Features
AI-powered unit test generation for methods and functions
Regression test generation and verification for every Pull Request
Full repository regression guard scanning entire codebase
Earl personal AI test engineer within VSCode
Generates mocks, happy paths, edge cases, and documentation
Green and red test generation (passing and failing tests)
Pull Request tab to test latest changes
Repository guardrails to enforce quality standards
API and workflow protection against breaking changes
Risk and coverage visibility dashboards
Early Quality Score (EQS) to quantify test quality
Test generation results on full repository with PR coverage
Strict Privacy Mode for sensitive code
CLI Agent for non-IDE workflows
Admin dashboard with usage reports and trends
Multi-agent orchestration with handoffs
Sandbox Agents for containerized long-running tasks
Agent-as-tool delegation (v0.15.0+)
Realtime Agents with gpt-realtime-2 voice support (v0.17.6+)
Human-in-the-loop mechanisms
Automatic session history management
Built-in tracing for debugging
Provider-agnostic LLM support (100+ models via LiteLLM)
Redis session support (optional, v0.17.6+)
Instructions, tools, and guardrails configuration
Jupyter notebook compatibility
Supports OpenAI Responses and Chat Completions APIs
