Test Jylus with your workload.
Developer workload access
Test Jylus with your workload.
Send logs, OpenTelemetry, Docker events, telemetry or awkward JSON. Measure ingest, retrieval and proof-bound Context Packs with your own data.
Get a free API key →Read developer docs
Using an AI coding agent?Give it the Jylus quickstart and let it wire the first event, query and Context Pack into your application.
No credit cardNo sales callYour data stays yoursNever used to train general-purpose AI
AI / AGENTS
Test better evidence.
Ingest evidence, generate a proof-bound Context Pack, then compare model input and answers on your workload.
Test AI evidence →AI quickstart
DATA / REAL-TIME SYSTEMS
Push the data engine.
Send events, search retained history and test mixed structured, semantic and relationship queries.
Test the data engine →API quickstart
Measured native stack50.695% QASPER NDCG@1075.130% QASPER Recall@1036.443% FinQA execution40.048% live TEMPO NDCG@10Methodology →
Free storage1 GB
Ingest capacity1,000 events/sec
Data regionSydney, Australia
AccessHTTPS API
Single-use trial
Drop in data. Get a proof-bound result.
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.
Start with a synthetic example:State over timeMissing informationConflicting recordsLate correction
Text, JSON or log fileMaximum 32 KB. The browser reads the file into the field below.
DataJSON: use an array or one object per line. Text: leave a blank line between records; start with \[YYYY-MM-DD\] to preserve the date. Dated log lines are separate records.
Question
State as of (UTC, optional)
State effective as of (UTC, optional)
Evidence known as of (UTC, optional)
Use these together to separate what happened from what was known at the time.Run single-use trial
RESULTYour compiled evidence will appear here.
The response contains source-backed facts, proof IDs, conflicts, missing evidence and the deletion state.
Test AI evidence
See what your model gets when the evidence improves.
Use your own current state, history and documents. Jylus returns a bounded Context Pack with facts, timeline evidence, contradictions, freshness and proof IDs.
1. 01 Send dataUse real records, including irrelevant history and conflicting values. 2. 02 Ask Jylus for evidenceCall `/api/v1/analyze` with the question your model needs answered. 3. 03 Inspect the Context PackCheck retained facts, proof IDs, token estimate, completeness and execution time. 4. 04 Compare against your modelRun the same question with your current context path and the Jylus evidence. Generate your first Context Pack →
QASPER · 1,335 TEST QUERIES50.695% NDCG@10
75.130% Recall@10 · 45.663% MRR@10
_NATIVE JYLUS STACK_FINQA · 1,147 TEST CASES36.443% execution accuracy
31.473% program accuracy · zero model calls
TEMPO · FULL LIVE API COHORT40.048% NDCG@10 Measured on the native Jylus stack.QASPER uses the untouched mteb/QASPER test task. FinQA uses the official program executor. TEMPO is the full 1,730-question public-v1 API result. Metrics measure different tasks and are reported separately.
The complete test loop
Ask for evidence. Inspect exactly what your model receives.
The response keeps facts, temporal evidence, contradictions, missing evidence and proof IDs explicit. Efficiency values are measured from your own request.
CONTEXT PACK REQUESTPOST /api/v1/analyze
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 }'
ABRIDGED EXAMPLE RESPONSEapplication/json
{ "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
From account to a real event in minutes.
1. 01 Create a free workspaceEmail, GitHub or Google. No payment step. 2. 02 Copy the one-time API keyThe key is scoped and shown once. 3. 03 Send your real payloadThe Developer hub includes HTTPS, NATS JetStream, Docker and OpenTelemetry setup. Create free workspace →
FIRST EVENTcurl
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 } }] }'