メニュー
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.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/Tyler-R-Kendrick/agentic_speculative_knowledge --skill recallコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
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.
SKILL.md を表示中
SOC 職業分類に基づく
| name | recall |
| description | 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. |
Retrieve past knowledge from the memory layers.
import pathlib
from datetime import date
from src.api.memory_manager import MemoryManager
from src.retrieval.composer import RetrievalComposer
from src.journal.appender import JournalAppender
root = pathlib.Path(".agent-memory")
# High-level retrieval via MemoryManager
mgr = MemoryManager(root_dir=root)
context = mgr.retrieve_context(include_terminus=False)
# context keys: session, working_items, entities, tasks, claims,
# terminus_memories, speculative_inference, facet_relations
# Include trusted Terminus memories and speculative inference
full = mgr.retrieve_context(
include_terminus=True,
include_speculative=True,
inference_branch="inference/sess-1",
)
# Journal history for today
appender = JournalAppender(root)
events = appender.read_day(date.today())
for event in events:
print(event.mutation_kind, event.changed_files)
from src.retrieval.composer import RetrievalComposer
from src.terminus.adapter import TerminusMemoryRepository
repo = TerminusMemoryRepository(url="http://localhost:6363")
composer = RetrievalComposer(root, terminus_repo=repo)
trusted = composer.retrieve(include_terminus=True)
exploratory = composer.retrieve(
include_terminus=True,
include_speculative=True,
inference_branch="inference/sess-1",
)
| Class | Method | Purpose |
|---|---|---|
MemoryManager | retrieve_context() | High-level composed retrieval with opt-in layers |
RetrievalComposer | retrieve() | Low-level retrieval combining active, Terminus, and speculative sources |
JournalAppender | read_day() | Read mutation events for a specific date |
ActiveRetriever | get_session() / get_working_set() / get_entities() / get_tasks() / get_claims() | Individual active-memory readers |
src/retrieval/composer.py — composed retrieval from multiple layerssrc/retrieval/active_retriever.py — filesystem active-memory readersrc/retrieval/terminus_retriever.py — Terminus trusted/speculative readersrc/journal/appender.py — journal day-file readertests/integration/test_retrieval.py — integration coveragenotebooks/03_historical_recall.ipynb — executable walkthroughRetrievalComposer from src/retrieval/composer.py to merge context layers rather than hand-merging sources.JournalAppender in src/journal/appender.py as the source for mutation history.include_speculative=True.tests/integration/test_retrieval.py.