Pokant adds reliability, observability, and error recovery to any browser automation agent. Two lines of code. Zero dependencies.
agent = Agent(task="Extract pricing", llm=llm)result = await agent.run()# Crashes on API errors# Loops forever on broken pages# No idea what happened# Costs spiral invisiblyfrom pokant import wrapresult = await wrap(agent).run()# Auto-retry on transient errors# Stuck detection kills loops# Step-by-step screenshots + replay# Cost tracking per stepYour agent crashes on a transient API error at 3 am. No retry, no alert, no visibility into what happened. You find out when a customer complains.
The agent clicks the same button 47 times because the page didn’t load as expected. You burn $12 in API costs before the timeout kills it.
The task failed. Why? Was it the website, the LLM, the network, the credentials? Without step-by-step replay, you’re guessing.
Seven error categories. Transient failures retry automatically with exponential backoff. Permanent failures surface immediately.
Detects visual stagnation, action loops, and failure spirals in real time. Kills the agent before it wastes your budget.
Every action screenshotted, timestamped, and saved. HTML files you can open in any browser—no account needed.
Per-step and total LLM cost monitoring. Know exactly how much each task costs before your invoice surprises you.
Encrypted cookie storage across runs. Your agent stays logged in without re-authenticating every time.
pokant dashboard launches a debugging UI on your machine. See all runs, replay steps, inspect errors. No cloud required.
Works with Browser Use, Playwright, or any browser automation framework. Bring your own agent—Pokant doesn’t replace it, it makes it reliable.
$ pip install pokantfrom pokant import wrapresult = await wrap(agent).run()$ pip install pokant[dashboard]$ pokant dashboardSame task, same agent, same target website. The only difference is two lines of code.
Core library is pure Python. No accounts, no API keys beyond your LLM provider, no vendor lock-in.
Screenshots, replays, and run metadata saved to .pokant/ on your machine. Nothing leaves your environment unless you configure it.
Use it commercially, modify it, contribute back. The code is on GitHub.
Save and reuse task templates with parameterized inputs.
Run workflows on a cron schedule.
The system learns from every run. Success patterns become reusable knowledge.
from pokant import wrapresult = await wrap(agent).run()