Browse
→ AI & Models
→ Engram Alpha MCP
Engram Alpha MCP
Sovereign local-first cognitive memory and knowledge-graph MCP server for AI coding agents. It combines on-device embeddings, vector search, bi-temporal graph memory, trigram full-text search, SQLite WAL storage, cognitive decay scoring, Obsidian sync, and zero-cloud operation behind a uvx-installable stdio server. Public GitHub repository created August 31, 2026.
MCP unverified
Integration
| Transport | stdio |
| Auth | none |
| Endpoint | uvx engram-alpha-mcp |
| Install | uvx engram-alpha-mcp |
Use Cases
| 01 | Give local coding agents durable on-device memory with hybrid vector, graph, and full-text retrieval |
| 02 | Replace flat MCP memory JSON with indexed SQLite-backed memory that stays private on the machine |
| 03 | Sync agent memory workflows with Obsidian while avoiding cloud vector databases or SaaS memory stores |
Tags
memory knowledge-graph vector-search sqlite obsidian local-first apple-silicon python
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>