# Macroscope

> AI code review, agent orchestration and engineering status updates for GitHub teams

- Category: [Coding AI](https://finderatlas.com/categories/coding-ai)
- Pricing: Freemium
- Website: https://macroscope.com
- Platforms: Web, CLI, Slack App, API
- API: available
- Made by: Macroscope, founded 2023, San Francisco, CA
- Last updated: 2026-10-19
- FinderAtlas page: https://finderatlas.com/tools/macroscope

## Overview

Macroscope is an AI platform for software teams that combines automated pull request review, commit-level status reporting and an AI agent that works against a team's GitHub repositories. Its Code Review product reads each change together with the surrounding code, comments inline on GitHub, writes PR summaries, can open fix PRs and can auto-approve low-risk changes. Status turns commits into plain-language summaries, area reports and weekly digests, while the Agent answers questions and takes actions in Slack, GitHub and through an API.

## Key features

- Code Review
- Fix It For Me
- Approvability
- Check Run Agents
- Status
- Agent
- Murmur (beta)
- Macroscope CLI

## Pricing

- **Code Review** ($0.05/KB reviewed): Usage-based PR review, billed per KB of diff
- **Status** ($0.05/commit): Commit summaries and engineering status reporting
- **Agent** ($0.01/credit): AI agent for codebase questions and actions
- **Enterprise** (Custom): Contact sales for enterprise needs

## Best for

- Teams on GitHub that merge a high volume of PRs, including agent-written ones, and want automated review and visibility into shipped work

## Who uses it

- Software Engineers
- Engineering Managers
- Engineering Teams
- Open Source Maintainers

## Strengths

- Usage-based pricing with no per-seat fee, so cost follows review volume rather than headcount.
- $100 in free usage for each new workspace and 1,000 free Agent credits per month.
- Reviews use full-repository context rather than only the diff.
- Covers review, auto-approval, fix PRs and status reporting under one balance.
- Free credits available for qualified non-commercial open source projects.

## Limitations

- Monthly cost is hard to predict up front because it depends on KB reviewed, commits and agent credits.
- Documented setup is built around GitHub; no GitLab or Bitbucket support is stated.
- Murmur is still in beta.
- Benchmark claims of leading detection rates come from the vendor's own MacroscopeBench, not an independent test.

## Not recommended for

- Teams on GitLab or Bitbucket (the documented install path is a GitHub App), or buyers who want a fixed per-seat price

## Integrations

- GitHub
- Slack
- Jira
- Linear
- BigQuery
- PostHog
- Amplitude
- LaunchDarkly
- Sentry

## FinderAtlas editorial scores (out of 10)

- Ease of Use: 8.2/10
- Feature Depth: 8.4/10
- Value for Money: 7.8/10
- Performance & Speed: 7.9/10
- Documentation & Support: 8/10

## Alternatives

- [OpenAI Codex](https://finderatlas.com/tools/openai-codex): OpenAI's coding agent that writes, reviews and runs code from terminal, IDE, desktop or cloud ([compare](https://finderatlas.com/compare/macroscope-vs-openai-codex))
- [GitHub Copilot](https://finderatlas.com/tools/github-copilot): AI coding assistant for code completion, chat and cloud agents across IDEs, terminal and GitHub ([compare](https://finderatlas.com/compare/github-copilot-vs-macroscope))
- [Conductor](https://finderatlas.com/tools/conductor): Run a team of coding agents in parallel, each in its own isolated workspace ([compare](https://finderatlas.com/compare/conductor-vs-macroscope))
- [Kilo Code](https://finderatlas.com/tools/kilo-code): Open-source AI coding agent for VS Code, JetBrains and CLI with 500+ models ([compare](https://finderatlas.com/compare/kilo-code-vs-macroscope))
- [Google Antigravity](https://finderatlas.com/tools/google-antigravity): Google's agent-first platform for building software with parallel AI coding agents ([compare](https://finderatlas.com/compare/google-antigravity-vs-macroscope))
- [Devin](https://finderatlas.com/tools/devin): Autonomous cloud software engineer that takes tickets through to tested pull requests ([compare](https://finderatlas.com/compare/devin-vs-macroscope))
- [Cursor](https://finderatlas.com/tools/cursor): AI coding agent and VS Code-based editor for multi-file edits and cloud agents ([compare](https://finderatlas.com/compare/cursor-vs-macroscope))
- [Augment Code](https://finderatlas.com/tools/augment-code): Agentic coding platform that runs code review and ticket-to-PR work on your codebase ([compare](https://finderatlas.com/compare/augment-code-vs-macroscope))

## Recent updates

- 2026-09-01: Announced Murmur beta for orchestrating cloud coding agents in isolated sandboxes

## FAQ

**How is Macroscope priced?**

Usage-based. Code Review is $0.05 per KB of diff reviewed (10KB minimum per review), Status is $0.05 per commit and Agent is $0.01 per credit, with 1,000 free Agent credits per month. There are no per-seat fees.

**Is there a free trial?**

Every new workspace receives $100 in free usage. Qualified non-commercial open source projects can apply for free credits.

**Which source control platforms does it support?**

The documented install path is a GitHub App, available from the website or GitHub Marketplace. Support for other platforms is not stated on the pages reviewed.

**Does Macroscope train on my code?**

The company states that customer code is not used for model training and that it is SOC 2 Type II certified. Named subprocessors include GCP, OpenAI, Anthropic and Slack.

**How can I control spend?**

Teams can set per-review and per-PR caps, monthly budget limits, repo-level toggles and file exclusions. Default caps are $10 per review and $50 per pull request.

**Which languages does it review?**

The company says it reviews every language the same way, including Go, Python, Java, Swift, Kotlin, JavaScript, TypeScript and Rust, plus configuration, documentation and scripts, subject to file exclusions.