Home / Solutions / AI Agents
AI Agents

Structured on-chain data for autonomous agents

LLMs can't parse raw hex calldata. SQD delivers pre-decoded events, typed transaction fields, and labeled contract interactions as clean JSON over a REST API — so your agents reason about blockchain state instead of fighting with data formats.

225+ Networks
27ms P50 latency
0% Error rate
2,800+ Worker nodes
Capabilities

Built for ai agents at scale

{

Pre-decoded, typed data

Events arrive with decoded parameter names, typed values, and contract labels. No ABI lookup, no hex-to-int conversion, no address resolution. Your agent gets {"from": "0x...", "amount": "1500000000", "token": "USDC"} — not raw log topics.

>

Streaming context window

Feed your agent the latest blocks, events, and state changes as a continuous NDJSON stream. The agent's context stays current without polling or cron jobs — new on-chain actions arrive in the same HTTP connection within milliseconds.

+

Multi-chain reasoning in one call

An agent monitoring a cross-chain arbitrage opportunity doesn't need 5 different RPC integrations. One SQD query spans Ethereum, Arbitrum, Base, Polygon, and Solana — the agent sees all relevant state in a single response.

~

Framework-agnostic REST API

Plain HTTP POST returning JSON. Works as a LangChain tool, a CrewAI data source, an Eliza plugin, or a raw fetch() call in your custom agent loop. No SDK lock-in, no client library required.

Use cases

What teams build with SQD

Autonomous trading agents with real-time market state
On-chain research assistants that cite verified data
Smart wallet copilots that explain transaction history
Governance monitoring agents tracking proposal lifecycles
Risk assessment bots with cross-protocol exposure analysis
Cross-chain bridge monitors detecting anomalous flows
The problem with raw chain data

Your agent shouldn't waste tokens parsing hex

A raw Ethereum event log is a blob of hex-encoded topics and data fields. An LLM needs to know the ABI, decode the parameters, resolve addresses to labels, and convert wei to human-readable amounts — all before it can start reasoning about what actually happened.

That's 500+ tokens of context window burned on data wrangling for every single event. Multiply by hundreds of events per block, across multiple chains, and your agent is spending more compute on parsing than on actual decision-making.

SQD delivers pre-decoded, typed JSON with human-readable field names. Your agent gets structured data it can reason about immediately — the same way a human analyst would read a block explorer, but at API speed.

What your agent receives
{
  "event": "Transfer",
  "contract": "0xa0b8...3e7b",
  "contractLabel": "USDC",
  "from": "0x28c6...9f21",
  "to": "0x7a25...4d08",
  "amount": "1500000000",
  "amountDecimal": "1500.00",
  "blockNumber": 19847362,
  "timestamp": "2025-03-15T14:32:11Z",
  "txHash": "0xf7a1...8c3d"
}

Decoded parameters, labeled contracts, human-readable amounts. No ABI lookup, no hex conversion, no address resolution needed.

Integration

Plain HTTP. No SDK required.

SQD's Portal API is a single POST endpoint returning NDJSON. It works with any framework that can make an HTTP request — which is all of them.

LangChain Define SQD as a tool in your agent's toolchain. The agent decides when to query on-chain data based on the conversation.
CrewAI Give each agent in your crew access to specific chain data. One agent monitors swaps, another tracks governance proposals.
Eliza Plug SQD into character-driven agents that need on-chain context for personality-aware blockchain interactions.
Custom agents A fetch() call in your agent loop. POST your query, stream the NDJSON response, feed results into your LLM context.
Get started

Your blockchain data infrastructure, handled.

Private Portal. Dedicated. Validated. Managed. Tell us what you're building — we'll show you what it looks like on SQD.