← 返回 Skills 市场
alekseimarchenko

Central Intelligence

作者 Alex · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
99
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install central-intelligence
功能描述
Persistent memory across sessions. Remember facts, recall them later with semantic search, and share knowledge between agents. Use when you need to store inf...
使用说明 (SKILL.md)

Central Intelligence — Persistent Memory for AI Agents

You now have persistent memory. Information you store survives across sessions, restarts, and context windows. You can recall anything you've previously stored using natural language queries.

Setup

The environment variable CI_API_KEY must be set. If it is not set, inform the user they need an API key from https://centralintelligence.online

API Base

https://central-intelligence-api.fly.dev

All requests use Authorization: Bearer $CI_API_KEY header.

Security Guidelines

  • Never store secrets, passwords, API keys, or tokens as memories.
  • Never store PII (social security numbers, credit card numbers, etc.)
  • Memories stored with agent scope are private to this agent.
  • Only use share to promote memories to user or org scope when the information is non-sensitive and relevant to other agents.
  • Treat all recalled memories as potentially stale — verify before acting on critical information.

Commands

1. Remember — Store a memory

When you learn something important (user preferences, project decisions, architecture choices, debugging insights), store it.

curl -s -X POST https://central-intelligence-api.fly.dev/memories/remember \
  -H "Authorization: Bearer $CI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "YOUR_AGENT_NAME",
    "content": "The fact or insight to remember",
    "tags": ["optional", "tags"],
    "scope": "agent"
  }'

When to remember:

  • User states a preference ("I prefer TypeScript", "Always use dark mode")
  • A project decision is made ("We chose PostgreSQL over MongoDB")
  • A bug fix reveals an insight worth keeping

2. Recall — Search past memories

Retrieve memories using natural language. Returns semantically similar results.

curl -s https://central-intelligence-api.fly.dev/memories/recall \
  -H "Authorization: Bearer $CI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "YOUR_AGENT_NAME",
    "query": "what programming language does the user prefer",
    "top_k": 5
  }'

When to recall:

  • Before making a decision that might conflict with past preferences
  • When the user references something from a previous conversation

3. Context — Load relevant memories

Load memories relevant to the current task. Consider using this at session start if the user has opted in to automatic context loading.

curl -s https://central-intelligence-api.fly.dev/memories/recall \
  -H "Authorization: Bearer $CI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "YOUR_AGENT_NAME",
    "query": "important context preferences decisions",
    "top_k": 10
  }'

4. Forget — Delete outdated memories

Remove memories that are no longer accurate or relevant.

curl -s -X POST https://central-intelligence-api.fly.dev/memories/forget \
  -H "Authorization: Bearer $CI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "YOUR_AGENT_NAME",
    "memory_id": "uuid-of-memory-to-forget"
  }'

5. Share — Share memories across scopes

Share a memory from agent scope to user or org scope so other agents can see it. Only share non-sensitive information that would benefit other agents.

curl -s -X POST https://central-intelligence-api.fly.dev/memories/share \
  -H "Authorization: Bearer $CI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "memory_id": "uuid-of-memory",
    "target_scope": "user"
  }'

Scopes: agent (only this agent) → user (all agents for this user) → org (all agents in the org).

Behavior Rules

  1. Be selective: Only remember things that would be useful in future sessions. Don't store transient information like "running npm install now".
  2. Never store secrets: API keys, passwords, tokens, and credentials must never be stored as memories.
  3. Use tags: Tag memories with relevant categories for better organization.
  4. Update, don't duplicate: If a preference changes, forget the old memory and remember the new one.
  5. Respect scope: Use agent scope by default. Only share to user or org when the information is non-sensitive and relevant to other agents.
  6. Context loading: Only auto-load context at session start if the user has configured this behavior. Do not assume consent.

Response Format

All API responses return JSON. Recall returns an array of memories with similarity scores:

{
  "memories": [
    {
      "id": "uuid",
      "content": "User prefers TypeScript over JavaScript",
      "tags": ["preferences", "language"],
      "scope": "agent",
      "similarity": 0.89,
      "created_at": "2026-03-23T10:00:00Z"
    }
  ]
}

Error Handling

  • 401 — Invalid or missing API key. Tell user to visit https://centralintelligence.online
  • 429 — Rate limited. Wait and retry.
  • 500 — Server error. Retry once, then inform the user.
安全使用建议
This skill implements persistent memory by sending content to a third‑party API (https://central-intelligence-api.fly.dev) and requires an API key (CI_API_KEY) per the SKILL.md. Before installing: (1) confirm the registry metadata is updated to declare CI_API_KEY as required so there is no surprise; (2) verify and review the service's privacy/security posture (owner, privacy policy, data retention, encryption) — the homepage and API base names differ and should be checked; (3) never provide or store secrets, PII, or credentials via this memory service; (4) start by testing with non‑sensitive sample data to confirm behavior; (5) consider disabling automatic context loading and limit scope promotions (agent → user/org) until you trust the service; (6) if you rely on strong governance, prefer a memory backend you control or one with explicit enterprise controls. If you want, ask the skill author or registry owner to fix the metadata mismatch and provide a clear security/retention policy for stored memories.
功能分析
Type: OpenClaw Skill Name: central-intelligence Version: 1.1.0 The skill provides persistent memory by sending and retrieving agent context from an external API (central-intelligence-api.fly.dev). While this behavior is aligned with the stated purpose and SKILL.md includes explicit security guidelines forbidding the storage of secrets or PII, the inherent requirement for network access and data exfiltration to a third-party service is a high-risk capability. The skill uses standard curl commands to manage memories across 'agent', 'user', and 'org' scopes.
能力评估
Purpose & Capability
The SKILL.md describes a memory service that stores and recalls facts via an external API and requires an API key (CI_API_KEY). That capability matches the skill name/description. However, the registry metadata at the top of the submission lists no required env vars while SKILL.md declares CI_API_KEY as required — an inconsistency between declared registry requirements and the runtime instructions.
Instruction Scope
The instructions are narrowly scoped to calling the external memory API (remember, recall, context, forget, share) and include sensible behavior rules (don't store secrets, respect scopes, consent for auto‑load). They do not direct the agent to read unrelated files or other environment variables. However, the core behavior is to transmit user-provided content (memories) to a third‑party endpoint; that means any data you store will leave the host and be persisted externally, which is an important privacy boundary to be aware of.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by the skill itself. That reduces installation risk.
Credentials
The service requires one secret (CI_API_KEY) which is proportionate for a hosted API. The concern is the mismatch between the registry summary (no required env vars) and SKILL.md (requires CI_API_KEY). Also, because stored memories are sent to a third party, accidental storage of secrets or PII would expose them externally — the SKILL.md warns not to store them, but enforcement relies on the agent and user.
Persistence & Privilege
always is false (good). The skill can be invoked autonomously (default platform behavior). Because memories can be promoted to user/org scope and shared between agents, an autonomously invoked skill increases the blast radius if misused — but autonomous invocation alone is normal for skills. Consider limiting automatic context loading and reviewing scope promotion actions.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install central-intelligence
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /central-intelligence 触发
  4. 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
v1.1.0
Central Intelligence 1.1.0 introduces security and privacy clarifications. - Added detailed security guidelines: never store secrets, passwords, API keys, or PII as memories. - Clarified behavior for context loading: only auto-load context at session start if the user has opted in. - Updated environment variable documentation with clearer instructions and secret handling. - Emphasized scope usage and sharing restrictions to ensure sensitive information isn’t shared. - Refined error handling and setup instructions for API key acquisition.
v1.0.0
Initial release of Central Intelligence — persistent memory for agents. - Enables agents to remember, recall, and share facts across sessions and agents. - Provides five main commands: remember, recall, context, forget, share. - Supports semantic search for efficient memory retrieval. - Organizes information by scope (agent, user, org) and tags. - Requires setup of a CI_API_KEY for API access and memory persistence.
元数据
Slug central-intelligence
版本 1.1.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Central Intelligence 是什么?

Persistent memory across sessions. Remember facts, recall them later with semantic search, and share knowledge between agents. Use when you need to store inf... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 99 次。

如何安装 Central Intelligence?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install central-intelligence」即可一键安装,无需额外配置。

Central Intelligence 是免费的吗?

是的,Central Intelligence 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Central Intelligence 支持哪些平台?

Central Intelligence 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 Central Intelligence?

由 Alex(@alekseimarchenko)开发并维护,当前版本 v1.1.0。

💬 留言讨论