
Augment Code
Enterprise AI coding assistant with a whole-repo Context Engine.
About
Augment Code (augmentcode.com) is the enterprise-focused AI coding assistant: a Context Engine that indexes entire codebases (400k+ files claimed) so agents reason over architecture, not just open files. VS Code and JetBrains extensions plus the Auggie CLI, with MCP support.
$252M raised; SOC 2 Type II and ISO/IEC 42001; no training on customer code. Caveat: the October 2025 switch to credit-based pricing was widely perceived as a 10x+ hike for heavy users — check current pricing carefully. Paid plans from ~$20/mo; Business $100/mo flat up to 50 seats.
What it can do
- Whole-repo Context Engine
- VS Code + JetBrains + CLI
- Agent + chat + completions
- MCP support
- SOC 2 II / ISO 42001, no training on code
Setup
- Install the extension (VS Code / JetBrains) or the Auggie CLI.
- Let the Context Engine index your repo (large monorepos take a while).
- Set workspace guidelines via .augment-guidelines.
- Monitor credit usage — variance per task is high.
Prerequisites
VS Code or JetBrains; paid plan.
Use cases
Works with
Trust score — 7/10
Scored 7/10 (metrics tier). Strong enterprise story (certifications, whole-repo context, $252M raised) but the credit-pricing controversy and proprietary licensing are real caveats. Adoption is a provider-tier estimate (thinner evidence). Metrics tier.
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 7.0/10
- Maintenance · recency, releases, issue load
- 7.0/10
- Openness · license + docs
- 4.5/10
- Manual review · sanity read + red-flag check
- 7.0/10
- · provider-tier estimate — thinner evidence (no public adoption metric)
- · $252M raised; no public repo — adoption estimated from enterprise traction
- · released 251 days ago
- · manual review: enterprise AI coding assistant; Context Engine for large codebases; credit-pricing controversy (Oct 2025) is a caveat; $252M raised; license: proprietary
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.