predict
/predict
Prognozuje, co użytkownik lub konto zrobi dalej, na podstawie wzorców zachowań, z pewnością, która maleje z czasem, i podaniem pochodzenia wniosków.
- Autor
- thinkfleetai ↗
- Repozytorium
- memmesh ↗
- Licencja
- Apache-2.0
- Ostatnia zmiana repozytorium
- 25.08.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 25.08.2026, bez odwołań do wycofanych modeli i API.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
Co robi i kiedy
Prognozuje, co użytkownik lub konto zrobi dalej, na podstawie wzorców zachowań, z pewnością, która maleje z czasem, i podaniem pochodzenia wniosków.
Wyzwalacze z opisu
Oryginalny opis (EN)
Forecast what a subject will do next from their mined behavior patterns — with a calibrated, horizon-decayed confidence and provenance. Use when the user asks "what is this user/account likely to do next", "will X churn/convert/ reorder", or wants a forward prediction rather than a recall of known facts. This is a MemMesh capability a plain memory layer does not have.
Jak działa
- Forward behavior prediction (local MCP)
- Read the result honestly
- Predict ANY target (hosted / SDK)
- Prereq
Podgląd SKILL.md
---
name: predict
description: >
Forecast what a subject will do next from their mined behavior patterns — with
a calibrated, horizon-decayed confidence and provenance. Use when the user
asks "what is this user/account likely to do next", "will X churn/convert/
reorder", or wants a forward prediction rather than a recall of known facts.
This is a MemMesh capability a plain memory layer does not have.
---
# predict
> **⚙️ Requires MemMesh hosted mode.** Calibrated prediction and behavior discovery run on the hosted engine — set your `mm-` API key. On a local / open-source install these tools (`memory_predict`, `memory_build_context`) are not registered; if a call returns "unknown tool", tell the user this is a hosted capability and fall back to `search` / `recall` for what's already known.
Turn accumulated memory into a forward forecast. Unlike `search` ("what do we
know"), `predict` answers "what happens next" — and it tells you how confident it
honestly is, or abstains.
## Forward behavior prediction (local MCP)
```jsonc
{ "name": "memory_predict",
"arguments": { "subjectKind": "user", "subjectId": "<id>",
"horizonDays": 30, "minConfidence": 0.5, "limit": 20 } }
```
Returns ranked predictions, each with a confidence decayed over the horizon and
the provenance behind it. Confidence is **calibrated** — 0.8 means it's right
~80% of the time — not a raw model logit.
## Read the result honestly
- Present the top predictions with their confidence and horizon.
- If a prediction **abstains** (not enough evidence), say so plainly — "not
enough signal yet" is a valid, correct answer, and the point of MemMesh.
- Cite the evidence ids so the user can trace *why*. Use the `why` skill to dig
into calibration/provenance.
## Predict ANY target (hosted / SDK)
The declarative "predict anything" surface (`lattice.predictTarget` with
`target.kind ∈ event_occurrence | numeric | event_time | anomaly`) lets you add
a new prediction with **no code change** — just name the target. It runs on the
hosted gRPC/SDK path:
```ts
await memory.lattice.predictTarget({
subject: { kind: "account", externalId: "acme" },
target: { kind: "event_occurrence", name: "churn" },
});
```
## Prereq
Predictions come from mined `behavior_pattern` memories. If `memory_predict`
returns nothing, the subject may not have enough observed history yet — feed more
via `observe`, or check what patterns exist with the `behaviors` skill.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · thinkfleetai/memmesh | 100 | Apache-2.0 |
| synaptiai/agent-capability-standard | 100 | Apache-2.0 |
| kakarot-dev/deepmiro | 100 | AGPL-3.0 |
Migawka bazy z 13.11.2026 · wersja paczki 0965c33e5404 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100memmesh-sdk
Opisuje SDK TypeScript MemMesh (@thinkfleet/memory-sdk) dla platformy hostowanej: klient ThinkFleetMemory, observe, search, list, predykcje, uczenie w pętli zamkniętej i pakiety branżowe zdrowia i finansów. - 95why
Wyjaśnia przewidywanie modelu MemMesh: źródła wspomnień, kalibrowaną pewność i powód ewentualnego wstrzymania się. - 95bug-predict
Wskazuje miejsca w kodzie najbardziej podatne na błędy na podstawie wzorców i złożoności.