AI Agent SDK
OPEN SOURCE · 119★LLMs could finally reason about on-chain data — but every team was hand-rolling the same fragile glue to let them act on it.
ZEE — the Zero-Employee Enterprise — needed an orchestration layer where autonomous agents could interact with on-chain data, external tools, and each other, without each integration being bespoke. I built and shipped it as @covalenthq/ai-agent-sdk on npm — 119 stars, 56 forks, and 2,000+ downloads since its December 2024 launch.
A ZeeWorkflow wraps the task agents you define with three defaults. The planner breaks the goal into dependency-ordered tasks; the router assigns each task to the most suitable agent — and answers their follow-up questions mid-run with full context; the endgame agent compiles everything into the final response. An action queue drives the whole run, capped at 50 iterations.
PLAN
the goal becomes dependency-ordered tasks
planner agent
ASSIGN
each task routed to the best-suited agent
router agent
ACT
your agents complete tasks; follow-ups loop back through the router
task agents · tools
CONCLUDE
the full context, compiled into one answer
endgame agent
I built the core SDK package and led the architectural milestones from launch through v0.3.0:
multimodal support
Gemini image analysis alongside text reasoning
Vercel AI SDK migration
one layer for streaming + tool calls — killed a cross-provider tool-calling bug
ZEE assignment refactor
the v0.3.0 agent-assignment model
cza CLI
scaffold a new agent project in one command
import { Agent, ZeeWorkflow } from "@covalenthq/ai-agent-sdk";
const analyst = new Agent({
name: "onchain-analyst",
model: { provider: "OPEN_AI", name: "gpt-4o-mini" },
description: "reads balances, transfers, and approvals",
tools: { balances, transactions },
});
const zee = new ZeeWorkflow({
description: "audit the wallet, then write the report",
output: "a structured risk report",
agents: { analyst, writer },
});
const result = await ZeeWorkflow.run(zee);