agentic-engineering-framework
Add task traceability, approval gates, memory, and audits to coding agents.
Add task traceability, approval gates, memory, and audits to coding agents.
Agentic Engineering Framework wraps CLI coding agents with task gates, human approval for destructive actions, persistent session memory, dependency mapping, and audit trails. It coordinates and governs tools such as Claude Code, Cursor, or Aider rather than running the model itself. The framework is intended for long-lived repositories that need traceable commits and controlled agent autonomy, and it is still alpha software.
Resource types
Use cases
Platforms
Connect private data to retrieval systems and agentic applications.
Build and operate an agent platform in infrastructure you control.
Runtime
Protocols & integrations
Capabilities
Audience
Public GitHub facts last synced Jul 10, 2026.
Let Claude create, load, and chain new tools during a conversation.
Structure AI-assisted engineering from requirements through implementation, testing, and review.