Plan and execute
Agents break down goals, plan steps, and execute. Self-correct on failure.
Tool use
Function calling, code execution, web browsing, file system, your custom tools.
Branching workflows
Parallel execution, conditional logic, error recovery. Complex agentic flows.
Drop-in SDK
Define an agent in 20 lines. Deploy to the network. Scale automatically.
Memory
Short-term conversation, long-term vector memory, structured state.
Observable
Trace every step, tool call, and decision. Debug visually.
Pricing
Token-efficient, with volume discounts and burn incentives.
Plus token cost
Plus underlying token cost
Sandboxed, isolated
Long-term persistence
Pricing is illustrative. Final rates are governed by on-chain parameters and may vary based on network state.
Staking requirements
Tier-based access. Higher stakes unlock better economics and more capacity.
| Tier | Required stake | Access |
|---|---|---|
| Builder | 50M QUBIC | Agent SDK, basic workflows |
| Startup | 150M QUBIC | Persistent memory, code exec |
| Business | 500M QUBIC | Custom tools, A/B testing |
| Enterprise | Custom | On-prem, dedicated capacity |
Example
Drop-in compatible with the OpenAI SDK.
from aigarth import Agent, tool
@tool
def search_docs(query: str) -> list[dict]:
return aigarth_client.search(query, limit=5)
agent = Agent(
model="aigarth-reason-1",
tools=[search_docs],
system="You are a research assistant. Be thorough.",
)
result = agent.run("What's the latest on useful proof of staking?")
print(result.answer)Enterprise benefits
Everything in the standard tier, plus the things enterprises need.
- Deploy agents to production in hours
- Built-in rate limiting and cost controls
- Human-in-the-loop checkpoints
- A/B testing across agent versions
- Compliance with audit trail for every step
- Migration from LangChain, CrewAI, AutoGen
- On-prem deployment for sensitive workflows
- Quarterly business reviews and roadmap input