Skip to main content
TENET’s memory system ensures nothing is forgotten between sessions. Every journal entry, code change, and decision is indexed, embedded, and searchable.

​
What Gets Remembered

SourceWhat’s IndexedHow Often
Journal entriesFeatures, fixes, decisions, discoveries, pivotsEvery 60 seconds
Code headers@purpose annotations from source filesEvery 5 minutes
Manual memoriesInsights, notes, decisions via jfl_memory_addOn demand

​
How Search Works

TENET uses hybrid search — combining lexical and semantic approaches for best results: 
Query: "CLI startup optimization"
         |
    +----+----+
    |         |
  BM25+    Embedding
  (lexical) (semantic)
    |         |
    +----+----+
         |
   Reciprocal Rank
      Fusion (RRF)
         |
    Ranked Results

​
BM25+ (Always Available)

Term-frequency scoring with:
  • Stopword removal and phrase detection
  • Adaptive document length normalization
  • Query term weighting based on IDF
  • Positive IDF floor (BM25+ variant) — common terms still contribute

​
Semantic Search (When Embeddings Available)

Cosine similarity on text-embedding-3-small vectors:
  • 1536 dimensions
  • OpenAI or OpenRouter fallback
  • Auto-backfill: if key was missing when indexed, embeddings are added later

​
Reciprocal Rank Fusion

Merges BM25 and embedding results by rank position, not raw scores. More robust than linear interpolation because it doesn’t require score normalization.

​
Current Stats

jfl memory status

total_memories: 349
by_type: {feature: 96, milestone: 96, decision: 55, fix: 40, ...}
embeddings: {available: true, count: 349, model: "openrouter/text-embedding-3-small"}
349/349 memories embedded — zero gaps.

​
Graph Edges

Memories aren’t isolated. They connect to each other:
Edge TypeMeaningExample
updatesNew info supersedes old”CLI speed now 98ms” updates “CLI speed was 6.7s”
contradictsNew finding invalidates old”Connection pooling helps” contradicts “Keep connections short”
related_toTopically connectedMemory about eval system → related to agent config
caused_byCausal relationship”Test failures” caused_by “Dependency upgrade”
part_ofHierarchical groupingSession memories → part_of project milestone
# Add a link via API
curl -X POST http://localhost:4360/api/memory/link \
  -H "Content-Type: application/json" \
  -d '{"from": 42, "to": 17, "type": "updates"}'

​
Code Header Indexing

Files with @purpose annotations are automatically indexed: 
/**
 * Memory Indexer Module
 *
 * @purpose Automatic indexing of journal entries and code headers
 */
This creates a searchable memory entry:
  • Source: file
  • Type: code-header
  • Content: src/lib/memory-indexer.ts: Automatic indexing of journal entries and code headers
Scans: src/, packages/, scripts/, eval/ Updates if @purpose changes. Deduped by file path.

​
Knowledge Doc Lifecycle

Knowledge docs (VISION.md, THESIS.md, etc.) are audited for staleness: 
jfl organize

  Doc Health

  ✓  VISION              0d old  drift:   20%  mentions: 221
  ✓  THESIS              0d old  drift:   20%  mentions: 223
  ✓  NARRATIVE            0d old  drift:   20%  mentions: 206

  0 of 5 docs need attention
When docs drift from journal evidence, jfl organize generates a PENDING.md with proposed updates and open questions for human review.

Search

BM25+ hybrid search internals and query optimization.

Graph Edges

Structured relationships between memories.

Embeddings

Auto-backfill, model selection, and fallback behavior.

Code Headers

Indexing @purpose annotations from source files.