Indie
$20/mo
40K credits, 1 user
Augment Code
The AI-native engineering platform built for production codebases.
Augment Code's AI-native engineering platform. Intent is the multi-agent orchestration workspace for VS Code and JetBrains; Cosmos is the underlying OS for agentic software development — agents that span the full SDLC with shared context and multi-model support. Remote Agent runs cloud-based coding tasks autonomously, and the Code Review Agent is ranked #1 for AI-powered PR review. Prism model routing automatically selects the optimal model per task, cutting costs 20–30%.
+ Pros
- Context Engine provides deep semantic codebase understanding — not grep-based retrieval — mapping code structure across millions of lines, reducing token consumption by ~50% vs competitors on benchmarks like SWE-Bench.
- Cosmos platform orchestrates multi-agent workflows across the full SDLC: triage, authoring, code review, and verification, with built-in experts (PR Author, Pair Review, Tester) that chain together autonomously.
- Prism model routing automatically selects the optimal LLM per turn (GPT-5.5, Claude, Gemini, Kimi), matching frontier model quality at 20–30% lower cost per task.
- Enterprise-grade security: SOC 2 Type II, ISO/IEC 42001, HIPAA/BAA, CMEK encryption, VPC deployment, on-prem option, SAML/OIDC/SCIM, granular RBAC, audit logs, and a contractual ban on training on customer code.
- Multi-surface support spans VS Code, JetBrains, CLI (Auggie), Vim/Neovim, Slack, and ACP-compatible clients, plus GitHub Actions for automated PR review and description generation.
− Cons
- Fully closed-source and proprietary — no self-hosted or community edition exists, and the core platform runs exclusively on Augment's infrastructure with no on-premise option for Indie/Standard/Max plans.
- Credit-based pricing can become expensive at scale: Indie ($20/mo) includes only 40,000 credits (~130 small tasks or ~9 complex ones), auto top-ups cost $15 per 24K credits.
- Indie plan is capped at 1 user with no team features, no SSO, no dedicated support, and no CMEK/ISO compliance — effectively making it a single-developer trial tier.
Pricing
Standard
$60/mo
130K credits
Max
$200/mo
450K credits
Enterprise
Custom
SSO, CMEK, VPC, on-prem
Augment Code is an AI-native engineering platform built around deep codebase understanding. Founded in 2023 and backed by $270M in funding, it has evolved from a context-aware coding assistant into a full multi-agent orchestration platform, with a 70% win rate over GitHub Copilot on SWE-bench coding benchmarks and a rapidly growing enterprise customer base.
The 2026 product is centered on three pillars. Intent is the multi-agent orchestration workspace, integrated into VS Code and JetBrains, that lets developers manage parallel Remote Agents running cloud-based coding tasks — each with full-codebase context and awareness of the entire project's architecture, history, and conventions. Cosmos is the underlying OS for agentic software development: a shared-context layer that coordinates agents across the full software development lifecycle, from planning to review to deployment, with Prism model routing automatically selecting the optimal LLM per task to reduce inference costs by 20–30%.
The Code Review Agent — ranked #1 among AI code reviewers — powers automated PR review, flags security issues and logic bugs, and can auto-approve low-risk pull requests. In March 2026, Augment announced the sunset of its standalone Next Edit and Completions features for non-Enterprise plans, doubling down on agent-centric workflows as the primary interface. Figma MCP integration (one-click install) rounds out the platform for teams working across design and engineering.
Key Features
• Intent: multi-agent orchestration workspace in VS Code and JetBrains
• Cosmos: agentic OS for the full SDLC — shared context across all agents
• Remote Agent: cloud-based coding agents with full-codebase awareness
• Code Review Agent: #1 ranked AI PR reviewer, auto-approves low-risk PRs
• Prism model routing: auto-selects optimal LLM per task, 20–30% cost reduction
• Full-codebase indexing: understands architecture, history, and conventions across all files
• Figma MCP integration: one-click design-to-code workflow
• Multi-model support: GPT-5.5, Claude, Gemini, and others via Prism
• Credit-based pricing (Indie / Standard / Max / Enterprise)
• $270M raised · 70% win rate vs GitHub Copilot on SWE-bench
Version History
Lighter custom environment images — custom environments no longer require Node.js, only bash and git, enabling smaller Docker base images.
Service account attribution for automated workflows; scoped webhook subscriptions per agent; cloud agent hosted artifacts via CLI/API; redesigned webhooks page; org-scope shared files.
MCP Tool Search with settings toggle; conversation forking (editing earlier messages branches into new threads); KaTeX math rendering; improved Mermaid diagram styling.
Transcript persistence with keepTranscriptOnNewSession setting; non-interactive login via --no-tui flag; fixed TUI flickering during indexing/typing/sub-agent work.
New Prism model routing option that efficiently routes each turn to the optimal model (GPT+Kimi or Claude+Gemini), matching best single-model quality at 20–30% lower cost per task.
Signature Snippet
In VS Code with Intent: assign three parallel tasks — 'Refactor the auth module', 'Add OpenTelemetry tracing to all API endpoints', 'Review the incoming PR #204'. Intent routes each to a Remote Agent, tracks progress in a shared workspace, and the Code Review Agent posts a structured review on the PR — all running concurrently with full codebase context.More in this Space
Sourcery
AI code review platform for the AI era. Automated code reviews, security scanning, and team analytics across GitHub, GitLab, VS Code, and JetBrains. Used by 300,000+ developers.
What The Diff
AI-powered PR description generator and code review assistant. Automatically writes pull request descriptions, sends stakeholder notifications, creates changelogs, and provides inline code refactoring.
Blackbox AI
Multi-agent AI coding platform with 12+ agents and 24+ models, featuring Chairman LLM for parallel multi-agent evaluation and end-to-end encrypted inference. Ships across six surfaces: CLI, IDE, Cloud, API, Mobile, and Builder.