hub1
由 topguyaii 提供
DevOps & Cloud简介
**Memory Infrastructure for Autonomous Agents**.
描述
该技能的功能
OpenClawdy provides persistent memory storage for AI agents across sessions. Agents store facts, preferences, decisions, and learnings, then retrieve them via semantic search. Advanced features include reputation scoring for proven strategies, cross-agent shared memory pools, and snapshot-based state restoration.
Semantic recall retrieves memories by meaning rather than exact keywords, so agents surface relevant context even when query phrasing differs from what was originally stored.
何时使用
- Remembering user coding preferences across separate sessions
- Sharing bug discoveries and fixes between agents on a team
- Rolling back agent memory after an experiment goes wrong
- Ranking error-handling strategies by past success rate
- Carrying project context into a new conversation without re-explaining
示例工作流
User asks: Create a new API endpoint for user authentication
- 1
Calls memory_recall to retrieve stored preferences about coding style and tech stack
- 2
Finds preference memory: 'User prefers TypeScript for all code'
- 3
Finds fact memory: 'Project uses Next.js 14 with PostgreSQL'
- 4
Generates a TypeScript endpoint consistent with stored preferences
- 5
Calls memory_store to record the architectural decision made during this session
TypeScript API endpoint code, with the agent citing stored preferences as the basis for its implementation choices
前置要求
- Agent wallet address configured for wallet-based authentication
安装
clawhub install topguyaii/hub1运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。