Features
Simulated world with 9 apps (notes, messaging, shopping, etc.)
457 APIs for manipulating app states
106 fictitious users with realistic digital activities
750 benchmark tasks (normal and challenge)
State-based unit tests for robust evaluation
Collateral damage detection (unexpected state changes)
Interactive Jupyter notebook for exploration
Local CLI via pip install appworld
Leaderboard for comparing agent performance
ACL 2024 Best Resource Paper award
Live knowledge graph from code, commits, issues, and docs
Feasibility analysis: flags buildable vs risky items
Technical design document generation grounded in service topology
Impact assessment maps services, APIs, and dependencies across repos
Auto-scoping epics into Jira/Linear stories with effort estimates
One-shot production code generation grounded in service patterns
AI code reviews with cross-repo impact analysis
Production issue triage via MCP
Conversational learning from Slack and Jira
Accelerated onboarding via system-level Q&A in coding agents
Create Jira tickets and merge requests from Slack
MCP server for integration with Cursor, Claude Code, Codex
On-prem or cloud deployment
No code storage or model training
