Engram
JSON →Persistent memory layer for AI agents with semantic search, consolidation, and cross-session intelligence via MCP.
Install
npx engram-serve Tools · 17
- engram_remember Store a memory. Auto-extracts entities and topics.
- engram_recall Recall relevant memories via semantic search.
- engram_ask Ask a question and get a synthesized answer with confidence and sources.
- engram_briefing Structured session briefing — key facts, pending commitments, recent activity.
- engram_consolidate Run consolidation — distills episodes into semantic knowledge, discovers entities, finds contradictions.
- engram_surface Proactive memory surfacing — pushes relevant memories based on current context.
- engram_alerts What needs attention right now — pending commitments, stale follow-ups, contradictions.
- engram_audit Cross-reference external content (e.g. CLAUDE.md) against the vault — flags outdated claims.
- engram_checkpoint Save current session context before it is lost (extracts durable memories from a summary).
- engram_connect Create a relationship between two memories in the knowledge graph.
- engram_forget Forget a memory (soft or hard delete).
- engram_entities List all tracked entities with memory counts.
- engram_stats Vault statistics — memory counts by type, entity count, etc.
- engram_ingest Auto-ingest conversation transcripts or raw text into structured memories.
- engram_import_obsidian Import an Obsidian vault (wikilinks, tags, frontmatter).
- engram_import_claude_code Import memory from Claude Code (CLAUDE.md files, sessions).
- engram_powered_by Returns attribution info about the memory system.
Environment variables
GEMINI_API_KEYENGRAM_LLM_API_KEYENGRAM_LLM_BASE_URLENGRAM_HOSTENGRAM_PORTENGRAM_AUTH_TOKEN
Links
★ 39 GitHub stars