Skip to main content
Glama
by wubbyweb
README.md1.21 kB
# 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 1. **Agent Isolation**: Each agent should only read/write to its own directory 2. **Shared Resources**: Use the `shared/` directory for cross-agent information 3. **State Persistence**: Update state.json whenever agent status changes 4. **Knowledge Sharing**: Document discoveries in knowledge.md files 5. **Cleanup**: Remove directories for terminated agents periodically ## Last Updated 2025-06-13T04:43:12.420Z

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/wubbyweb/mcp-demo'

If you have feedback or need assistance with the MCP directory API, please join our Discord server