos + brand straight off their page - builds exactly that: a video, creatives, or a website - sends the finished build back before a competitor replies every step from facebook post to finished build is automated. reply "AGENT" + RT and i'll send you the full breakdown so you can build this too (must be following so i can DM)show more

encrypt every chat with this open sourced repo 18... year old just killed the encryption problem it's called conversation-steganography you type a secret and a local AI buries it inside a dead boring chat about coffee, etc. then you send that through any normal messenger your friend runs the same tool and the small talk unfolds back into the real words > the secret is locked with AES-SIV before it ever becomes text > the cover message is written by a model on your own machine so nothing touches the cloud > it rides through whatsapp telegram imessage even plain email > every message is cryptographically chained so tampering shows instantly whatsapp sees you planning dinner your isp logs small talk the real sentence was never in the data at all quietly one of the most dangerous repos i have seen all month repo in replyshow more