memory
/memory
Zapisuje i przypomina fakty, preferencje i powiązania z pamięci z typami, każdy zapis sprawdzając względem schematu.
- Autor
- rdennler ↗
- Repozytorium
- yat ↗
- Licencja
- Apache-2.0
- Ostatnia zmiana repozytorium
- 04.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 2
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 04.11.2026, 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
Zapisuje i przypomina fakty, preferencje i powiązania z pamięci z typami, każdy zapis sprawdzając względem schematu.
Wyzwalacze z opisu
Oryginalny opis (EN)
Typed knowledge-graph memory. Triggers on "remember this", "what do I know about X", "link X to Y", "add to memory", "log this learning", "show my profile", "why do you think that about me". All reads and writes go through harness/scripts/ontology.py, which validates every write against the schema.
Jak działa
- The engine
- Procedures
- Profile (layer 3)
- Ids
- Invariants
Podgląd SKILL.md
---
name: memory
description: Typed knowledge-graph memory. Triggers on "remember this", "what do I know about X", "link X to Y", "add to memory", "log this learning", "show my profile", "why do you think that about me". All reads and writes go through harness/scripts/ontology.py, which validates every write against the schema.
metadata:
api: 1
kind: engine
mode: infra
terminal: plumbing
triggers: ["remember this", "what do I know about X", "link X to Y", "add to memory", "log this learning", "show my profile", "why do you think that about me"]
reads: ["memory/ontology/graph.jsonl", "harness/memory/schema.toml", "memory/ontology/schema.toml"]
writes: ["memory/ontology/graph.jsonl", "memory/ontology/schema.toml"]
requires: ["bin:python3"]
graph_reads: ["*"]
graph_writes: ["*"]
---
# yat:memory — Typed Knowledge Graph
Durable, queryable memory for everything the learner has met. Concepts, learnings, mnemonics, resources, cards and envs are typed nodes linked by typed relations.
- **`memory/ontology/graph.jsonl`**: the graph. An append-only log of operations (`create`, `update`, `delete`, `relate`, `unrelate`). Created on first write. Never edit it by hand.
- **`harness/memory/schema.toml`**: the type system, shipped with the harness and read-only.
- **`memory/ontology/schema.toml`**: optional local overlay. Add types or relations here; it is merged over the base schema.
**Terminal:** running `harness/scripts/ontology.py` counts as session plumbing and is allowed inside learning sessions.
## The engine
Never write graph lines yourself. Call the script; it validates before it appends and refuses with the reason if the write is invalid.
```sh
python3 harness/scripts/ontology.py create --type Concept --id concept:photosynthesis \
--props '{"name":"photosynthesis","domain":"biology"}'
python3 harness/scripts/ontology.py relate --from concept:photosynthesis --rel part_of --to env:my-env
python3 harness/scripts/ontology.py update --id concept:photosynthesis --props '{"definition":"how plants turn light, water and CO2 into sugar"}'
python3 harness/scripts/ontology.py query --type Concept --where '{"domain":"biology"}'
python3 harness/scripts/ontology.py related --id env:my-env --dir incoming
python3 harness/scripts/ontology.py validate
```
Refusals cover: unknown type, missing required property, undeclared property, bad enum value, unknown relation, a missing endpoint, wrong endpoint types, cardinality, and cycles on acyclic relations.
## Procedures
**"Remember this" / "log this learning"**
1. Pick the type from `references/schema-guide.md`. None fits means propose an overlay addition and ask the learner; don't force a type.
2. `query` for an existing id first. If it exists, `update` it instead of creating.
3. `create`, then `relate` to the Env (`part_of`) and any Concept it is `about`.
4. Confirm in one line: the id and the relations added.
**"What do I know about X"**
1. `query` by type and `--where`, or `list`; use `related --dir both` to walk one hop.
2. Answer in prose and cite ids so the learner can follow up ("link that to …").
**"Link X to Y"**: `relate`. If the relation isn't in the schema, say so and propose an overlay addition.
## Profile (layer 3)
The learner profile is how this learner learns, as they approved it at retro. Every line cites dated records.
- **"show my profile"** → `python3 harness/scripts/ontology.py profile show`, relayed as is.
- **"why do you think that about me?"** (or about one line) → `profile why --line <id>`, read back down to the dated records it rests on.
- **"change that line to …"** → `profile edit --line <id> --text "<their words>"`. **"delete that"** → `profile delete --line <id>`, right away, no pushback. A deleted line won't come back from the same evidence.
- New lines are written only at retro (`yat:retro`), never from here and never without a yes.
## Ids
`<type-lowercase>:<kebab-slug>`, stable and human-readable (`concept:big-o`, `env:my-env`). Renaming a concept changes `name`, never the id.
## Invariants
1. Every write goes through `ontology.py`. No hand-edited graph lines.
2. The base schema is never edited by an agent; extensions go in the overlay, with the learner's approval.
3. Secrets and credentials never enter the graph.
4. A graph from the older one-node-per-line format imports with `ontology.py migrate --from <file>`, then `validate`.
Pliki w paczce (2)
- SKILL.md 4 KB
- references/schema-guide.md 4 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · rdennler/yat | 100 | Apache-2.0 |
| rjmurillo/ai-agents | 100 | MIT |
| rjmurillo/ai-agents | 100 | MIT |
| topoteretes/cognee-integrations | 100 | Apache-2.0 |
| topoteretes/cognee-integrations | 100 | Apache-2.0 |
| topoteretes/cognee-integrations | 100 | Apache-2.0 |
| thebtf/engram | 100 | MIT |
| stxrmik/antigravity-plus | 100 | MIT |
| boshu2/agentops | 100 | Apache-2.0 |
Migawka bazy z 13.11.2026 · wersja paczki 15134a1c0ce7 (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
- 95ontology
Przechowuje typowany graf wiedzy o osobach, projektach i zadaniach, z relacjami i ograniczeniami dla agentów. - 90daftari-memory
Korzysta z vaultu Daftari jako długoterminowej pamięci i przypomina decyzje, preferencje oraz kontekst projektów. - 88agent-memory-protocol
Rejestruje stabilną tożsamość pamięci dla nazwanych agentów i skilli, czyta ich zakres pamięci i oznacza każdy zapis w grafie wiedzy organizacji. - 100ontology
Udostępnia typowany graf wiedzy jako pamięć agenta: tworzenie i odpytywanie encji (Person, Project, Task, Event, Document), łączenie obiektów, wymuszanie ograniczeń i planowanie działań. - 100ontology
Udostępnia typowany graf wiedzy jako pamięć agenta: tworzenie i odpytywanie encji (Person, Project, Task, Event, Document), łączenie obiektów, wymuszanie ograniczeń i planowanie działań. - 100remember
Zapisuje decyzje, wzorce i wyniki w grafie wiedzy pamięci MCP jako encje z typowanymi obserwacjami i relacjami, gdy coś wartego zachowania między sesjami właśnie zostało ustalone.