Download
Agent Apprenticeship is an open infrastructure project for turning real AI-agent work into reusable learning signals. It lets local agents complete tasks through iterative workflow loops, then records the process as experience that can improve future agents. Apprentice agents can be paired with mentor agents, human reviewers, or domain experts depending on the selected mode. The project supports Codex, Cursor, Claude Code, OpenClaw, OpenCode, Hermes Agent, and custom agent commands. Its seed dataset includes curated tasks, reusable lessons, execution traces, work episodes, and structured experience records. It is designed for long-horizon agent work, workflow evaluation, runtime training, and shared improvement across an agent ecosystem.
Features
- Iterative agent workflow loops
- Autonomous, expert-led, and organization modes
- Codex, Cursor, Claude Code, OpenClaw, OpenCode, and Hermes support
- Reusable experience compilation records
- Seed dataset with agent traces and lessons
- Local CLI setup and configuration
Project Samples
