Skip to main content

​
Overview

Mengram gives your AI three distinct memory types, inspired by how human memory works:
TypeStoresExample
SemanticFacts, knowledge, preferences”User prefers dark mode and uses Python 3.12”
EpisodicEvents, experiences, interactions”Fixed an OOM bug on Jan 15 by reducing pool size”
ProceduralWorkflows, processes, skills”How to deploy: 1) run tests, 2) build, 3) push to main”
When you call m.add(messages), all three types are extracted automatically from the conversation.

​
Semantic Memory

The knowledge graph. Entities with facts, types, and relationships. This is the core memory layer. 
# Search semantic memory
results = m.search("user preferences")
# Returns entities with facts and scores

# Get a specific entity
entity = m.get("PostgreSQL")
# {"name": "PostgreSQL", "type": "technology", "facts": [...]}

​
Episodic Memory

Autobiographical events — what happened, when, with whom, and what the outcome was. Each episode has a summary, context, outcome, and participant list. 
# Search episodes
events = m.episodes(query="deployment issues")
# [{"summary": "Fixed OOM on Railway", "outcome": "Resolved by reducing pool", ...}]

# List recent episodes
recent = m.episodes(limit=10)

# Time-range filter
jan_events = m.episodes(after="2026-01-01", before="2026-02-01")

​
Procedural Memory

Learned workflows and processes. Mengram extracts step-by-step procedures from conversations and tracks which ones work and which fail. 
# Search procedures
procs = m.procedures(query="deploy")
# [{"name": "Deploy to Railway", "steps": [...], "success_count": 5}]

# Report success/failure — triggers experience-driven evolution
m.procedure_feedback(proc_id, success=True)

# On failure with context, the procedure evolves automatically
m.procedure_feedback(proc_id, success=False,
    context="Step 3 failed: OOM on build",
    failed_at_step=3)

# View how a procedure evolved over time
history = m.procedure_history(proc_id)
# {"versions": [v1, v2, v3], "evolution_log": [...]}

​
Graph RAG

Memories aren’t flat — they’re connected in a knowledge graph. When you search, Mengram doesn’t just find direct matches. It traverses relationships to surface context that simple vector search misses. 
Query: "Python"
  → Direct match: Python (technology)
    → 1 hop: Django (framework) — "used_with" → Python
      → 2 hop: Railway (platform) — "deployed_on" → Django
This 2-hop traversal means searching for “Python” also returns your Django deployment setup on Railway — context that a flat vector search would never find. Control traversal depth with graph_depth: 
m.search("Python", graph_depth=0)  # direct matches only
m.search("Python", graph_depth=2)  # default — 2 hops
m.search("Python", graph_depth=4)  # deep traversal

​
Ebbinghaus Decay

Mengram models memory decay like the human brain. Facts that haven’t been accessed recently fade in importance, while frequently recalled facts get stronger. The formula: effective_importance = base_importance * e^(-0.03 * days_since_access) + frequency_boost
  • A fact accessed yesterday has full weight
  • A fact untouched for 30 days decays to ~40% weight
  • A fact accessed 100 times gets a frequency boost regardless of recency
This means search results naturally prioritize fresh, relevant knowledge over stale information — without manual cleanup. The curator agent also periodically finds and archives facts that have become outdated or contradicted by newer information.

​
Confidence Scoring

Procedural memory uses confidence scoring to decide when to create new procedures:
ConfidenceAction
< 0.4Skip — not enough evidence
0.4 – 0.6Create a suggestion trigger — user decides
>= 0.6Auto-create the procedure
Confidence is calculated from episode clustering — how many similar events support the pattern. This prevents noisy one-off events from becoming permanent workflows. Search all three types at once with a single call: 
results = m.search_all("deployment problems")
# {
#     "semantic": [...],    # knowledge graph entities
#     "episodic": [...],    # related events
#     "procedural": [...]   # relevant workflows
# }