Augment Code

Code review agent in the Cosmos platform: risk-triaged inline PR comments with full-codebase context; GitHub-native, others via CLI.

Visit Website [↗]

[ Facts ]

Category: AI PR Review
Open source: No
Pricing: Business $100/mo flat (up to 50 seats) incl. $100/mo pooled usage, plus flat 40% fee on LLM usage; Enterprise custom. Code review on all plans source
Self-hosted: No — No self-hosted offering documented; Enterprise cites custom compute and multi-region deployment in Augment's cloud.
Platforms: github, gitlab, bitbucket, azure-devops
Model control: Choose from a vendor model list (Claude, GPT-5.x, Gemini families); no BYOK
Last verified: 2026-08-11

[ Against the 9 Standards ]

Based on public documentation as of 2026-08-11. ✓ documented · ~ partial · ✗ not offered · ? unknown. Methodology on the about page.

✓ Multi-dimensional Context

Context Engine reads the full codebase; cross-repo context via external repos declared in AGENTS.md.

✓ Rule-Centric & Default Quiet

YAML review guidelines with globs and severities; docs commit to high signal-to-noise and no style nags.

~ Dual-Workflow: Local vs. PR

GitHub PR reviews plus Auggie CLI/CI automation; no distinct local pre-commit review mode documented.

~ Business Logic Validation

Jira Cloud and Linear integrations plus MCP tools; ticket-vs-code validation not explicitly documented.

✓ Continuous Learning

Code Review Memory captures reviewer feedback and distills per-repo knowledge shared across agents.

✓ Sandbox Validation

Cosmos Verifier agent exercises changes in a running environment and reports evidence-backed findings.

~ Economic Transparency

No BYOK; model choice from a vendor list; discloses a flat 40% fee on LLM usage with a credit dashboard.

~ Actionability

'Fix in Augment' hands findings to an agent session in IDE/CLI; no one-click commit from the PR.

~ Measurable ROI

Dashboard: PRs reviewed, % comments addressed, thumbs-up rate, estimated dev hours saved; no DORA metrics.

[ In Our Coverage ]

AI Code Review vs Static Analysis: 2026 Guide

AI code review vs static analysis compared: determinism vs reasoning, false positives, SAST coverage, cost, and why mature teams run both.

What Is AI Code Review? How It Works (2026)

AI code review explained: how LLM reviewers work, what they catch and miss, how they differ from linters and static analysis, plus sourced adoption data.

AI Code Review Statistics (2026): Sourced Data

AI code review statistics for 2026: adoption, trust, review turnaround, AI code volume, and bug-catch benchmarks — every stat linked to a primary source.

Evaluating Augment Code?

Run it through the two-week trial protocol before you commit.

Evaluation Guide [↗]