Skip to main content

OpenCode

AI for software development — on your premises.

State-of-the-art coding models deployed locally. Not a single line of your code leaves your infrastructure.

Model tiers

Choose the model tier that matches your hardware and performance requirements.

OpenCode model tiers with SWE-bench scores
TierModelParamsVRAMSWE-bench
ProMiniMax M2.5230B115 GB74.0%
AirQwen 3.5122B100 GB72.0%
FlashDevstral Small 230B24 GB68.0%

SWE-bench Verified scores. Models updated as part of the annual retainer.

Capabilities

Code Review & Bug Fixing

In-depth analysis of pull requests, diff reviews, and targeted bug fixes with context-aware suggestions.

Greenfield Development

Spec-driven development from requirements to working code. Build complete features with multi-file context.

GitHub Integration

Connect directly to your repositories. Review PRs, understand codebases, and push changes — all locally.

Codebase Understanding

Index and query large codebases. Ask questions, trace call paths, and understand unfamiliar projects quickly.

Test-Driven Development

Generate comprehensive test suites, identify edge cases, and ensure coverage across your codebase.

Multi-Agent Orchestration

Delegate complex tasks to specialised sub-agents. Parallelise work across multiple AI instances.

Ready to code with AI — privately?

Book a discovery session to understand your hardware requirements and integration approach.

Book a Discovery →