Cost attribution, live monitoring, and quality scoring — built for the teams running them in production.
Founding cohort First 50 customers lock in founding pricing for life.
Our support-triage agent quietly broke for 11 days. We found out from a customer.
→Heartbeat monitoring with expected schedules. Get paged in seconds when a scheduled agent goes silent, with full context on what was supposed to run and what the last successful run produced.
Our token bill jumped from £2,400 to £8,900 last month. Three days to figure out which agent.
→Per-agent, per-customer, per-feature cost attribution. Spend alerts the moment any agent breaks its own baseline. Cost-per-successful-run as the metric finance can build budgets around.
We shipped a prompt change. Output quality fell 22%. Nobody noticed for two weeks.
→Define what good looks like once: a rubric, a JSON schema, an LLM-as-judge prompt. Every run gets scored. Drift surfaces in your dashboard before it surfaces in your support inbox.
Every team running agents in production needs the same three things working together. Most stitch them together from a pile of separate tools. We ship them as one platform.
Stop finding out about the bill at month-end.
Find the dead agent before your customer does.
Catch the 22% quality drop before users churn.
Three tiers. No per-seat. No per-span tax.
For one team running a handful of agents.
For teams shipping AI features to customers.
For larger teams with multiple agent fleets.
Two lines in your code and every Anthropic, OpenAI, Bedrock, Mistral, Gemini, or Cohere call is captured: tokens, cost, latency, tool use, errors. No manual tracing.
First-class hooks for LangChain, LlamaIndex, Vercel AI, Pydantic AI, CrewAI, and the OpenAI Agents SDK. Trace agent loops, chains, and handoffs without custom plumbing.
One authenticated HTTP endpoint works from cron, n8n, Make, Zapier, GitHub Actions, Claude Routines, or any shell script. If your agent can curl, it's monitored.
curl, it works. Custom integrations via plain HTTP.
Python, TypeScript, cron, n8n, Claude Routine, anything. Two lines of code or one HTTP request.
Tokens, cost, latency, tool calls, outputs. Captured asynchronously and never blocks your agent — if our service is down, yours keeps running.
Live dashboard, drift alerts to Slack or PagerDuty, weekly reports for your team and finance.
Native SDKs for Python, TypeScript, Go, Ruby, and PHP auto-capture every Anthropic, OpenAI, Bedrock, or Gemini call your agents make, with tokens, cost, latency, tool use, and errors.
For agents you can't host an SDK in, a single authenticated webhook works from cron, n8n, GitHub Actions, Claude Routines, or anything that can speak HTTP.
import agentping agentping.init("daily-summary") # auto-captures every llm call # anthropic · openai · bedrock · gemini
import { AgentPing } from "agentping"; AgentPing.init({ agent: "daily-summary" }); // works with @anthropic-ai/sdk, openai, // vercel ai sdk · node, bun, deno
import "github.com/agentping/agentping-go" agentping.Init("daily-summary") // wraps anthropic-sdk-go, go-openai // context-aware, goroutine-safe
require "agentping" AgentPing.init("daily-summary") # wraps anthropic-ruby, ruby-openai # works with sidekiq, rails jobs, rake
use AgentPing\AgentPing; AgentPing::init('daily-summary'); // auto-discovered service provider // hooks scheduled commands + queued jobs
# a single request, that's it curl https://api.agentping.io/p/your-agent-id # report status, duration, cost as params curl "https://api.agentping.io/p/your-agent-id?status=ok&cost=0.012"
If one of these reads like you, you're in the right place.
"We ship AI features inside our product — a support agent, a triage classifier, a summariser. The token bill needs keeping an eye on."
Most start on Team.
"We run several agents in production. They call other agents. One goes silent and we find out from a Zendesk ticket. We need traces, heartbeats, and an alert path on-call respects."
Most start on Business.
"I shipped one critical agent into the product six weeks ago. I check the logs every morning before opening Linear. I need to sleep through the night."
Most start on Starter.
When does this launch?
Closed beta is running today. General availability is planned for the second half of 2026. Get on the waitlist to be invited as cohorts open.
Will it slow my agents down?
No. The SDK never blocks your agent. Telemetry runs on a separate thread with a hard 2-second timeout, a bounded local queue, and graceful degradation when our service is unreachable. If we go down, your agents run as if we weren't installed.
What's the deployment model?
Hosted SaaS at launch. EU and US regions available.
Can I export my data?
Yes. Full event export to JSON or Parquet. API access on every tier. We don't lock your data in.
What about SOC2, GDPR, data residency?
GDPR-compliant from day one. SOC2 Type II within 12 months of launch. EU region available now; project-level setting for redacting prompt and output bodies if you'd rather not send content at all.
Join the founding 50 and get lifetime founding rates (£79 / £199 / £399), a direct line to me on Slack during onboarding, and a real say in what ships next. Once the 50th seat is taken, founding pricing closes for good. Standard pricing applies after.
No spam. Build updates only. Unsubscribe whenever.