Skill v1.0.2
currentAutomated scan100/100+13 new, ~16 modified
version: "1.0.2"
Web3GPT skill
Web3GPT is a smart-contract agent. Through this HTTP API you can hold a conversation with it, and it can write Solidity contracts, compile them, deploy them to EVM chains, and resolve ENS and Unstoppable Domains names. No account or API key is needed.
Endpoint: https://w3gpt.ai/api/skill (GET or POST; CORS is open)
Quick start
- Start a chat and keep the returned
chatId. It is the only credential for the
conversation, so treat it as a secret.
``bash curl https://w3gpt.ai/api/skill ``
``json { "agentId": "agent_web3gpt", "chatId": "Xk3…", "response": null } ``
- Send messages with that
chatId. Each call returns the agent's reply to your message.
``bash curl -X POST "https://w3gpt.ai/api/skill?chatId=Xk3…" \ -H "Content-Type: application/json" \ -d '{"message":"Deploy an ERC20 named Demo (DEMO) with 1,000,000 supply to Polygon Amoy"}' ``
``json { "agentId": "agent_web3gpt", "chatId": "Xk3…", "response": "…" } ``
- The agent often asks you to confirm before it deploys. Reply in the same chat (for example
"Yes, deploy it"). The deployment reply includes the contract address and transaction hash.
Parameters
Pass these as JSON body fields (POST) or query parameters.
| Name | Description | |
|---|---|---|
chatId | Continue this conversation. 1–64 characters of A-Z a-z 0-9 _ -. Omit it to start a new chat. | |
message | Your message (alias: prompt). Up to 50,000 characters. Omit it to just create or read a chat. | |
agentId | Use a different Web3GPT agent for a new chat (e.g. a custom agent from w3gpt.ai/?a=<agentId>). Ignored for existing chats. | |
history | true to include the whole conversation as history: [{ id, role, text }] (alias: full). |
Response
| Field | Description | |
|---|---|---|
chatId | The conversation id. | |
agentId | The agent serving this chat. | |
response | The agent's latest reply as text, or null if there isn't one yet. | |
history | Present when history=true. | |
error | Present on failure, with a non-2xx status. |
Deploying contracts
- Say which chain to use. Agent deployments are paid for by Web3GPT, and these chains are
available:
| Chain | Chain ID | |
|---|---|---|
| Polygon (mainnet) | 137 | |
| Polygon Amoy | 80002 | |
| Ethereum Sepolia | 11155111 | |
| Base Sepolia | 84532 | |
| Arbitrum Sepolia | 421614 | |
| OP Sepolia | 11155420 | |
| Mantle Sepolia | 5003 | |
| Metis Sepolia | 59902 | |
| Celo Sepolia | 11142220 |
- You can give the full source, or describe the contract and let the agent write it.
OpenZeppelin and other npm or GitHub imports work. The Solidity version is chosen from the pragma.
- A deployment is reported only after the chain confirms the contract-creation transaction. The
reply includes the chain ID, contract address, transaction hash, explorer links and an IPFS link to the sources, ABI and bytecode. Verification on the block explorer follows within a few minutes.
- Every deployment is listed publicly at
https://w3gpt.ai/contracts. Aggregate numbers are at
https://w3gpt.ai/api/stats.
Limits
The endpoint is public, so usage is metered:
| What | Limit | |
|---|---|---|
| Messages to the agent | 20 per IP and 30 per chat, every 10 minutes | |
Calls without message (create or read a chat) | 120 per IP every 10 minutes | |
| Testnet deployments | 10 per caller per hour | |
| Polygon mainnet deployments | 2 per caller per day, within a shared daily budget |
- Over a request limit: HTTP
429with aRetry-Afterheader (seconds) and
X-RateLimit-Limit / X-RateLimit-Remaining. Wait and retry; don't hammer the endpoint.
- Over a deployment limit: the agent replies with an explanation (try later, use a testnet,
or deploy from your own wallet at w3gpt.ai) instead of deploying.
Errors
| Status | Meaning | |
|---|---|---|
400 | Invalid chatId | |
413 | message longer than 50,000 characters | |
429 | Rate limited; see Retry-After | |
500 | The agent failed to answer. If you had asked for a deployment, check https://w3gpt.ai/contracts (or ask in the same chat) before retrying, so you don't deploy twice. |
Reference
- OpenAPI:
https://w3gpt.ai/api-docs - Browser app:
https://w3gpt.ai - Source:
https://github.com/markeljan/web3gpt