Features
Parallel multi-agent orchestration for CLI coding agents
Deterministic Python scheduler (zero LLM overhead)
HMAC-chained audit log with per-entry hash references
Per-artefact transparency log with Ed25519 signatures
Git worktree isolation for each agent
Built-in verification (lint, types, tests, PII checks)
46+ CLI adapters (Claude Code, Codex, Gemini CLI, etc.)
Plugin system (Pluggy) for custom adapters and hooks
MCP server and client for tool interoperability
A2A capability cards for agent-to-agent communication
Cost guards and cost estimation per task
Secrets broker for credential management
Playwright sandbox for UI agents
Web UI and PWA (since 2.0)
Air-gap deploy and on-prem clustering
Role-based agent assignment (PM, architect, engineer, QA)
Structured output generation (requirements, design, code)
Data Interpreter for data analysis tasks
SELA module for self-evolving agents
Multi-agent collaboration and workflow orchestration
Meta-programming support for custom agent behaviors
Modular and extensible architecture
Built-in demo projects and case studies
MIT License fully open-source
Flow orchestration for complex agent pipelines
Integration with GitHub Actions and CI/CD
Community-driven with GitHub and Discord
