High-performance temporal-associative memory store designed for dynamic contextual retrieval.
CueMap implements a Continuous Gradient Algorithm optimized for associative data structures:
- Intersection (Context Filter): Triangulates relevant memories by overlapping cues
- CuePack-Guided Intent Routing: Uses compiled deterministic rules to add structural facets and weighted intent cues without runtime model calls.
- Recency & Salience (Signal Dynamics): Balances fresh data with salient, high-signal events prioritized by an adaptive impact scoring module.
- Reinforcement (Access-based Learning): Frequently accessed memories gain signal strength, remaining highly accessible even as they age.
- Deterministic Facets & Intent Routing: Extracts synchronous source, evidence, temporal, type, and entity facets, then uses sparse intent cues and reranking during recall.
As of v0.7.0, CueMap's core path is deterministic and embedding-free. GloVe/Ollama cue generation, WordNet/POS expansion, semantic bridges, pattern completion, external lexicon graphs, context expansion/speculation endpoints, and autonomous consolidation have been removed from the core engine.
v0.7.0 also uses numeric per-project memory IDs everywhere. If callers need deterministic upsert/dedupe identity, pass source_key; memory IDs remain compact runtime addresses.
Use this SDK to talk to the Rust engine from TypeScript and JavaScript applications.
npm install cuemapdocker run -p 8080:8080 cuemap/engine:latestimport CueMap from 'cuemap';
const client = new CueMap();
// Add a memory with deterministic cue extraction
await client.add("The server password is abc123", []);
// Recall by natural language
const response = await client.recall({
query_text: "server credentials",
limit: 10,
});
console.log(response.results[0].content);
// Output: "The server password is abc123"// Manual cues
await client.add(
"Meeting with John at 3pm",
["meeting", "john", "calendar"]
);
// Deterministic cues are derived when cues are omitted
await client.add("The payments service is down due to a timeout", []);// Natural language search
const response = await client.recall({
query_text: "payments failure",
limit: 10,
depth: 2,
explain: true,
});
console.log(response.results[0].explain);
// Shows normalized cues, intent cues, and reranking details.CueMap v0.7 adds temporal query intent, CueBridge artifact expansion, and optional reconstruction passes for longer conversational/codebase context.
const response = await client.recall({
query_text: "what did we decide about auth retries?",
query_time: "2026-07-06",
ordered_reconstruction: "auto",
evidence_coverage: "auto",
parent_fusion: "auto",
cuepacks: ["default"],
explain: true,
});Get verifiable context for LLMs with a strict token budget.
const response = await client.recallGrounded(
"Why is the payment failing?",
500 // token budget
);
console.log(response.verified_context);
// [VERIFIED CONTEXT] ...
console.log(response.proof);
// Cryptographic proof of context retrievalManage project snapshots in the cloud (S3, GCS, Azure).
// Upload current project snapshot
await client.backupUpload("default");
// Download and restore snapshot
await client.backupDownload("default");
// List available backups
const backups = await client.backupList();Ingest content from various sources directly.
// Ingest URL
await client.ingestUrl("https://example.com/docs");
// Ingest File (PDF, DOCX, etc.)
// Requires a File or Blob object (browser) or similar in Node
await client.ingestFile(myFileObject);
// Ingest Raw Content with v0.7 logical-block chunking
await client.ingestContent("Raw text content...", "notes.md", {
sourceKey: "docs:notes",
structuralCues: ["source_type:docs"],
segmenter: "logical_block",
});Inspect and wire the brain's associations manually.
// Inspect a cue's relationships
const data = await client.lexiconInspect("service:payment");
console.log("Synonyms:", data.outgoing);
console.log("Triggers:", data.incoming);
// Manually wire a token to a concept
await client.lexiconWire("stripe", "service:payment");Check the progress of background ingestion tasks.
const status = await client.jobsStatus();
console.log(`Ingested: ${status.writes_completed} / ${status.writes_total}`);Disable specific brain modules for deterministic debugging.
const response = await client.recall({
query_text: "urgent issue",
disable_salience_bias: true,
disable_alias_expansion: true,
disable_cuebridge_artifacts: true,
});- Write Latency: ~2ms (O(1) complexity)
- Read Latency: ~3ms (P99, 1M memories)
MIT