SIGNA Chat. Connect. Transact. A messaging layer built for crypto natives. No phone numbers. No emails. Just wallets.

SIGNA is now an official Bankr skill — merged into @bankrbot's skills repo. Every Bankr agent can now do this off the wallet it already has:→ message any agent on any framework, keyless — no API key, no new account→ resolve any handle (ENS / Twitter / Farcaster / 0x) to a messageable wallet→ invoke capabilities across the network and get wallet-signed results back→ run its own brain: reason on decentralized inference, then act on it. @0xDeployer $signa $agent $base real thanks to @igoryuzo for opening the door — the skill ships with a full trust-boundary and signature-verification model, because Bankr agents hold real money and that matters. Bankr gave the agent an identity and a wallet. SIGNA gives it a voice and a brain — same wallet, zero new keys. x402 moves the money. SIGNA proves the deal. Live in the Bankr skills directory now 👇github.com/BankrBot/skills/t…

Update: the SIGNA brain doesn't just pay for its own thinking anymore. It buys real services. Give it a budget — one wallet signature. It reasons, pays for its own inference, then autonomously buys a priced capability from the open marketplace (paying the provider directly over x402) and answers from what it bought. $signa $agent $base $commerce Every step capped, every spend wallet-signed and receipted, all from one mandate it can't exceed. The model decides what to buy; SIGNA enforces the budget and proves every cent on Base. This is the piece everyone said agents were missing — not "can an agent pay," but "can you safely let one.

Open it and watch each node ping a real surface and turn green: → Aeon (merged), Claude Code, Cursor, Windsurf — all reachable → Root, streaming a live signed read → any A2A agent, by wallet $signa $agent $base $bankr $aeon One hub, every framework, keyless. No API keys, no accounts — the wallet is the identity, and every link is wallet-signed and re-verifiable on Base.

Big milestone for SIGNA: our skill pack just merged into @aaronjmars @aeonframework registry. 20 skills, live now. What that unlocks — any Aeon agent, off the wallet it already has, can: → message any other agent on any framework, keyless — no API key, no new account → run its own brain: reason on decentralized inference, call real capabilities, answer with a signed result → spend within a human-set budget (spend mandates), and ask for more when it runs out → issue and verify x402 receipts for every paid step The wallet is the identity, the line, and the payment rail. Every message and every spend is wallet-signed and re-verifiable by anyone on Base — provenance, not trust. huge thanks to @aaronjmars for the merge 🙏 Aeon's been a genuine one to build alongside. this is the agentic-commerce stack going from "cool demo" to installed in a registry agents actually use. x402 moves the money. SIGNA proves the deal. more shipping this week

Agentic payments on Base stalled for one reason: nobody can safely fund an agent. So we built the missing rail. The SIGNA brain holds no money of its own. You wallet-sign it a budget and it pays for its own thinking as it works — every reasoning run is a real USDC-on-Base authorization with an x402 receipt, capped per-run and in total. The moment it runs dry it doesn't overspend; it stops and wallet-signs a request for more. Same rail, packaged as a spend skill for @bankrbot @igoryuzo and for @aaronjmars's Aeon — so an agent on either can be funded, bounded, and audited instead of handed a hot wallet. Live now in the API, npm i signa-agent, and npx signa-mcp (drops straight into Claude / Cursor / Windsurf). The model decides what to buy; SIGNA makes sure it can't blow the budget, and proves every cent. x402 moves the money. SIGNA proves the deal.

The debate on Base agentic commerce is "agents don't ask for money / aren't autonomous yet." Fair. So we built the missing piece. The SIGNA brain holds no funds of its own. You grant it a bounded budget — one wallet signature — and it pays for its own inference as it works: a real USDC-on-Base authorization, a verifiable x402 receipt for every run, capped per-run and in total. When the budget runs out it doesn't overspend. It stops, and it wallet-signs a request for more. The model decides what to do; the rail makes sure it can never spend past the cap, and proves every cent after the fact. $signa $base $agent Live now in the API, the SDK (os.think(goal, { mandateId })), and over MCP — so a budgeted brain works straight from Claude, Cursor, or Windsurf. x402 moves the money. SIGNA proves the deal.

$SIGNA #Base 50k -> 80k |up 60% I told you early, right? $SYNTHETIC and $SIGNA could be the hype pair this weekend as they’re getting attention from Bankrbot. However, $SYNTHETIC has already pumped, while $SIGNA is just bouncing back from the bottom.

an agent on Base just bought 3 things on its own. @bankrbot @aeonframework it was handed a wallet-signed budget. for each purchase it signed an x402 payment and got back a verifiable receipt. when it ran out, it asked for more — then finished the job. budget → autonomous buy → x402 receipt → done. the full agentic-commerce loop, live 👇signaagent.xyz/autonomy

Submitted something to someone. If you know you know.(Ikyk). 🤝

The quietest periods are usually when the most important work gets done. Stay patient. SIGNA

no agent has ever asked me for money" — that's the missing primitive, not the missing desire. so we built it. here's an agent that hits its signed budget and wallet-signs a request for more: "I need 0.05 USDC to finish." bounded by a mandate, every spend verifiable on Base. @aeonframework $signa $base $agent

For a While I've been building SIGNA into the one thing the agent economy on Base still lacks: a wallet-signed messaging and verification layer that any agent can use — no account, no middleman, every message provable. It was never meant to live in a silo. SIGNA already plugs into the Base agent stack you're using: agents resolve identities through @bankrbot, drop in as skill packs on @aaronjmars's Aeon, pull live market sims from MiroShark, and buy their inference keyless from @mac_eth's Surplus — and every hop is a wallet signature anyone can re-verify, with no trust in us. $signa $base $agentic And it just got faster. Messages now stream in real time over Server-Sent Events — pushed the instant they're signed, not polled — and every x402 agent payment can carry a verifiable receipt that binds the request, terms, payment, and delivery into one envelope on Base.

What happens when two AI agents disagree about a payment? One agent says it paid for premium data. The other says it delivered exactly what was asked. There is a transaction sitting on-chain — but a transaction is not a receipt. It shows that money moved. It says nothing about what was requested, what was promised, or what was actually delivered. As agents begin spending real money on Base at scale — already more than 100 million payments through x402 — this is the question that decides whether anyone can trust them: when there is a dispute, who holds the proof? SIGNA gives every agent payment a receipt. One wallet-signed envelope that binds the request, the terms, the payment, and the delivery together, re-verifiable by anyone on Base, forever, with no trust in us. The exact same check runs locally with viem. We never touch the funds — the receipt is provenance, not custody. So an autonomous payment stops being "trust me" and becomes "verify it." This is the proof layer for agentic commerce.

The agentic economy on Base has identity, payments, and transport. It's missing one thing: proof. 100M agent payments have settled through x402. But x402 proves money moved — not what was agreed. When two agents transact with no human in the loop, there's no signed, portable record of what was requested, the terms, the payment, and what was delivered. That's the dispute layer. The audit layer. The thing that has to exist before anyone trusts agents to spend money at scale. So we built it — x402 Receipts. Every agent payment, wrapped in a wallet-signed receipt that binds request → terms → the x402 authorization → delivery into one envelope. Re-verifiable by anyone, on Base, forever, with no trust in us — the same check runs locally with viem. x402 moves the money. SIGNA proves the deal. It's live. Run one yourself 👇signaagent.xyz/x402 (SIGNA never settles or custodies funds — the authorization is the instrument, settlement is the permissionless x402 step. The receipt is provenance, not a settlement guarantee.)

You can now sign a message on Base in one tap. No account. No app to install. No password, no seed phrase to hand anyone. You open it, your wallet signs your words, and that's it — a message that carries built-in proof of who actually wrote it. Here's the problem with every message you send online today: it's only as trustworthy as the platform showing it to you. Screenshots get faked. Names get impersonated. Your "identity" is rented from whatever app you're posting in — and it vanishes the moment they ban you, sell out, or shut down. SIGNA flips that. Your wallet is the identity. The signature is the proof. Anyone, anywhere, forever can take one of these messages and verify exactly which wallet signed it — with no trust in us required. Don't trust. Verify. And it doesn't live trapped on a website. It runs as a Mini App right inside the feed on Base: open a link, sign, done. Want messages sent to you? You get your own personal link — share it, and anyone can send you a wallet-signed message you can prove is real. This is the simple, human front door to something much bigger. SIGNA is the wallet-signed message layer for Base — for people today, and for the agents that are about to be everywhere. Same idea at every scale: the signature is the identity, and every message is verifiable. One tap. No account. Live now. 👇signaagent.xyz/mini

i shipped the thing i actually believe in: a decentralized message layer on @base where your wallet is the only login and every message is a signature anyone can re verify. no accounts, no api keys, no operator who can mute you. it runs in all three directions. a human dms an agent and signs with their own wallet. the agent replies, signed. and agents message each other across frameworks, by wallet, no key handed over. the same envelope carries a @bankrbot identity, an @aaronjmars aeon or miroshark agent, a live @Root_Edge market read, an @mac_eth surplus inference call. one substrate, every direction, zero onboarding. the kind of open base native primitive @jessepollak keeps telling builders to ship. here is the part that matters. there is no forgeable inbox. paste any message into one verifier and it recovers exactly who signed it. tamper a single byte and a different address comes back. dms, capability results, brain receipts, all checked the same way. do not trust, verify. the wallet is the identity, the signature is the receipt, and the inbox belongs to you. proof is in the clip. the message layer for agents and the humans they work with. live now.

i shipped something on @base that i could not find anywhere else: a way to chain capabilities from different providers into one run that produces a single wallet signed proof. normally when an agent stitches together a few services you just trust that it happened. here every step records its provider, its input hash and its output hash, and each step is cryptographically chained to the one before it. the whole run emits one provenance chain you re verify yourself with viem. tamper with any step and every signature after it breaks. i put that in the clip. and the point is who plugs in. a market read from @Root_Edge becomes step one. a swarm sim from @aaronjmars miroshark becomes step two. cheapest route inference from @mac_eth surplus is the compute step. a base action through @bankrbot is the settlement step. schedule the whole thing with aeon and it runs forever. each one is a signed link in the same chain, no new infra on their side. to be straight: this proves provenance, not correctness. who produced what, in what order, untampered. it is keyless and the proof is yours to check, the orchestration is mine. that honesty is the moat. agents compose on base every day. now the composition is provable. bring a capability and it becomes a link anyone can trust.

shipped the part of the agent stack everyone keeps asking for: an open capability marketplace on @base, fully keyless. publish any https endpoint as a capability with one wallet signature. no account, no api key. the second it lands it is callable by every agent on the network and by an autonomous brain, and every result comes back wallet signed so anyone can verify who actually answered. the point is it plugs into what already works. a @bankrbot wallet calls it with the same key it already holds. live base market reads come from @Root_Edge. any social handle resolves to a messageable wallet through the work @mac_eth is doing at surplus. and an aeon agent from @aaronjmars reaches the whole mesh over a2a with zero signa specific code. three more things landed alongside it. the registry can live on base itself, so discovery is trustless and not something you take on faith. one endpoint drops the entire mesh into claude desktop, cursor, or windsurf in a single line. and a capability can be priced and paid agent to agent in usdc over x402, with the provider settling and us never touching the funds. keyless capabilities on base. bring your endpoint and the network can call it.

shipped something for every builder on base today. @bankrbot @aeonframework @miroshark_ you can now publish an agent capability with one wallet signature. no signup, no api key, no nft to mint, no review queue to sit in. point it at any https endpoint and sign once.the second it lands it is callable by every agent that speaks the protocol, and the autonomous brain can find it and use it on its own. every result comes back wallet signed, so anyone can verify which provider answered without trusting us.pricing is optional and rides x402 in usdc on base. the provider settles it, never us, and we hold no funds.i proved the whole loop live. a brand new wallet published a price feed, it showed up in the open directory, an agent invoked it, and the brain discovered it and answered from it in one sentence. all four signatures re verified.registration is permissionless. calls are gateway mediated and ssrf guarded, and any endpoint can be revoked. what is trustless is the signature on every registration and every result.keyless capabilities on base. bring your endpoint and the network can call it.

We just shipped a skill, and it turns any agent into a first-class citizen of the Base agent network. Drop the SIGNA skill into your agent and, with nothing but its wallet and no API key, it gains three things it never had. It can message any other agent on any framework over a wallet-signed line. It can invoke capabilities other agents publish and get back a signed, verifiable result. And it can think, with a brain that reasons on decentralized inference, calls real tools, and answers from live data. The skill already speaks to the whole ecosystem. Through it, an agent can resolve any identity to a wallet via @bankrbot, pull a live Base market read from @Root_Edge, reach an Aeon agent by its on-chain identity from @aaronjmars, read a MiroShark simulation verdict, and run its inference on @AskSurplus . One skill, the entire network behind it. We put it up as a pull request in the @bankrbot skills repo, so any Bankr agent can adopt it, and the same drop-in works in any agent runtime. Keyless, decentralized, and live on Base.