Memory Bridge
- 648 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
memory-bridge is a Claude Flow skill that imports Claude Code auto-memory markdown into AgentDB with 384-dim ONNX embeddings, deduplication, and unified cross-project search for developers who need semantic recall across
About
memory-bridge is a RuFlo Claude Flow skill that bridges Claude Code auto-memory into AgentDB with ONNX embeddings, deduplication, and unified cross-project search. Claude Code stores memories as markdown in ~/.claude/projects/*/memory/*.md; memory-bridge reads those files for the current project or all projects via --all-projects, generates 384-dim ONNX embeddings using all-MiniLM, deduplicates with --dedupe, and exposes results through memory_search_unified. MCP tools memory_import_claude and memory_bridge_status track import health. Developers reach for memory-bridge when agent context scattered across Claude Code memory files must become searchable alongside AgentDB patterns. Bash and Read access support filesystem traversal of project memory directories.
- memory-bridge
Memory Bridge by the numbers
- 648 all-time installs (skills.sh)
- +10 installs in the week ending Jul 26, 2026 (Skillselion tracking)
- Ranked #562 of 4,347 Backend & APIs skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill memory-bridgeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 648 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you search Claude Code memory across projects?
Use memory-bridge for development tasks
Who is it for?
Developers using Claude Code auto-memory who need AgentDB semantic search and deduplication across multiple projects.
Skip if: Developers without Claude Code memory files or teams not running claude-flow AgentDB and memory_import_claude MCP tools.
When should I use this skill?
Claude Code memory files must be imported, deduplicated, or searched uniformly across projects via AgentDB.
What you get
AgentDB-indexed memories, 384-dim ONNX embeddings, deduplicated entries, and unified cross-project search results.
- AgentDB memory index
- unified search index
By the numbers
- Generates 384-dim ONNX embeddings using all-MiniLM
- Reads Claude Code memory from ~/.claude/projects/*/memory/*.md paths
Files
Memory Bridge
Import Claude Code's native auto-memory files into AgentDB for semantic search across sessions and projects.
What it does
Claude Code stores memories as markdown files in ~/.claude/projects/*/memory/*.md. This bridge: 1. Reads all memory files (current project or all projects) 2. Generates 384-dim ONNX embeddings (all-MiniLM-L6-v2) 3. Stores in AgentDB's claude-memories namespace with HNSW indexing 4. Deduplicates against existing entries (cosine similarity > 0.95) 5. Enables unified semantic search across all memory sources
Steps
1. Check bridge health: mcp__claude-flow__memory_bridge_status({}) Verify: Claude files count, AgentDB entries, SONA state, connection status.
2. Import memories:
- Current project:
mcp__claude-flow__memory_import_claude({}) - All projects:
mcp__claude-flow__memory_import_claude({ allProjects: true })
CLI alternative:
node .claude/helpers/auto-memory-hook.mjs import-all3. Verify import: mcp__claude-flow__memory_bridge_status({}) Confirm entry counts match expected file counts.
4. Deduplicate (if --dedupe): Search for near-duplicate entries (cosine > 0.95) and merge them, keeping the most recent version.
5. Test unified search: mcp__claude-flow__memory_search_unified({ query: "test query", limit: 3 }) Results include source attribution: claude-code, auto-memory, or agentdb.
Auto-import
The bridge runs automatically on session-start via the SessionStart hook. Manual invocation is only needed for:
- First-time import of all projects
- After bulk memory changes outside normal sessions
- Forcing re-embedding after model updates
Integration with ruvector
When ruflo-ruvector is loaded, bridged memories are also indexed by ruvector for:
- Hybrid search (sparse + dense with RRF)
- Graph RAG multi-hop queries across memory entries
- Brain knowledge sharing across sessions
Related skills
Lark Openapi ExplorerInstantly explore, test, and generate calls against the full Lark (Feishu) OpenAPI surface without leaving their agent workflow.493k
Lark EventConsume real-time events from Lark/Feishu as structured NDJSON streams inside AI agent workflows.387k16kLark Openapi ExplorerWhen an existing Lark/Feishu skill or CLI command cannot fulfill a specific requirement and they need to discover and invoke the exact native OpenAPI endpoint.386k16k
Just ScrapeQuickly search, crawl, extract structured JSON, or monitor web pages without writing custom scraping code.245k41Lark AppsQuery the current visibility and permission scope of a Lark (Feishu) app without writing HTTP client code.235k16k
Design An InterfaceGenerate multiple radically different interface or API designs in parallel before committing to one.188k198kHow it compares
Choose memory-bridge over manual memory copy when Claude Code markdown must become deduplicated, embeddable AgentDB records with unified search.
FAQ
Where does memory-bridge read Claude Code memories?
memory-bridge reads markdown files from ~/.claude/projects/*/memory/*.md. The --all-projects flag imports every project; otherwise only the current project memory directory is processed.
What embedding model does memory-bridge use?
memory-bridge generates 384-dim ONNX embeddings using all-MiniLM before storing entries in AgentDB. --dedupe removes duplicates prior to enabling memory_search_unified across projects.