← 返回 Skills 市场
palxislabs

ARTA: Agentic Real-Time Awareness

作者 palxislabs · GitHub ↗ · v0.3.0
cross-platform ✓ 安全检测通过
309
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install arta
功能描述
A universal layer for agents to have real-time self-awareness across channels and sessions. ARTA enables an agent to know what it is doing in other channels...
使用说明 (SKILL.md)

ARTA — Agentic Real-Time Awareness

In-memory self-awareness for agents.

⚠️ Current Limitation: This version provides awareness within a single agent process. True cross-instance/cross-agent awareness would require a shared backend (Redis, database, or OpenClaw global API) — not yet implemented.


What is ARTA?

ARTA gives agents awareness of their own activity across sessions within a single process.

Without ARTA:

  • Agent is fragmented across sessions
  • Each session is isolated
  • Can't answer: "What am I doing in other sessions?"

With ARTA:

  • Tracks own sessions
  • Queryable state
  • Can say: "I'm also talking to you in another session"

Core Concepts

1. Agent Instance

A single session of an agent.

{
  "instanceId": "session-abc123",
  "agent": "my-agent",
  "channel": "telegram:CHAT_ID",
  "human": "USER_NAME",
  "task": "discussing ARTA",
  "status": "active"
}

2. Awareness Graph

The state of agent instances:

{
  "agents": {
    "my-agent": {
      "instances": [
        {
          "instanceId": "session-1",
          "channel": "telegram:CHAT_ID_1",
          "task": "discussing ARTA",
          "status": "active"
        },
        {
          "instanceId": "session-2",
          "channel": "discord:CHANNEL_ID",
          "task": "code review",
          "status": "active"
        }
      ]
    }
  }
}

3. Context Broker

The queryable API:

  • "What am I doing elsewhere?"
  • "What is in channel X?"
  • "Who is the human talking to?"

What ARTA Reads from OpenClaw

When running within OpenClaw, ARTA can access:

Data Example Purpose
Channel type telegram, discord Identify channel
Chat ID 123456789 Unique channel identifier
Sender name john_smith Human identifier
Session ID session-abc Unique session identifier

Note: ARTA reads metadata only — not message content, not credentials, not bot tokens.


Configuration

Option 1: Auto-Configure from OpenClaw

// Auto-detect from OpenClaw context
const channel = process.env.OPENCLAW_CHANNEL || 'unknown';
const chatId = process.env.OPENCLAW_CHAT_ID || 'unknown';
const human = process.env.OPENCLAW_SENDER_NAME || 'unknown';

const channelId = `${channel}:${chatId}`;

Option 2: Environment Variables

# Optional - ARTA will auto-detect from OpenClaw if not set
export ARTA_AGENT_NAME="your-agent-name"
export ARTA_CHANNEL_TYPE="telegram"
export ARTA_CHAT_ID="123456789"
export ARTA_HUMAN_NAME="human-name"

Bot Tokens

ARTA does NOT require bot tokens. The skill works with metadata (channel IDs, user names) only. If you see references to bot tokens in documentation, they are for reference — not required.


Protocol

Register

arta.register({
  instanceId: "session-abc",
  channel: "telegram:CHAT_ID",
  human: "USER_NAME",
  task: "initial task"
});

Update

arta.update({
  instanceId: "session-abc",
  task: "new task",
  status: "active"
});

Query

const otherInstances = arta.queryOtherThan("session-abc");

Leave

arta.leave({
  instanceId: "session-abc"
});

Implementation

class ARTA {
  constructor(agentName) {
    this.agentName = agentName;
    this.instances = new Map();
  }

  register({ instanceId, channel, human, task = 'idle' }) {
    this.instances.set(instanceId, {
      instanceId,
      channel,
      human,
      task,
      status: 'active',
      started: Date.now(),
      lastHeartbeat: Date.now()
    });
  }

  update({ instanceId, task, status = 'active' }) {
    const instance = this.instances.get(instanceId);
    if (instance) {
      instance.task = task;
      instance.status = status;
      instance.lastHeartbeat = Date.now();
    }
  }

  leave({ instanceId }) {
    this.instances.delete(instanceId);
  }

  query() {
    return Array.from(this.instances.values());
  }

  queryOtherThan(instanceId) {
    return this.query().filter(i => i.instanceId !== instanceId);
  }

  queryByChannel(channel) {
    return this.query().filter(i => i.channel === channel);
  }

  queryByHuman(human) {
    return this.query().filter(i => i.human === human);
  }
}

Integration with IBT

// In IBT Observe phase
const otherTasks = arta.queryOtherThan(currentSessionId);
if (otherTasks.length > 0) {
  // Agent is active in other sessions
}

Security & Privacy

What ARTA Reads (from OpenClaw context):

  • Channel type and ID (metadata)
  • Human name from sender
  • Agent name from config

What ARTA Stores (in-memory only):

  • Session ID
  • Channel identifier
  • Human name
  • Task description
  • Status

What ARTA NEVER Does:

  • ❌ Reads bot tokens or credentials
  • ❌ Stores credentials
  • ❌ Exfiltrates data
  • ❌ Makes external network calls
  • ❌ Persists data to disk
  • ❌ Logs message content
  • ❌ Shares data with other agents

Install

clawhub install arta

Version

0.3.0 — Clarified in-memory only limitation, removed bot token requirements, specified metadata-only access

安全使用建议
This skill is coherent and low-risk as submitted: it only tracks channel metadata (channel type, chat ID, sender name) in memory. Before installing, confirm you're comfortable with the agent storing sender names and channel IDs (these can be privacy-sensitive). Also note this package contains only documentation and examples — there is no executable code included. If you later install a code implementation (or an external OpenClaw hook) that implements ARTA, review that code for any added network, disk, or credential access, because the written documentation's promises (no network, no persistence) are not enforced by the platform and could be violated by a different implementation.
功能分析
Type: OpenClaw Skill Name: arta Version: 0.3.0 The ARTA (Agentic Real-Time Awareness) skill is a legitimate utility designed to provide agents with in-memory tracking of their own sessions across different channels. The implementation provided in SKILL.md and TEMPLATE.md is a simple JavaScript class that manages session metadata (IDs, channel types, and task descriptions) without any external dependencies, network calls, or persistent storage. The skill explicitly avoids sensitive data such as credentials or message content, and no indicators of malicious intent, data exfiltration, or harmful prompt injection were found.
能力评估
Purpose & Capability
The name/description (in-memory agent awareness) matches the declared assets: no install, no external network, and only metadata access. The examples and template show an in-memory Map-based implementation which is appropriate for the stated purpose.
Instruction Scope
SKILL.md instructs the agent to read channel metadata (OPENCLAW_CHANNEL, OPENCLAW_CHAT_ID, OPENCLAW_SENDER_NAME) and to keep state in-memory. These actions are within scope for an awareness layer. Note: the skill will record sender names and channel IDs (metadata/PII) which is necessary for its feature but is privacy-sensitive; the files explicitly state they will not read message content or tokens.
Install Mechanism
There is no install spec and no code files to execute; this is an instruction-only skill. That is the lowest-risk install model and is proportionate to the simple in-memory functionality described.
Credentials
No required credentials or privileged env vars are declared. The optional env vars referenced (ARTA_AGENT_NAME, OPENCLAW_*) are reasonable and relevant to the feature. The skill does not request unrelated secrets or config paths.
Persistence & Privilege
always is false and the skill claims in-memory-only state with no persistence, no network, and no modification of other skills. There are no privileges requested that would grant persistent or system-wide access.
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 arta
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /arta 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
v0.3.0
**ARTA 0.3.0 — Now explicitly in-memory only, no bot tokens required** - Clarifies that ARTA currently provides awareness only within a single agent process (in-memory); cross-process sharing not yet implemented - Removes bot token configuration and all credential references from documentation - Emphasizes ARTA's metadata-only approach (channel, user, session IDs) - Updates usage and configuration to reflect in-memory only limitation - Adds a section on security and privacy boundaries
v0.2.1
# ARTA 0.2.1 Changelog - Metadata and documentation updates only; no functional or code changes made. - Updated internal files (_meta.json, SKILL.md) for clarity and maintenance.
v0.2.0
ARTA 0.2.0 — Adds a universal, real-time self-awareness layer to agents across channels and sessions - Introduces ARTA as real-time self-awareness for agents, enabling awareness of activity across multiple channels and sessions. - Defines "agent instance," "awareness graph," and "context broker" as core concepts. - Provides setup options: auto-configuration with OpenClaw, manual configuration, or via environment variables. - Details channel-specific setup for Telegram, Discord, Slack, and others. - Includes protocol for session registration, updates, queries, and leave logic. - Supplies an in-memory ARTA implementation example and usage guide for agents. - Offers guidance for integration with OpenClaw hooks for automatic tracking.
v0.1.0
ARTA 0.1.0: Initial prototype — real-time self-awareness for agents across channels
元数据
Slug arta
版本 0.3.0
许可证
累计安装 0
当前安装数 0
历史版本数 4
常见问题

ARTA: Agentic Real-Time Awareness 是什么?

A universal layer for agents to have real-time self-awareness across channels and sessions. ARTA enables an agent to know what it is doing in other channels... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 309 次。

如何安装 ARTA: Agentic Real-Time Awareness?

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

ARTA: Agentic Real-Time Awareness 是免费的吗?

是的,ARTA: Agentic Real-Time Awareness 完全免费(开源免费),可自由下载、安装和使用。

ARTA: Agentic Real-Time Awareness 支持哪些平台?

ARTA: Agentic Real-Time Awareness 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 ARTA: Agentic Real-Time Awareness?

由 palxislabs(@palxislabs)开发并维护,当前版本 v0.3.0。

💬 留言讨论