Start local with the free SDK. Add the hosted dashboard when you need alerts, retained incident history, remote kill, and team visibility.
Install with pip install agentguard47. Inspect the SDK on
GitHub.
OpenAI is the fastest local path today.
Fastest local proof
Keep the first proof simple. One package. One local run. Add the hosted dashboard only after the agent matters to the team.
pip install agentguard47 openai
import agentguard
from openai import OpenAI
agentguard.init(
service="repo-coder",
budget_usd=5.00,
trace_file="traces.jsonl",
local_only=True,
)
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[
{"role": "user", "content": "Review this function and return one bug risk."}
],
)
print(response.choices[0].message.content)
Illustrative incident
The buyer problem is not generic visibility. It is stopping retry storms, looped tool calls, and runaway spend before they become a finance or ops problem.
A broken tool call keeps firing because the agent never exits the bad path.
Budget keeps climbing while nobody is watching the run.
The team has no retained incident trail when they come back to debug it.
The SDK stops the run locally. The dashboard keeps the incident, alerts the team, and gives you remote control afterward.
Built for coding-agent failure modes, not generic tracing dashboards.
Put a dollar boundary on a run before a bad agent burns through budget.
Cut repeated tool calls and runaway agent loops before they compound.
Stop broken retry paths from turning one failure into hundreds of useless calls.
Use the dashboard for retained incidents, alerts, service rollups, and remote controls.
For engineering teams shipping coding agents in production.
Need one place to see which services and repos are producing incidents.
Need local guardrails now, then hosted alerts and retained history once usage grows.
Need budget boundaries, incident visibility, and remote control before agents reach production scale.
The SDK is the free acquisition path. The dashboard is the hosted control plane for incidents over time.
Step 1
Use the SDK to verify one guarded coding-agent path before you send anything to a hosted service.
agentguard doctorStep 2
Use the dashboard when incidents need to be retained, shared, alerted on, and operated over time.
The SDK stops the incident locally. The dashboard makes the incident operational for the team.
Local stop
Hosted follow-through
This is the line between the products: the SDK enforces locally, the dashboard helps the team operate incidents over time.
One package to audit. No transitive dependency sprawl in the runtime path.
The SDK is MIT-licensed and readable on GitHub.
The dashboard only sees data you explicitly send through the SDK.
Hosted plans keep 30 or 90 days of retained incident history, depending on plan.
The SDK stays free. The hosted dashboard starts with a 14-day trial, then moves to a paid plan.
Run one guarded coding-agent path locally first. Move into hosted alerts, retained incident history, remote kill, and team visibility when the agent matters.
Product updates, new guides, and real coding-agent failure writeups. No spam.