One engine that turns habit data into patterns, risks and plans. It powers a privacy-first tracking app for people, and the same intelligence is sold to AI agents by the request — paid in USDC on Base over x402. No account, no API key, no subscription.
Live API endpoint: api.mydev-tools.tech
Habit trackers record. They rarely explain. The interesting question is not whether you ran on Tuesday, it is which conditions make you run at all — and what to change when a streak is about to break.
Habitcore is the analysis layer, built once and exposed twice. People reach it through an app. Agents reach it through paid HTTP. Because both consume the same engine, an improvement to the intelligence lands for both at the same time, and there is no second implementation drifting away from the first.
Log habits with optional mood, energy and context. Get trends, streak intelligence, consistency scoring and multi-week plans. Raw notes stay in the database — only derived statistics ever cross an AI boundary.
The same analysis as stateless, pay-per-call endpoints. An agent discovers the capability, pays for exactly what it needs, and gets structured JSON back. No onboarding, no contract, no minimum.
Published in a machine-readable manifest so an orchestrator can match on the capability it needs rather than on a product name.
behavioral_analysisAggregate patterns, momentum and risk across a set of habitshabit_analysisPer-habit completion, streaks and consistencybehavioral_insightsCondensed highlights and watchoutshabit_recommendationRanked next-best actions with rationale and priorityhabit_planningStructured multi-week plan with weekly targets and milestones| Endpoint | Per call |
|---|---|
POST /agent/v1/habits/analyzeAggregate behavioural analysis, up to 25 habits per call | $0.05 |
POST /agent/v1/habits/planStructured multi-week habit plan | $0.10 |
POST /agent/v1/habits/insightsCondensed highlights and watchouts | $0.05 |
POST /agent/v1/habits/recommendRanked next-best actions | $0.03 |
Price is per request, not per habit — sending 25 habits in one analyze call costs the same as sending one, so batching is the cheapest way to use this.
Volume rebate. Verified spend earns credits back: 5% from $10 lifetime, 10% from $100, 15% from $1,000, with higher rate limits at each tier. Credits arrive inline in the response that earns them. Full terms →
Call the endpoint. It answers 402 with the payment terms in the
PAYMENT-REQUIRED header. Sign them with your wallet and retry the
identical request with the payload in X-PAYMENT.
# 1. ask — returns 402 with the terms curl -X POST https://api.mydev-tools.tech/agent/v1/habits/analyze \ -H 'Content-Type: application/json' \ -d '{"habits":[{"name":"Morning run","completion_rate":0.72, "current_streak":9,"best_streak":21}]}' # 2. sign the challenge, retry with X-PAYMENT — returns 200 and the analysis
Most x402 client libraries do both steps for you. The challenge also carries a machine-readable input and output schema, so an agent can construct a valid call without reading any documentation.
statelessAgent endpoints operate only on the payload supplied. They accept no identifier of any stored user and can return no stored user's data.minimisedOnly derived statistics reach a language model. Raw notes and journal text never leave the database.deletableAccount deletion removes derived behavioural data too. Security and billing records are kept but stripped of anything identifying.retained brieflyRequest and response bodies are discarded after seven days; only aggregate usage is kept.USDC on Base x402 v2 exact scheme OpenAPI 3.1
/healthService status/openapi.jsonMachine-readable contract/v1/capabilitiesCapability manifest with schemas and prices/llms.txtPlain-text summary for LLM crawlers