mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
Profa
fd2f37eaa0
Changes: - Fix README.md agent counts (48 QE agents = 41 main + 7 subagents) - Fix README.md skill counts (15 QE-specific skills) - Fix v3/README.md agent counts (47 → 48) - Fix init-wizard.ts hooks from 'npx @agentic-qe/v3' to 'npx agentic-qe' - Complete v2 → v2/ folder reorganization (54 items moved) - Update root package.json to point to v3 as main version Verified claims: - 48 QE agents (41 main + 7 TDD subagents) - 15 QE-specific skills - 12 DDD bounded contexts - ~5,600+ tests - HNSW, ReasoningBank, Queen Coordinator features exist Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Agent Memory Storage
Purpose
This directory stores agent-specific memory data, configurations, and persistent state information for individual Claude agents in the orchestration system.
Structure
Each agent gets its own subdirectory for isolated memory storage:
memory/agents/
├── agent_001/
│ ├── state.json # Agent state and configuration
│ ├── knowledge.md # Agent-specific knowledge base
│ ├── tasks.json # Completed and active tasks
│ └── calibration.json # Agent-specific calibrations
├── agent_002/
│ └── ...
└── shared/
├── common_knowledge.md # Shared knowledge across agents
└── global_config.json # Global agent configurations
Usage Guidelines
- Agent Isolation: Each agent should only read/write to its own directory
- Shared Resources: Use the
shared/directory for cross-agent information - State Persistence: Update state.json whenever agent status changes
- Knowledge Sharing: Document discoveries in knowledge.md files
- Cleanup: Remove directories for terminated agents periodically
Last Updated
2025-12-01T08:46:19.574Z