← 返回 Skills 市场
140
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install memory-oracle
功能描述
Persistent structured memory system for OpenClaw agents with SQLite storage, hybrid search (FTS5 + decay scoring), rule-based capture, LLM-powered daily refl...
安全使用建议
This skill appears to implement what it claims: a local SQLite-backed memory system with rule-based capture and optional LLM-powered nightly reflection. Before installing, consider:
- Sensitive data exposure: The LIGHT path (capture/recall) runs locally and stores conversation content in a SQLite DB and daily logs. If you store sensitive PII, API keys, or secrets in conversation or session files, those will be recorded. Decide whether you want those saved and adjust settings (paths, delete/retention thresholds) accordingly.
- External LLM use is explicit: The HEAVY pipeline (consolidate/reflect) will send daily logs / memory content to Anthropic/Claude if you set ANTHROPIC_API_KEY. If you do not want any data sent to an external LLM, do not set the key and/or skip cron setup (the LIGHT features still work).
- Cron and secrets: The installer can add a nightly cron job. If you put an API key directly into a crontab entry or otherwise make it visible in system config, that can expose the key to other local users/processes—prefer storing the key in a secure file or environment management mechanism and double-check what gets written into your crontab.
- Backups & cleanup: The installer/backups appear to be conservative (it creates a pre-oracle MEMORY.md backup and the uninstaller exports state). Review the printed AGENTS.md and compaction snippets before pasting them into your agent config.
- Code quality notes: Some helper functions in the sample (e.g., utcnow()) and truncated examples in the provided evaluation snippet look buggy or incomplete; that is not evidence of malicious intent but you should run tests (tests/*) and review scripts in a safe environment before enabling cron/HEAVY tasks on a production agent.
If you are comfortable with local persistence of conversation history and optionally sending condensed daily summaries to Anthropic, this skill is coherent with its stated purpose. If you want to avoid any remote transmission, skip providing ANTHROPIC_API_KEY and skip cron installation (run HEAVY tasks manually if needed).
能力评估
Purpose & Capability
Name/description (persistent structured memory with SQLite, FTS5, capture/recall, nightly reflection) match the included scripts (capture.py, recall.py, init_db.py, consolidate.py, reflect.py, maintenance.py) and config. Optional ANTHROPIC_API_KEY for HEAVY (LLM) work is consistent with the stated nightly consolidation/reflect steps.
Instruction Scope
SKILL.md and the agent protocol instruct the agent to run recall before replies and capture after replies, and to checkpoint SESSION-STATE.md on compaction — this legitimately requires reading/writing local files (MEMORY.md, SESSION-STATE.md, daily logs) and the SQLite DB. That behavior aligns with the purpose but means the skill will ingest and persist potentially sensitive conversation contents locally; the HEAVY pipeline also sends selected daily logs to Anthropic when the API key is provided (explicitly documented).
Install Mechanism
There is no opaque remote installer: the repo contains install.sh/uninstall.sh and pure-Python scripts. install.sh initializes the DB, imports existing MEMORY.md, and optionally writes a nightly cron job. No downloads from untrusted URLs or archive extraction are present in the provided files. Installation modifies user crontab and filesystem under the user's workspace (expected for this functionality).
Credentials
Only one optional credential is referenced: ANTHROPIC_API_KEY for the HEAVY pipeline which uses an external LLM (Claude). That is proportionate to the declared functionality. There are no other unrelated secret env vars requested. Be aware that using the HEAVY pipeline means some memory text will be sent to an external LLM service (user-controlled by providing the key).
Persistence & Privilege
always:false, user-invocable:true, and model invocation is permitted (normal). The installer optionally writes a nightly cron job under the user's crontab (user-level persistence only). The skill does not request system-wide privileges or modify other skills' configs automatically; it prints snippets for manual AGENTS.md / compaction edits.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install memory-oracle - 安装完成后,直接呼叫该 Skill 的名称或使用
/memory-oracle触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.2
- Added uninstall.sh script for safe rollback and memory export.
- SKILL.md updated with detailed uninstall and rollback instructions, outlining step-by-step uninstallation process.
- No changes to existing functionality or dependencies.
v1.0.1
memory-oracle 1.0.1
- Added explicit documentation for compatibility (Python ≥3.8, FTS5 support) and required environment variables (ANTHROPIC_API_KEY only needed for HEAVY process).
- Installation steps now clarify that installer does not auto-edit any config files; users must manually review and paste provided snippets.
- Expanded privacy section: stated exactly which data is sent externally, when, and how to opt-out for local/LLM-free setups.
- Clarified that LIGHT process (rule-based capture/recall) is fully local and works with zero network/API calls.
- Other minor editorial improvements throughout SKILL.md for clarity and transparency.
v1.0.0
Initial release of memory-oracle: a persistent, structured memory system for OpenClaw agents.
- Replaces markdown-only memory with a hybrid SQLite-backed, three-tier (hot/warm/cold) system
- Automatic rule-based fact extraction, LLM-powered daily reflection, and weekly trend analysis
- Hybrid search using FTS5 with decay-based scoring for contextual recall before responses
- Emergency checkpointing, safe compaction, and self-maintaining memory with no external dependencies
- Simple installation with migration, agent protocol, and configurable retention/recall policies
元数据
常见问题
Memory Oracle 是什么?
Persistent structured memory system for OpenClaw agents with SQLite storage, hybrid search (FTS5 + decay scoring), rule-based capture, LLM-powered daily refl... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 140 次。
如何安装 Memory Oracle?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install memory-oracle」即可一键安装,无需额外配置。
Memory Oracle 是免费的吗?
是的,Memory Oracle 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Memory Oracle 支持哪些平台?
Memory Oracle 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Memory Oracle?
由 Oleg(@oleglegegg)开发并维护,当前版本 v1.0.2。
推荐 Skills