
Kevin
4.9K posts

Kevin
@cryptokevin2011
GP @LiquidCapitalX | Ex-Head of Defi @Binance | Defi Founder 2016 | Organizer @Yale DAO | @McKinsey



Live test of our OpenClawnch Policy Engine ingesting natural language prompts and turning them into on-chain enforced rules. 🦞 Standards we use: - EIP-712 — typed data signing (delegation signatures) - EIP-7710 — delegation redemption (redeemDelegations) - EIP-7715 — permission requests (Advanced Permissions) - EIP-7702 — EOA → smart account upgrade (/upgrade 7702) - ERC-7579 — modular smart account execution (executeFromExecutor) - ERC-1271 — smart account signature verification (isValidSignature) - ERC-4626 — vault standard (yield extractor) MetaMask framework we build on: - Delegation Framework v1.3.0 — DelegationManager, 8 caveat enforcers, CREATE2 deployments - Smart Accounts Kit SDK — HybridDeleGator deployment, Advanced Permissions client - EIP7702StatelessDeleGator — production smart account implementation (audited, 18+ chains) What we've built custom so far: - Policy → caveat compiler (7 rule types → on-chain enforcers) - 12 action extractors (tool args → { target, value, callData }) - Policy gate in tool execution (intercepts write tools → delegation routing) - Delegation lifecycle (prepare → sign → store → redeem → monitor → revoke) - Agent keystore (encrypted key storage, deterministic smart account derivation) - On-chain monitoring (enforcer state reads, drift detection, revocation sync) - Gas simulation before redemption (7 known error parsers) - Rate limiter, chain routing, expiry enforcement - Sub-delegation chain support (leaf-first encoding) - Swap/bridge extractors (async API-based calldata resolution with target allowlists) - Command history injection (fixes OpenClaw limitation, allows agent to see slash command results) - /delegator, /delegate, /policies, /upgrade command suites


Agents shouldn't need permission for every transaction. 🦞 We're building an experimental policy engine on top of the @MetaMask Delegation Framework that lets you define what your agent can do in plain English, then enforces it on-chain. No approval popups. No trusting application code. The chain rejects anything outside the bounds you set. "Max $500/week, only on Uniswap, never more than $100 per tx" compiles to on-chain caveats and gets signed as a delegation. The agent executes by redeeming through the DelegationManager. If it exceeds the limits, the contract reverts. Enforcement lives on-chain, not in our application layer. How we're extending this framework for agents: → Natural language to on-chain caveats — a compiler that maps English spending rules to the framework's enforcer contracts, with live price feeds for USD→wei conversion → Two enforcement modes: on-chain delegation for smart accounts, app-layer fallback for EOAs → Autonomy profiles: from "supervised" (approve everything) to "autonomous" (weekly budget, scoped contracts, 30d expiry) → Sub-delegation: agent spawns a sub-agent, grants it a narrower slice of its own permissions via delegation chaining. The DelegationManager verifies the full chain on redemption → EIP-7702 detection + upgrade path for EOA wallets that want on-chain enforcement → Live monitoring: tracks spend against delegation limits, alerts before exhaustion Built on viem against the Delegation Framework contracts across 8 EVM chains. Under active development. On-chain execution currently covers native ETH transfers; ERC-20s and swap calldata routing are next. Off-chain policy layer for non-EVM actions (fiat ramps, social posts, browser automation). Delegation auto-renewal before expiry. Strategy templates that ship with recommended delegation profiles - activate a DCA strategy and it requests exactly the permissions it needs. Where this goes: autonomous agents running complex economic strategies within cryptographically enforced constraints you defined in a sentence. The Delegation Framework gives us the on-chain primitives. We're building the AI-native interface to them. 🦞

Keep an eye on $MEI—it looks deeply undervalued 👁️💎 @xerberus security specialists, utilizing AI agents, are building the @MeiMighty1 terminal for market and risk analytics. Access for $MEI token holders.



I’ve met Clawnch Dev and can personally attest to the fact that they are one of the sharpest, highest output individuals I’ve ever come across. As one of many examples, I know this particular expansion to product began just days ago and has already been brought to life

i have been $juno pilled. i think this will be one of the market leaders for zero human companies. it incubates other ZHCs, revenue share from that flows back to juno @tomosman is well connected and u can see that by the launch of $ROBOTMONEY which is doing really well. the fact that robotmoney was able to surpass juno, isn't a bad thing, its actually a good thing. its one of the reasons i was bullish on metaDAO last year. a launchpad should have projects launch on it without traders having the mentality that it cannot surpass the launchpad token. this is slightly different as launches are on bnkr and juno is more of an incubator, but it is giving me the same early vibes. i think this reprices to an 8fig mcap, soon.

Agents shouldn't need permission for every transaction. 🦞 We're building an experimental policy engine on top of the @MetaMask Delegation Framework that lets you define what your agent can do in plain English, then enforces it on-chain. No approval popups. No trusting application code. The chain rejects anything outside the bounds you set. "Max $500/week, only on Uniswap, never more than $100 per tx" compiles to on-chain caveats and gets signed as a delegation. The agent executes by redeeming through the DelegationManager. If it exceeds the limits, the contract reverts. Enforcement lives on-chain, not in our application layer. How we're extending this framework for agents: → Natural language to on-chain caveats — a compiler that maps English spending rules to the framework's enforcer contracts, with live price feeds for USD→wei conversion → Two enforcement modes: on-chain delegation for smart accounts, app-layer fallback for EOAs → Autonomy profiles: from "supervised" (approve everything) to "autonomous" (weekly budget, scoped contracts, 30d expiry) → Sub-delegation: agent spawns a sub-agent, grants it a narrower slice of its own permissions via delegation chaining. The DelegationManager verifies the full chain on redemption → EIP-7702 detection + upgrade path for EOA wallets that want on-chain enforcement → Live monitoring: tracks spend against delegation limits, alerts before exhaustion Built on viem against the Delegation Framework contracts across 8 EVM chains. Under active development. On-chain execution currently covers native ETH transfers; ERC-20s and swap calldata routing are next. Off-chain policy layer for non-EVM actions (fiat ramps, social posts, browser automation). Delegation auto-renewal before expiry. Strategy templates that ship with recommended delegation profiles - activate a DCA strategy and it requests exactly the permissions it needs. Where this goes: autonomous agents running complex economic strategies within cryptographically enforced constraints you defined in a sentence. The Delegation Framework gives us the on-chain primitives. We're building the AI-native interface to them. 🦞

We're building analytics throughout Molten to capture and process data about searches in real-time, allowing us to understand demand in depth. Spikes in searches for some solution will lead to the automatic creation of plugins to serve that demand intelligently and responsively.



Apparently $CLAWNCH first to launch tokens on Moltbook, now acquired by Meta. There are many legacy agents on there with coins now. Interesting to see how this plays out.

🚨In recognition of this major milestone I have just burned 1,000,000,000 $MCCLAW tokens representing 1% of the total token supply. Combined with my previous burn of ~1.6B tokens, that makes the total burn to date of ~2.6% gone forever! 🤝Deflationary tokenomics is the way.

BREAKING: META acquires Moltbook, a social network built for AI agents.

