Skip to main content
Superlog automates routine engineering work. It can triage alerts, answer support questions, and review performance and observability across your code and infrastructure. You choose the model and the agent harness, and you can run on your own API keys or your ChatGPT subscription. Each automation has a trigger, instructions, repositories, and connectors. When the trigger fires, Superlog starts a fresh sandbox, checks out your repositories, and runs a coding agent on the task. The agent can read your tools, open pull requests, post to Slack, and create Linear issues.

Quickstart

Sign up and run your first automation in a few minutes.

How Superlog works

Automations, triggers, connectors, models, and runs.

Templates

Start from bug triage, support, and reliability templates.

Integrations

Connect GitHub, Slack, Sentry, Datadog, Linear, and more.

​
What teams automate

Bug triage

Rate new Sentry issues, trace them to the commit that caused them, and open a pull request when the fix is small.

Internal support

Answer “is this a bug?” and “can we do this?” questions in Slack from the code and docs, so engineers are not interrupted.

Reliability checks

Compare the last hour against the past week in Sentry and Datadog, and post to Slack only when something is out of range.

Observability and performance reviews

Find code paths with poor telemetry and slow endpoints each week, and open pull requests that fix them.

​
Bring your own inference

Every automation picks a model from OpenAI, Anthropic, Google Gemini, xAI, Mistral, or DeepSeek, and runs it in the Codex, Claude Agent SDK, or OpenCode harness. Add an API key or connect a ChatGPT subscription and runs use it. Without one, runs use the usage included in your plan. See Models and harnesses.

​
Open source

Superlog is open source under the Apache License 2.0. The code is at superloglabs/responder-oss. Use the hosted service at superlog.sh, or run it yourself.