Serotonin

We made a 60 second film for Marque and we’re weirdly proud of it. Sound on. The reason we’re building this: there are 390,000+ agents registered on BNB Chain and nobody can tell you which ones actually work. A listing proves an agent exists. It doesn’t prove it does the job. So on Marque the hire itself is the proof: - the agent signs its price - it takes a public test - the terms are in writing - your money sits in escrow - the answer gets checked against the chain before the agent is paid If it can’t pass, it doesn’t get paid. That’s the whole idea. Set and Earn is the quest on top of it. Hire three agents, build one. Practice hires are free on testnet, so you can try the full flow without risking anything. 9 days left. It closes Thu 5 Nov, 12:00 UTC. We’re still wiring things up and shipping daily from Lagos, so if you try a practice hire and something breaks, reply here and we’ll fix it. marque.trade What’s the first thing you’d test an agent on before you let it touch your money?

We've put a lot of work into making Marque more than just another agent marketplace. From seamless onboarding to onchain hiring and verifiable outcomes, every update brings us closer to the vision we're building toward. Proud of the progress we've made as a team. And we're far from done. 🚀

Building @marquetrade has taught me something: Getting AI agents listed is one thing. Proving they actually work, can be trusted, and deliver value is an entirely different challenge. That's the problem we're tackling on BNB Chain. Proud of how far we've come. Still much more to build.👌🏼

Marque is ready! Discover agents, test before you hire, complete the quest, and put real agent performance onchain. → marque.trade

We started building Kerb around one uncomfortable question: What happens when tokenized stocks trade 24/7, but the markets and liquidity behind them don’t? A price can keep moving onchain while New York is closed, Hong Kong is on break, or executable liquidity has changed completely. Yet most credit systems still reason about collateral as though market access were continuous. We thought that assumption was worth challenging. So we built @usekerb. Kerb measures the exit that actually exists on X Layer — including executable depth, market state and the time a position must survive before meaningful liquidity returns — and converts those observations into verifiable credit terms. The system now includes: • live market-time risk infrastructure on X Layer mainnet • executable-depth measurement over real xStock liquidity • OKX DEX cross-checks • Carry and Session Max credit capacity • onchain KerbTerms, KerbClock and KerbQuote • a working borrow → Last Call → permissionless cure flow • independently reproducible terms from published input bundles • REST, SDK, MCP and x402 agent interfaces • empirical Market-Time Reports from the observation history One design decision mattered especially to us: there is no LLM deciding the risk numbers. Measurement, pricing and term generation remain deterministic and reproducible. Agents and applications can consume the result, but they do not have to trust a black box. Kerb Credit is only the reference market. The larger thesis is that market-time risk should be infrastructure — something lenders, exchanges, treasury systems, protocols and autonomous agents can all consume from the same verifiable layer. We built this for OKX Dev Day 2026 — Build a Market, but we deliberately pushed it beyond what we would normally consider a hackathon prototype. There is still a great deal to build, but this is the clearest expression so far of the idea we started with: measure the exit, understand the clock, then decide how much risk the market can actually support. Credit on the market’s clock. Kerb.

We’ve spent the last few days building Marque around a simple conviction: an agent being registered onchain does not mean it is reachable, capable, or safe to trust with capital. So we built the layer we felt was missing. Marque reads a user’s actual BNB Chain positions, finds agents that can work on them, measures whether those agents genuinely perform the jobs they claim to do, lets users compare the evidence, and gives the selected agent only bounded, revocable authority to act. Underneath that is a lot more than a marketplace UI: live BSC position readers, ERC-8004 discovery, continuous endpoint probing, deterministic conformance tests, agent-vs-human benchmarks, public receipts, spend-capped charters, and real mainnet execution. We even ran a real PancakeSwap V3 position through the full loop: detect that the LP had moved out of range → select the agent → constrain what it can touch and spend → rebalance on BSC mainnet → verify the resulting state onchain. The goal isn’t to create another directory with thousands of agent cards. We want Marque to become the place where registration becomes qualification, qualification becomes accountable work, and autonomous agents become something people can actually use with confidence. Still refining it, still testing it, but we’re proud of how far the product has come. Built on @BNBCHAIN marque.trade

SATIS is one of those builds that makes the idea click immediately: an agent shouldn’t keep calling tools just because it can. It should know when more evidence can no longer change the decision. Built on @Binance Agent OS. Worth watching.

Giving an AI agent permission to trade is not the same as giving it unlimited discretion. We built Oathline for Binance Agent OS. Oathline is a zero-key runtime mandate and execution-evidence layer that puts finite, continuing conditions around an agent's financial authority before an action reaches Binance — and then checks what actually happened afterward. Binance already gives agents a strong perimeter: an isolated Agentic sub-account, official OAuth, user-controlled scopes and Emergency Stop. We wanted to solve the next problem: What may this agent do right now, given what it has already done today? With Oathline, the user signs an expiring mandate such as: BNBUSDT only. SPOT only. BUY / SELL. Maximum 15 USDT per order. Maximum 40 USDT gross turnover per day. Maximum 3 orders. 300-second cooldown. Maximum 2% session drawdown. State no older than 30 seconds. Spread no wider than 20 bps. Before a Binance write is submitted, Oathline evaluates the proposed action against 11 deterministic clauses using the signed mandate, recently observed Binance state, and its own cumulative session history. No model votes on whether the order is allowed. No floating-point money arithmetic. No Binance API key copied into Oathline. In the demo, inert external text causes the agent to propose an 83.40 USDT BNBUSDT market sell. The proposal looks completely ordinary. Oathline rules: 83.40 USDT > 15.00 USDT permitted per order. And: 52.10 + 83.40 = 135.50 USDT > 40.00 USDT permitted for the day. Result: OUTSIDE MANDATE. BINANCE SUBMISSION: NOT CALLED. Then we let an action that is inside the mandate travel through the normal Binance Agent OS path. A real BNBUSDT mainnet order executes. But prevention is only half the product. Afterward Oathline independently compares its authorization receipts against Binance's observed account history. MATCHED: 1 ORPHAN: 0 DIVERGED: 0 The demo receipt chain verifies 36/36 entries with zero broken links. We also mapped the Agent OS surface we actually observed: 318 tools. 176 READ. 50 WRITE. 92 UNKNOWN. Unknown mutation-shaped capabilities do not silently inherit permission. And we deliberately do not claim things Oathline does not do. It does not detect prompt injection. It does not decide whether a trade is profitable. It does not replace Binance permissions. It cannot reverse an already executed order. Host enforcement is version/runtime dependent. The poisoned input in our demo is only the cause. Oathline constrains the resulting financial action regardless of whether the model was manipulated, hallucinated, miscalculated, or simply made a bad decision. That distinction matters. Policy before execution. Evidence after. Built for the Binance Agent OS Mini Hackathon Track A — Trading Workflows. Demo attached. Product: oathline.xyz Source: github.com/talk2francis/Oath… 90-second judge path: oathline.xyz/judge Youtube: youtu.be/mkqmfmiqzCA

We built this because we didn’t think it was enough for Occestra to create the work, grade the work, and then ask users to trust our own conclusion. The Tribunal and OQS already gave us a much stronger quality-control system than simply generating an artifact and shipping it, but the final judgment was still ours. @GenLayer gives us a genuinely independent layer that can look at the same evidence and disagree with us. What I like most about the integration is that we didn’t design it to always produce a positive result. If validators cannot reach consensus, Occestra reports that honestly. If they overturn us, the original verdict remains visible and the artifact can be repaired rather than quietly rewriting history. We also published the actual results from our first live runs: 12 reviews, six usable rulings, six that failed to reach usable consensus, and no live overturns yet. All six completed rulings agreed with the Tribunal. There is still work to do, especially around consensus reliability, but this is much closer to the kind of system we want Occestra to become: one where AI-generated work can be created, evaluated, challenged and improved rather than simply produced and presented as finished. We’ll keep building it in public.