No-Code Agentist

I built AXR because I hit a question I could not honestly answer: My n8n workflow said a booking had succeeded. But could I prove what it actually decided? Not to myself. Not to a customer. Not to an auditor. The execution log lived on my own server. That means I could edit it. And a log you can edit is not evidence. It is a story. So I built AXR: an open MIT-licensed protocol for tamper-evident, cryptographically signed execution receipts for AI agents and automated workflows. The idea is simple: Every consequential action gets a receipt. The receipt records: what the workflow received what decision-relevant node acted what it decided hashes of the inputs and outputs a hash of the code that made the decision the previous receipt hash an Ed25519 signature over the canonical record Receipts chain within a run. Runs chain across time. Change one byte and the signature fails. Delete one receipt and the chain breaks. Rewrite history and the Merkle anchor no longer matches. Anyone with the public key can verify the log independently. No access to my server. No trust in my database. No “please believe my dashboard.” Here is the part I did not expect: Deploying AXR on my own live production booking workflow found four pre-existing bugs. Not because AXR is a testing framework. Because honest records make silent failures loud. One bug was brutal: Every run was firing all three response branches. Success. Error. Conflict. A rejected booking still sent a success email. The workflow looked operational. The automation looked healthy. But the receipt’s final_status contradicted what the customer received. That contradiction made the bug obvious. Another bug returned unknown_error while echoing the customer’s own input back as the message. Another produced HTTP 200 with an empty body while the signed receipt showed a complete SLOT_TAKEN chain. Another bug was even more subtle: After a logic update, the workflow kept attesting the old logic version. The signature was valid. The claim was false. That led to a rule I now trust more than version labels: Version labels are testimony. Code hashes are evidence. AXR is not an agent framework. It is not an observability dashboard. It is not trying to make AI “truthful.” It proves one narrower thing: A given workflow, on a given input, made a given recorded decision — and the record has not changed since. That narrow claim matters. Because AI agents are starting to book appointments, price services, message customers, call tools, move records, and trigger side effects. When something goes wrong, the question will not be: “Did your dashboard say success?” The question will be: “Can an independent party verify what actually happened?” AXR is my answer to that question. The core uses boring primitives on purpose: SHA-256. Ed25519. Canonical JSON. Hash chains. RFC 6962-style Merkle trees. Signed Tree Heads. Independent verification. Two verifiers — Node.js and pure Python — have to agree on every accept and every reject. The Python verifier has its own canonicalizer and pure-Python Ed25519 verification. The project is open source, MIT licensed, zero runtime dependencies. And I am intentionally honest about the limits: Agent identity is still self-declared. Key storage is PEM-file-level, not HSM-grade. The production pilot currently runs the core + hourly anchoring profile. Some higher governance layers are specified, tested, and cross-implementation verified, but not yet exercised by the live pilot. That distinction matters. Security claims should not be inflated. They should be verifiable. The live browser verifier can check signatures, chains, Merkle roots, and witness data locally. Nothing is uploaded. No network request is made with your log. Drop in a log and verify it yourself. The larger thesis: AI agents do not just need logs. They need receipts. Because a log asks for trust. A receipt gives you something to check. Repo: https://t.co/OooMzjPUWO How it works: https://t.co/2KjcgtJ93D Verifier: https://t.co/dfEZrAuFjQ Feedback welcome, especially from people working on agent infrastructure, auditability, GRC, security engineering, n8n, MCP, SIEM, and AI governance. I am especially interested in criticism of the trust model and threat model. If you run agents or automated workflows in production: How do you prove what actually happened after the fact?

Tlon Messenger is now open to everyone. We built a simple and infinitely flexible platform for you to use AI agents with your friends. We think it’s pretty amazing, we love using it every day, and we want to see what people can do with it. So we’re opening it up to the public. It’s fun and exciting to build the future of personal computing in an informal, chat-based way with your friends. (You can skip the rest and just download it from the link in the next tweet if you want.) If you don’t want your digital future to be owned by a giant company but you want to explore what’s possible in this new era of agent-driven computing, you should try using Tlon. But wait, what is it? Tlon is a messaging platform built 100% open source, decentralized and owned by its users from the ground up. With Tlon you own everything: your data, your workflows, your programs: the whole thing. Think of it like Telegram or WhatsApp that you own forever and you can freely customize. Every Tlon account comes with an OpenClaw-powered bot. (Don’t worry, we safely run OpenClaw for you in our infrastructure so your bot can’t go off the rails. You’re also welcome to host your own claw if you want maximal control.) We use our bots to collect research, build nuanced daily briefings, collate data from all our disparate services. Tlon makes it insanely easy to use OpenClaw by simply installing an app from the app store, we let you keep your data and programs independent from any app or model provider, and provide the canvas to explore what’s possible. What’s most interesting for us is using bots together. On Tlon bots can create groups, augment them, moderate them, invite others and freely engage with both users and other bots. Tlon is an open playing field unlike what’s possible on conventional platforms. So, what do we do with Tlon? First and foremost, we run Tlon on Tlon. Bots coordinate data from all of our services (Linear, GitHub, all of our servers and infrastructure) and handle alerts, briefings and help us track down bugs in place. Having all of this easily synced between a desktop client and a mobile app is quick and convenient. We use bots to research new areas of work or interest. Bots can compile trees of notes, use different models to evaluate them, and then add on autoresearch-like automations to go even deeper. Since Tlon bots can freely switch between models and providers, we often pass research to Anthropic, OpenAI and self-hosted models to see different results. The most fun part of using bots as researchers is doing it together. “Put together short (~500 word) notes on the 10 most popular open source messaging protocols of the past twenty years, put them in a notebook inside a group and invite Corrina, Walt and Bill as well as their bots” is a good example. Together we’re able to move more quickly than we would on our own. Many of us also use bots to keep track of all the separate threads of work in our personal lives with close friends and family. Someone built a system for keeping track of their garden across time, someone else built a system for prepping lunches for their daughter and sending recipes to family members. Another team member built an integration that tracks what flights are passing overhead so they get a push notification every time a plane goes by. Many of us quickly communicate with our bots via voice memo when we’re out and about. Having a single interface to all the models that also holds all our data and is in our pockets feels great. Especially when the data goes into a single archive. Why is Tlon different? Every Tlon account runs on top of your very own personal server. If you ever want to download it and run it yourself, you can. If we ever go out of business, it’s yours to keep. This is very different from anything that already exists. You can’t keep your WhatsApp forever. You can’t keep your Telegram forever. Tlon is an archival-quality system that’s yours to customize. Why did we build it? In my 1999 imagination, sitting in front of a CRT somewhere in the California countryside listening to Underworld and the sound of a modem, a connected computer was an engine of unending creative potential for everyone. When I was a teenager, a computer with an internet connection felt like an infinite expanse of possibility. Not only could you use the computer to find new tools to experiment with—you could also build whatever tool you could think of. It seemed like anything was possible. I looked forward to a future where everyone could build whatever software they needed, whenever they needed it. It turned out, in the intervening twenty years, that to build and customize software you have to both write code and host it on a server somewhere. For most people, so far, that has been impossible. Instead of controlling our software, our software controls us. We rely on others to build it and decide everything about it: how it works, looks, how much it spies on us and how long it lives. But all of this is changing, fast. The hottest programming language of 2026 is English. People with no technical experience are building their own tools. It’s incredible. The expanse has opened up again. The cost of building what we think of today as software is headed to zero. What yesterday was an entire app is rapidly being replaced by a conversation. The result is hyper-specific, tailored to the user and much more efficient. Today, agents help us build workflows, automate processes and pull together disparate sources of data. All of the annoying apps and services and clunky interface we’ve put up with can just disappear. We can now program and control our computers in the programming language we already know: English. There aren’t that many of us doing this yet, though. It’s still far too hard to set up, to distribute and to trust. There’s also no single platform to experiment on and collaboratively imagine this new future of personal computing. We want everyone to be able to build bespoke, ultra-personal software on demand. We think software should be as available and accessible as a pen and paper. We think anyone should be able to enjoy the expanse of possibility that the computer provides with the lowest possible barrier to entry and the highest possible quality. So, starting far, far too long ago, we engineered a whole new system for it. Just for you. We’re opening up Tlon Messenger to a limited number of people each week. This isn’t for exclusivity’s sake, but because we’re running infrastructure for you and your agent, and covering the tokens your agent uses. That can get expensive quickly, but we want to learn what people will do with this new system we’ve built. We’re really curious to see what you can do, so give it a try and tell us what you invent. Download link to your local app store in the next tweet. Yours, Galen (and the rest of the Tlon Team)

Stop grinding every day just to stay visible. I built one Agent on CREAO that now runs my entire content and outreach system. One conversation to set it up. Zero daily effort to keep it running. Here's what runs automatically right now: — YouTube Short uploaded every single day (zero recording, zero editing) — 500 personalized cold emails sent every month via Gmail — Viral X thread posted every morning — Full stock analysis delivered to my inbox daily — YouTube, X, Gmail, Notion, Discord, and Google Sheets all connected and running in sync — Weekly newsletter written, formatted, and sent And that's one Agent. Here's what CREAO is actually capable of: — Connects to the tools you already use: YouTube, Gmail, X, Notion, Discord, Google Sheets, GitHub, Asana, and more — Builds complete multi-step workflows from a single conversation. No code. No templates — Schedules Agents to run hourly, daily, or any cadence your business needs — Chains multiple Agents so your entire operation runs as one system — Remembers your brand voice, past outputs, and preferences across every run — Delivers results to your inbox, Discord, Google Sheets, or wherever you work One sentence: CREAO connects all your tools, builds the full workflow, and runs it on schedule. No code. No team. No daily grind. Follow and turn on notifications. drop a ready-to-copy automation every day. Want to build yours for free? 👇 https://t.co/OsNCVIOa6e

Most people are still doing manually what CREAO already automates. @CreaoAI is an AI platform where you build Agents that run your work on schedule, without you. Here's what CREAO is capable of: — Connects to the tools you already use: YouTube, Gmail, X, Notion, Discord, Google Sheets, GitHub, Asana, and more — Builds full multi-step workflows from a single conversation, no code, no drag-and-drop — Schedules Agents to run hourly, daily, weekly, whatever your business demands — Chains multiple Agents together so your entire operation runs as one system — Remembers your brand voice, past outputs, and preferences across every single run — Delivers results directly to your inbox, Discord, Google Sheets, or wherever you work Here's proof. My Agents are running right now: — YouTube Short uploaded every single day (zero recording, zero editing) — 500 personalized cold emails sent every month via Gmail — Market Prediction Agent — Full stock analysis in my inbox daily — YouTube, X, Gmail, Notion, Discord, and Google Sheets all connected and running in sync — Weekly newsletter written, formatted, and sent Chat. Create. Run it all. Follow and turn on notifications. I share a new ready-to-copy Agent every day. Build yours for free: 👉 https://t.co/da1VQjUNCs