Give your AI agents
cross-domain memory
Prime is an optional module that adds knowledge graphs, vector search, and agent recall to the AllSource event store. Hybrid retrieval across graph traversal, HNSW embeddings, and temporal context — in 12 microseconds.
Everything an AI agent needs to remember
Knowledge Graph
Model entities and their relationships as a directed graph. BFS traversal discovers multi-hop connections across domains — customers to orders to products to suppliers — without pre-defined joins.
Vector Embeddings
HNSW index stores high-dimensional embeddings alongside your events. Semantic similarity search finds related entities even when they share no common identifiers or schemas.
Compressed Index
Auto-generated cross-domain scaffolding links entities that co-occur across event streams. Doubles recall accuracy by surfacing connections that keyword and vector search alone would miss.
Recall API
Hybrid search that combines vector similarity, graph traversal, and temporal ordering in a single query. Your AI agents get ranked results with provenance — not just embeddings, but the events that produced them.
12us Projection Lookups
DashMap concurrent reads deliver sub-microsecond projection lookups. Lock-free architecture means recall queries never block event ingestion, even under heavy write load.
Offline / Embedded Mode
Run Prime in-process via a Rustler NIF — no network hop, no separate service. Ship durable AI agent memory inside your Elixir application or as a standalone embedded binary.
One API call. Full context.
# Ask Prime to recall relevant context for an AI agent
curl -X POST https://api.all-source.xyz/api/v1/prime/recall \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "What do we know about customer acme-corp?",
"top_k": 5,
"strategy": "hybrid"
}'
# Response: ranked nodes with provenance and scores
{
"nodes": [
{
"entity_id": "customer:acme-corp",
"type": "customer",
"score": 0.94,
"source": "graph+vector",
"relationships": [
{ "to": "order:ord-7821", "rel": "placed", "weight": 0.88 },
{ "to": "ticket:tkt-312", "rel": "opened", "weight": 0.72 }
],
"last_event": "2026-04-15T09:32:11Z"
},
{
"entity_id": "order:ord-7821",
"type": "order",
"score": 0.88,
"source": "graph",
"payload": { "total": 24500.00, "status": "fulfilled" },
"last_event": "2026-04-14T14:07:44Z"
}
],
"recall_time_us": 12.3,
"strategy_used": "hybrid"
}Works with the Core event store
Prime reads from the Core event store. Every graph node, vector embedding, and index entry is derived from events that Core already persists with WAL + Parquet durability.
All Prime data is a projection. If you rebuild Prime from scratch, it replays events from Core and arrives at the same state. No separate source of truth.
You can run Core without Prime. The event store stands alone for event sourcing, time-travel queries, and projections. Prime is purely additive.
Prime never writes back to Core's event log. It maintains its own graph and vector indexes alongside Core, keeping the dependency direction clean and the event log immutable.
Add durable memory to your AI agents
Prime plugs into any AllSource Core deployment. Knowledge graphs, vector search, and compressed recall — no external dependencies, no separate database.