Ingest → Extract → Verify → Query.
Four steps. Cryptographic proof at every stage.
Send raw content — text, docs, conversation logs, code diffs. Stored as an artifact in a namespace.
LLM-powered extraction breaks content into structured assertions: subject-predicate-object triples with temporal markers. Each gets a 768-dim embedding.
Fallback chain: Llama 3.3 70B → DeepSeek R1 → Qwen3 480B → Mistral Small 3.1 → Gemini Flash Lite → Grok 4.1 Fast. Pipeline never breaks.
Assertion grounded against source spans. LLM evaluates support. Result: Ed25519-signed receipt with confidence score, evidence chain, Merkle chain position.
The receipt is the product.
Six retrieval channels fused with Reciprocal Rank Fusion + epistemic multipliers:
Most queries never hit Tier 3.
The atomic unit is an assertion: a subject-predicate-object triple with metadata. Assertions are append-only — never updated or deleted. Superseded assertions get new ones pointing back. Full temporal history is always queryable.
{
"assertion_id": "ast_9f2a...",
"subject": "auth_middleware",
"predicate": "uses",
"object": "JWT with RS256",
"confidence": 0.94,
"valid_from": "2026-04-01T00:00:00Z",
"valid_to": null,
"source_type": "coding_agent",
"namespace_id": "ns_project_auth",
"embedding": [0.023, -0.041, ...], // 768-dim
"receipt_id": "rct_7f3a..."
}
| Layer | Technology | Purpose |
|---|---|---|
| Compute | Cloudflare Workers (20+) | Edge processing |
| Database | Supabase Postgres + pgvector | Assertions, receipts, FTS, vectors |
| Embeddings | Cloudflare Workers AI (bge-base-en-v1.5) | 768-dim, free, on-edge |
| LLM | OpenRouter (6-model fallback) | Extraction + verification |
| Object Storage | Cloudflare R2 | Compression sidecars |
| Cache | Cloudflare KV | Delta bloom filters |
| Real-time | Supabase Realtime | Delta push |
| Crypto | Web Crypto (Ed25519, SHA-256) | Receipt signing |
No. A vector DB stores embeddings. We store assertions, verify them, sign them, detect conflicts, and provide six retrieval channels. Vectors are one channel of six.
Different primitives. Mem0 stores memories. We store assertions with cryptographic receipts. See /compare for the full breakdown.
RAG retrieves chunks. We extract structured facts, verify them, produce receipts. RAG: "the document said X." VS: "the fact X was verified at time T with confidence C, signed by key K."
Use VS as a memory layer and ignore receipts. Seven-channel retrieval, conflict detection, temporal validity, governance all work independently.
Free: 50,000 assertions/month. No credit card. No trial expiration.