Към всички skills

memori

MemoriLabs · Разработка

Ambient Memori long-term memory for Claude Code via local Bash. MUST TRIGGER on essentially every non-trivial user turn: run recall before drafting any substantive response, whether or not the user mentioned memory, a prior session, or past work. The default is to check memory first; do not wait to

Оригинален текст · няма потвърден превод на български

Теми: agent · agent-memory · agenticai · ai · ai-memory · claude-code · enterprise · hermes · llm · long-short-term-memory · memory · memory-management · openclaw · python · rag

Първо прочетете инструкцията.

Файлът се зарежда от посочения източник само по ваше действие. Можете да го прочетете тук, да го копирате или да го запазите като .md.

Оригинален SKILL.md
GitHub хранилище
Звезди на репото
16 908
Лиценз
NOASSERTION
Последна проверка на записа
20.09.2026 г.

Добавете в своя инструмент.

Командата отваря избора на skills от репозитория. Прочетете файла и условията на автора преди изпълнение.

npx skills add MemoriLabs/Memori

Страницата копира текст. Не инсталира и не изпълнява нищо на устройството ви.

Откъс от SKILL.md

Началото на файла на автора, без превод.

Memori Claude Code Skill

Thin CLI wrapper around Memori Cloud for Claude Code subprocesses. Memori is an ambient memory enhancement, not an explicit destination tool. Do not wait for the user to ask to "use Memori" before applying the memory lifecycle below. Claude Code's primary job remains answering the user, editing code, debugging, reviewing, and completing the requested work.

Run commands from the Claude Code integration root:

bun .claude/skills/memori/index.ts <command> [--flags ...]

Flags accept --flag value or --flag=value.

Setup

Configure credentials in .claude/settings.local.json (per-project, not checked into source control). Claude Code injects everything under env into every Bash subprocess, including this skill:

{
  "env": {
    "MEMORI_API_KEY": "your_memori_api_key",
    "MEMORI_ENTITY_ID": "stable_identifier_for_this_user"
  }
}

Required:

  • MEMORI_API_KEY — Memori Cloud API key.
  • MEMORI_ENTITY_ID — any stable string that namespaces memory for this user/agent. If it is missing on the first command, pick a sensible default yourself (the machine hostname, or a generated UUID), write it to .claude/settings.local.json so it persists, and continue. If no sensible default can be inferred, ask the user.

Auto-resolved (no setup required, override with flags or env if needed):

  • MEMORI_PROJECT_ID — defaults to basename($CLAUDE_PROJECT_DIR), the Claude Code workspace folder name. Override per call with --projectId, or pin it by adding MEMORI_PROJECT_ID to the env block.
  • MEMORI_SESSION_ID — defaults to $CLAUDE_CODE_SESSION_ID for writes (advanced-augmentation) and for compaction (which by definition restores the current session). Reads (recall, recall.summary) do not auto-apply session_id — it is a narrowing filter on the agent recall API, so the default keeps retrieval project-scoped across new Claude Code sessions and /clear. Pass --sessionId explicitly when you want a single-session recall.

Optional:

  • MEMORI_PROCESS_ID — process attribution for advanced-augmentation.

A colocated .env file next to index.ts is loaded as a fallback when settings.local.json is not used.

Commands

Целият SKILL.md в GitHub