Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

persisent-mind

bởi vedantsingh60

Search & Research
350Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

**Persistent, searchable, context-aware memory for AI agents.

Mô tả

Kỹ năng này làm gì

PersistentMind is a Python library that stores typed, searchable memories for AI agents across sessions. It supports seven memory types (fact, preference, procedure, correction, context, relationship, reminder) and three scopes (global, project, session). Data is stored locally with no external dependencies or API keys.

Unlike static prompt files or manual re-explanation, it ranks memories by importance and type, surfacing critical corrections first in every injected context block.

Khi nào nên dùng

  • Persisting code style corrections so agents stop repeating the same mistakes
  • Storing project-specific commands like migration or deployment steps
  • Injecting accumulated project context into new chat sessions automatically
  • Building a shared team knowledge base via JSON export and import
  • Setting temporary notes that auto-expire after a specified number of days

Quy trình ví dụ

ĐẦU VÀO

User asks: Remember that we never use wildcard imports and that migrations run with 'poetry run alembic upgrade head'

AGENT
  1. 1

    Call remember() with the wildcard import rule as MemoryType.CORRECTION, scope PROJECT, importance 10.0

  2. 2

    Call remember() with the migration command as MemoryType.PROCEDURE, scope PROJECT

  3. 3

    In the next session, call get_context(project='my-app') to retrieve stored memories

  4. 4

    Prepend the formatted context block to the incoming user prompt

ĐẦU RA

Context block with the correction surfaced first, followed by the procedure, automatically prepended to every subsequent prompt

Cài đặt

clawhub install vedantsingh60/persisent-mind

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết