메뉴
Use the memorize skill to store observations, entities, tasks, and claims into the filesystem-backed active memory. Covers session lifecycle, working-set writes, entity/task card creation, claim extraction, and candidate promotion.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | memorize |
| description | Use the memorize skill to store observations, entities, tasks, and claims into the filesystem-backed active memory. Covers session lifecycle, working-set writes, entity/task card creation, claim extraction, and candidate promotion. |
Store new knowledge into the agent's active memory layer.
import pathlib
from src.api.memory_manager import MemoryManager
mgr = MemoryManager(root_dir=pathlib.Path(".agent-memory"))
# 1. Start a session
session = mgr.start_session(current_goal="investigate auth failures")
# 2. Record a working item
item = mgr.add_working_item(
item_type="observation",
content="The auth service returned 401 after cert rotation.",
)
# 3. Register an entity
entity = mgr.add_entity(
name="auth-service",
entity_type="service",
description="Handles authentication and token issuance.",
)
# 4. Register a task
task = mgr.add_task(title="Check certificate expiry dates", priority=1)
# 5. Extract claims from text
claims = mgr.extract_claims(
text="The auth service failed after a certificate rotation.",
source_ref="incident-report-42",
)
# 6. Promote eligible memories
results = mgr.promote_memories()
# 7. Close the session
mgr.end_session()
| Class | Method | Purpose |
|---|---|---|
MemoryManager | start_session() | Open a new working session with an optional goal |
MemoryManager | end_session() | Close the active session |
MemoryManager | add_working_item() | Append an observation, note, or decision to the working set |
MemoryManager | add_entity() | Write an entity card to active memory |
MemoryManager | add_task() | Write a task card to active memory |
MemoryManager | extract_claims() | Extract and persist structured claims from text |
MemoryManager | promote_memories() | Run governance rules and promote eligible candidates |
SessionManager | create_session() / close_session() | Low-level session lifecycle |
src/api/memory_manager.py — high-level orchestration APIsrc/active_memory/session_manager.py — session create / close / loadsrc/active_memory/working_set.py — JSONL working-set appendersrc/active_memory/entity_card.py — entity card writersrc/active_memory/task_card.py — task card writersrc/claims/extractor.py — claim extraction from textsrc/governance/promotion.py — promotion eligibility enginetests/unit/test_active_memory.py — unit coveragenotebooks/01_active_memory_basics.ipynb — executable walkthroughMemoryManager from src/api/memory_manager.py as the entry point; do not bypass it with low-level appenders unless extending the API itself.active/, journal/, claims/ directories under the memory root.ClaimExtractor pipeline rather than duplicating extraction logic.tests/unit/test_active_memory.py.Use the speculate skill when you need critique-ready hypotheses from new observations: recall context, run the mutation pipeline on a fresh observation, retrieve ranked inference and facet results from an inference/* branch, and present candidate text, provenance, assumptions, uncertainty, and review priority without promoting anything to trusted memory.
Use the discover skill to find connections between claims through facet relations and to rank inference and facet candidates using manifold geometry. Covers facet modeling, manifold scoring, relatedness, distance, uncertainty, and retrieval of discovery results.
Use the infer skill to generate speculative inference candidates from claims, persist them on branch-local inference graphs, and run the full mutation pipeline that coordinates active memory, claims, Terminus persistence, and speculative ranking.
Use the recall skill to retrieve composed context from active memory, trusted Terminus graphs, and optional speculative branches. Also covers journal-backed history of past working-memory mutations.
Use the reflect skill to persist memories, claims, and inference nodes into the TerminusDB temporal graph. Covers branch lifecycle, trusted session writes, temporal recall, and the separation between session and inference branches.