Show HN:Jylus – give AI systems evidence from changing data.

Jylus launched a Show HN developer API that ingests logs, OpenTelemetry, Docker events and telemetry and returns a proof-bound "Context Pack" with facts, timeline evidence, contradictions, freshness and proof IDs, reporting 75.130% Recall@10, 45.663% MRR@10 and 31.473% program accuracy with zero model calls on its TEMPO full live API cohort. The service offers a single-use trial that creates an isolated one-time tenant, compiles the result, blocks further access immediately and runs the tenant through a deletion lifecycle, with no account required. A sample /api/v1/analyze response shows edge-17 reporting 12.4 ms latency with an estimated token reduction of 76.33% (1,842 source tokens to 436 retained evidence tokens).

Test better evidence. Ingest evidence, generate a proof-bound Context Pack, then compare model input and answers on your workload. Developer workload access Send logs, OpenTelemetry, Docker events, telemetry or awkward JSON. Measure ingest, retrieval and proof-bound Context Packs with your own data. Send events, search retained history and test mixed structured, semantic and relationship queries. Single-use trial No account is required. Jylus creates an isolated one-time tenant, compiles the result, blocks further access immediately, and sends the tenant through the deletion lifecycle. The response contains source-backed facts, proof IDs, conflicts, missing evidence and the deletion state. Test AI evidence Use your own current state, history and documents. Jylus returns a bounded Context Pack with facts, timeline evidence, contradictions, freshness and proof IDs. /api/v1/analyze with the question your model needs answered. 75.130% Recall@10 · 45.663% MRR@10 31.473% program accuracy · zero model calls TEMPO · FULL LIVE API COHORT The complete test loop The response keeps facts, temporal evidence, contradictions, missing evidence and proof IDs explicit. Efficiency values are measured from your own request. curl https://api.jylus.ai/api/v1/analyze \ --request POST \ --header "Authorization: Bearer $JYLUS READ API KEY" \ --header "Content-Type: application/json" \ --data '{ "source": "current", "text": "What is the latest latency reported by edge-17?", "vector": { "text": "latest edge device response time" }, "context": { "mode": "decision", "token budget": 2000, "max facts": 18, "max timeline": 12, "include documents": false }, "scan limit": 1000, "limit": 24, "include results": false }' { "success": true, "complete": true, "execution mode": "native current", "context": { "decision context id": "ctx ...", "decision readiness": { "status": "ready", "can answer": true }, "facts": { "statement": "edge-17 reported 12.4 ms latency", "proof ids": "evt 001" } , "timeline": { "observed at": "2026-08-21T08:00:00Z", "proof ids": "evt 001" } , "contradictions": , "missing evidence": , "context efficiency": { "source tokens estimated": 1842, "retained evidence tokens estimated": 436, "estimated token reduction percent": 76.33 }, "proof": { "event ids": "evt ..." , "complete": true } } } Test the data engine curl https://api.jylus.ai/api/v1/events \ -H "Authorization: Bearer $JYLUS API KEY" \ -H "Idempotency-Key: try evt 001" \ -H "Content-Type: application/json" \ -d '{ "stream": "my-workload", "events": { "id": "evt 001", "type": "telemetry.sample", "occurred at": "2026-08-21T08:00:00Z", "data": { "device": "edge-17", "latency ms": 12.4 } } }'