AI development with audit logs, HITL gates, and traceability built in.
Multi-agent ensemble review, phase-gate approvals, requirements-to-deployment traceability. 76% of devs won't trust AI for deployment (SO 2025) — AIWG's gates are why we can.
MIT licensed. Runs on your infra. → /team
cognitive architecture — agents, skills, rules, semantic memory, multi-agent ensembles, traceability
orchestration runtime — Agent Loop, daemon, Mission Control, aiwg serve with HITL drawer
isolation runtime — optional VM-grade per-agent isolation (/sandbox)
Write once. Deploy to Claude Code, Cursor, Copilot, Factory AI, Codex, Hermes, OpenCode, OpenClaw, tinyhumans.ai, Warp, or Windsurf with the same artifacts.
Identical-form portability — same agents, same memory, same gates, across 11 supported AI coding platforms.
Claude Code — full orchestration with autonomous workflows
Factory AI — Tier 1 headless droid exec, native MCP/tasks/missions
Cursor — inline agent assistance and rule enforcement
GitHub Copilot — contextual agents with workspace instructions
OpenAI Codex — autonomous agent orchestration
Hermes — first-class deployment target, token-optimized templates
OpenCode — extensible agents with tool and hook integration
OpenClaw — native behaviors support
tinyhumans.ai — personal-AI runtime with global skill install
Warp Terminal — terminal-native context and command workflows
Windsurf — cascade agents with rule-driven guidance
sdlc-complete — full lifecycle: requirements, architecture, implementation, testing, deployment, hypercare
aiwg use sdlc
media-marketing-kit — campaign, content, brand, analytics
aiwg use marketing
voice — SOUL.md identity, brand voice consistency, content blending
ops-complete — sysops, devops, itops, stream extensions; 9 templates from real ops patterns
forensics-complete — digital forensics, IR, IOC extraction, chain of custody
research-complete — FAIR/PROV provenance, GRADE quality, citation guard
Plus 21 addons covering daemon, Mission Control, RLM, behaviors, agentic-installer, prose-integration, and more.
188 agents · 128 skills · 50 CLI commands · 100+ artifact templates
Agent Loop / Ralph — closed-loop self-correction; external Ralph survives crashes for 6-8h+ autonomous runs
Daemon mode — persistent supervisor with web UI, scheduled tasks, multi-room messaging, cross-session memory
Mission Control — parallel agent loops as background missions with live dashboard
aiwg serve — PTY orchestrator + HITL drawer; supervise and approve agent actions from a browser
RLM — recursive context decomposition for repos that don't fit in any one window
Path A — Project-local: drop a bundle into .aiwg/extensions/, addons/, frameworks/, or plugins/. Auto-discovered, no fork.
Path B — Fork: customize AIWG core, dev mode, contribute back upstream.
Path C — Corpus: cross-project sharing without going public.
Identical-form portability — bundle layout is byte-identical across project-local, fork, and upstream. aiwg promote is a hash-verified copy with zero rewrite.
aiwg new-bundle my-rule --type extension --starter rule
Run Claude Code in its own VM, for hours, on your hardware.
QEMU/KVM or Docker per-agent isolation, virtiofs shared storage, telemetry, reconciliation. For regulated industries, on-prem requirements, and 6–8h+ autonomous coding runs.
# CLI + multi-platform
npm i -g aiwg
Requires Node.js 18+. Works with Claude Code, Codex, Copilot, Cursor, Factory AI, Hermes, OpenCode, OpenClaw, tinyhumans.ai, Warp, and Windsurf.
# Claude Code plugin
/plugin marketplace add jmagly/aiwg
/plugin install sdlc@aiwg
No npm required. Also: marketing@aiwg, voice@aiwg, ops@aiwg, utils@aiwg
# Install framework to your project
cd my-project && aiwg use sdlc
# Start an interactive workflow in Claude Code
/intake-wizard --interactive
# Provide guidance to tailor the output
/flow-inception-to-elaboration --guidance "focus on API design"
+ Complete on-demand indexes (#1784) — provider deployment resolves the
+ OpenHuman project context restored (#1785) — full deployment renders the
+ Generic vault release path — the tag wrapper and migration verifier now
+ Onboarding wire-in — existing projects are consistently directed through
+ Documentation fixes — Pagenary entity-safe inline markdown, a compact
Type changelog or releases below for full history.
