OpenCastle turns GitHub Copilot, Cursor, and Claude Code into coordinated multi-agent development teams. One orchestrator. Seventeen specialists. Zero chaos.
A complete framework of instructions, skills, agent definitions, workflow templates, and quality gates — battle-tested on a production codebase.
A single coordinator that analyzes, decomposes, delegates, and verifies work across specialist agents — never writes code itself.
From frontend developer to security expert, each with curated tools, model tiers, and domain-specific skills.
Modular knowledge files loaded per task. Keeps context windows lean while enabling deep domain expertise.
Reproducible execution plans for features, bug fixes, data pipelines, schema changes, security audits, and more.
Panel majority vote with independent reviewers, deterministic lint/test/build checks, and browser testing at multiple breakpoints.
Agents capture lessons learned from retries and failures, then graduate them into permanent instructions.
17 specialist agents, each with its own model tier, tool access, and file partition. The Team Lead orchestrator routes tasks based on complexity scoring.
Run npx opencastle init and select your IDE. The CLI
generates the right file format automatically — Copilot agents,
Cursor .mdc rules, or Claude Code commands — plus MCP server configs.
# Install OpenCastle $ npx opencastle init # Choose your IDE: 1) VS Code — .github/ agents, instructions, skills 2) Cursor — .cursorrules & .cursor/rules/*.mdc 3) Claude Code — CLAUDE.md & .claude/ commands # Other commands $ npx opencastle update # Update framework, preserve customizations $ npx opencastle diff # Preview what update would change $ npx opencastle eject # Remove dependency, keep files
8 workflow templates define phases, agent assignments, exit criteria, and file partitions. 8 prompt templates cover common tasks from brainstorming to PR reviews.
| Template | Pipeline |
|---|---|
| feature-implementation | Brainstorm → Research → Foundation → Integration → Validation → QA Gate |
| bug-fix | Triage & Reproduce → Root Cause Analysis → Fix → Verification |
| data-pipeline | Source Analysis → Scraping → Processing → Validation → Import |
| security-audit | Scope → Automated Checks → Manual Review → Panel Review → Remediation |
| performance-optimization | Baseline Measurement → Analysis → Optimization → Verification |
| schema-changes | Schema Analysis → Implementation → Query Updates → Page Integration → Verification |
| database-migration | Planning → Migration → Type Generation → Code Integration → Rollback Test |
| refactoring | Scope & Baseline → Test Coverage → Refactor → Verification → Panel Review |
Multi-layered quality assurance — from automated lint checks to panel reviews with three independent AI reviewers.
Lint, type-check, unit tests, and build verification run automatically after every agent output. No false positives.
Three isolated reviewer sub-agents evaluate high-stakes changes. 2/3 majority wins. BLOCK items become fix requests, not stop signals.
Chrome DevTools MCP validates UI changes at three breakpoints: Mobile (375px), Tablet (768px), Desktop (1440px).
Every agent is asked: “What edge cases am I missing? What test coverage is incomplete? What assumptions could be wrong?”
A real-time dashboard shows agent performance, model tier distribution, session timelines, and panel review outcomes.
52K+ words of curated knowledge, and everything you need to run a coordinated AI development team — from agent definitions to quality gates.
OpenCastle ships with Model Context Protocol server configs for popular services. Agents get direct tool access — no manual wiring required.
One command to install. One Team Lead to coordinate. Seventeen specialists ready to build.
