#325 · Primary category: AI Coding Assistants
Aegis
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
Project last updated:08/29/26
GitHub Stars
1.1K
Forks
51
Contributors
3
License
MIT
Why we included this project
Aegis is a method pack rather than a standalone agent: you drop its rules, prompts, and install scripts into an existing coding-agent host like Codex, Claude Code, or OpenCode. It adds a workflow discipline that makes the agent plan against the project's actual baseline before it edits, and it refuses to report anything as done without fresh evidence. Across long tasks it also checks for drift against the agreed design. That is the failure mode most teams hit when they let agents loose on real, long-lived codebases: the agent drifts from the intended architecture and confidently refactors against the grain of the project. If you have seen that, Aegis gives you a concrete protocol to constrain the agent and cut down on rework.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.