DEV Community

pranav-afk
pranav-afk

Posted on

Hello DEV, I build ops for AI agent fleets

Hi, DEV πŸ‘‹

I'm part of the team building Cartha β€” an ops layer for AI agents that actually run in production.

This is a short intro: the problem we kept hitting, what we shipped, and what I'll write about here.


The problem

We were debugging an agent that did something inexplicable in production. Logs and traces answered what ran. They didn't answer the question that mattered:

What did the agent know when it made that call β€” and was it allowed to know that?

If you run multi-agent systems, you eventually need more than a pretty timeline:

Need Why it matters
Scoped memory User vs agent vs team vs org β€” without leaks
Hard budgets Soft alerts don't stop a retry loop at 3am
Tool limits Child agents shouldn't inherit the keys to the kingdom
HITL Some actions need a human before they execute

Observability tells you what happened. Governance decides what is allowed to happen next.


What Cartha is

Not a chatbot builder. You keep your own agents (OpenAI, tools, business logic).

Yes a control plane for fleets:

  • Run timelines (tools + LLM steps)
  • Server-enforced memory scopes (user / agent / team / org)
  • Fail-closed spend budgets on a run
  • Nested agents + attenuated delegation
  • Policies + escalations
  • Dashboard for agents, traces, cost, memory

Minimal Python path


python
import cartha

cartha.init()  # CARTHA_API_KEY + CARTHA_API_BASE=https://cartha.in
client = cartha.wrap_openai()  # auto LLM steps + cost

@cartha.tool()
def crm_lookup(user_id: str) -> dict:
    return {"plan": "pro"}

@cartha.trace(id="support", team="support", budget_usd=0.5)
def handle(user_id: str, ticket: str) -> str:
    data = crm_lookup(user_id)
    r = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": f"{ticket}\n{data}"}],
    )
    return r.choices[0].message.content or ""

Docs: How to Use (https://cartha.in/how-to-use)
Product: cartha.in (https://cartha.in)
Enter fullscreen mode Exit fullscreen mode

Top comments (1)

Collapse
 
alexshev profile image
Alex Shev

Agent fleets make ops visible fast. Once there are multiple workers, the hard part becomes routing, shared memory, permission boundaries, and knowing which agent owns the next step. The fleet needs operations design as much as prompting.