Memory Bridge
技能 已验证 活跃Bridge Claude Code auto-memory into AgentDB with ONNX embeddings, deduplicate, and enable unified cross-project search
To make Claude Code's auto-generated memories searchable across projects and sessions by storing them with embeddings in AgentDB.
功能
- Bridge Claude Code auto-memory to AgentDB
- Generate ONNX embeddings for memory entries
- Deduplicate memory entries using cosine similarity
- Enable unified cross-project semantic search
- Automatic import via SessionStart hook
使用场景
- Searching across all your past Claude Code sessions and projects
- Recalling specific information learned or generated in previous interactions
- Leveraging historical context for new tasks without manual import
- Enabling advanced RAG patterns across auto-generated memories
非目标
- Managing external AgentDB instances
- Providing general-purpose text search unrelated to Claude Code memories
- Replacing Claude Code's core functionality
实践
- Memory management
- Data indexing
- Semantic search
先决条件
- Claude Code environment with auto-memory enabled
- AgentDB accessible with HNSW indexing
- Node.js runtime for helper scripts
安装
请先添加 Marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-rag-memory@ruflo质量评分
已验证类似扩展
Agentdb Query
99Query AgentDB through the controller bridge -- semantic routing, hierarchical recall, causal graphs, context synthesis, pattern store/search
V3 Memory Unification
99Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).
Memory Management
99AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous tasks, sharing knowledge between agents, building knowledge base. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.
Embeddings
99Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
Validate Plugin
100Validate a Claude Code plugin structure, frontmatter, and MCP tool references
Running Claude Code Via Litellm Copilot
100当通过本地 LiteLLM 代理将 Claude Code 路由到 GitHub Copilot 时使用，以减少直接的 Anthropic 支出，配置 ANTHROPIC_BASE_URL 或 ANTHROPIC_MODEL 覆盖，或对 Copilot 代理设置失败进行故障排除，例如 model-not-found、无 localhost 流量或 GitHub 401/403 身份验证错误。