You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
1.7 KiB
1.7 KiB
Phase 0: Context System Bootstrap
Date: 2026-02-13 Objective: Create the scaffolding for the G1 expert agent knowledge base
What Was Done
-
Created full directory structure:
context/— 13 topic files (all provisional, ready for data)reference/— glossary.yaml with initial termsexamples/— empty, ready for worked examplesphases/— this fileassets/— empty, ready for images/diagramstools/— empty, ready for utility scripts_archive/— empty
-
Created CLAUDE.md with:
- Expert agent identity declaration
- Lookup protocol (7-step question answering procedure)
- Quick Topic Lookup table (17 rows)
- Idea formulation protocol
- Conventions and DO NOT rules
- Evidence tier system (T0-T4)
- Key concepts map
- Content addition guidelines
- History table
-
Created topic files for:
- hardware-specs, joint-configuration, sensors-perception
- locomotion-control, manipulation
- sdk-programming, ros2-integration
- simulation, learning-and-ai
- power-system, safety-limits
- networking-comms, deployment-operations
- equations-and-bounds, open-questions
-
Created glossary with ~12 initial terms across hardware, sensors, software, control, power, and safety categories.
What's Next
- Phase 1: Populate context files from official Unitree documentation, spec sheets, and SDK repos
- Priority sources to find:
- Official Unitree G1 spec sheet / product page
- unitree_sdk2 GitHub repository and documentation
- unitree_ros2 GitHub repository
- URDF/MJCF models (MuJoCo Menagerie, Unitree repos)
- Published papers on G1 locomotion / control
- Community resources (forums, Discord, YouTube teardowns)