agentic-engineering vs AIWG
Persistent coding-agent workflows compared
agentic-engineering and aiwg both add reusable project context and structured workflows around AI coding tools. agentic-engineering centers on a documentation-first process with task checkpoints and human-controlled merges, while aiwg offers a TypeScript framework for deploying shared workflows and specialist agents across providers.
agentic-engineering: Give Coding Agents a Documentation-First Workflow
A documentation-first harness of ten chain skills for Claude Code, Codex, and compatible coding agents. It provides persistent project memory, implementation contracts, decision records, task planning, and independent verification for long-running development.
AIWG: Reusable Workflows for AI Coding Tools
AIWG provides reusable project context, specialist agents, and workflows for tools including Claude Code, Codex, Copilot, and Cursor. Its TypeScript CLI deploys these assets across providers and supports persistent project artifacts, reviews, and optional decision support.
| agentic-engineering | AIWG | |
|---|---|---|
| Language | — | TypeScript |
| License | MIT | MIT |
| Stars | 5 | 224 |
| Forks | 0 | 34 |
| Last analyzed | Oct 20, 2026 | Oct 20, 2026 |
Key differences
- agentic-engineering focuses on explicit project contracts, session handoffs, independent verification, and a Git workflow that reserves merges for humans; aiwg covers a broader range of specialist workflows, including security, research, operations, and writing.
- agentic-engineering provides markdown skills and workflow conventions rather than a standalone agent or library; aiwg is a TypeScript framework with support utilities for deploying shared assets.
- agentic-engineering describes a shared AGENTS.md entry point and tool-specific pointers; aiwg deploys provider-readable agents, skills, rules, and templates from a shared source.
- agentic-engineering uses a defined task process with a test-ratchet rule and a circuit breaker after three consecutive verification failures; aiwg offers optional bounded loops and lets teams adopt selected workflows.
- Both projects use the MIT license, but their listed adoption signals differ: agentic-engineering has 5 stars and 0 forks, while aiwg has 220 stars and 35 forks.
Choose agentic-engineering if you…
- need a documentation-first workflow with persistent plans, decisions, status, and verification evidence.
- want task checkpoints, a test-ratchet rule, and human-controlled merges.
- are onboarding an undocumented codebase before making source changes.
Choose AIWG if you…
- need to deploy shared instructions and specialist workflows across supported AI coding providers.
- want workflows for areas such as security, research, operations, or writing, alongside software delivery.
- prefer to adopt selected procedures and project artifacts rather than apply one full lifecycle to every task.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.