What makes Network-AI notable?

7.1K downloads. Trust evidence available

How should Network-AI be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

agentCLAWHUBUnverified

Network-AI

Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context. The bundled Python scripts make no network calls and have zero third-party dependencies. The parent repository also contains a TypeScript engine (not included in this skill bundle). Skill: Network-AI Owner: jovancoding Summary: Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context. The bundled Python scripts make no network calls and have zero third-party dependencies. The parent repository also contains a TypeScript engine (not included in this skill bundle). Tags: audit:4.0.4, autogen:4.0.4, b

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

7.1k

Updated

Oct 9, 2026

Version

5.15.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 7.1K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 7.1K downloadsadoption · observed Oct 9, 2026
Latest release: 5.15.4release · observed Sep 29, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s171ekwxgx1x85ga807c8zc0ws840q1k:network-ai

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-jovancoding-network-ai/snapshot"

Documentation

CLAWHUB

158,756 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: network-ai
description: "Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context. The bundled Python scripts make no network calls and have zero third-party dependencies. The parent repository also contains a TypeScript engine (not included in this skill bundle)."
allowed-tools: Read Bash(python3 scripts/blackboard.py:*) Bash(python3 scripts/check_permission.py:*) Bash(python3 scripts/context_manager.py:*) Bash(python3 scripts/swarm_guard.py:*) Bash(python3 scripts/validate_token.py:*) Bash(python3 scripts/revoke_token.py:*)
metadata:
  openclaw:
    emoji: "\U0001F41D"
    homepage: https://network-ai.org
    capabilities:
      filesystem: "read/write — project root `swarm-blackboard.md` (blackboard state), `data/pending_changes/<id>.json` (WAL entries), `data/audit_log.jsonl`, `data/active_grants.json`, `data/.signing_key`, `data/project-context.json`, `data/task_tracking.json`, `data/agent_health.json`, `data/budget_tracking.json`, `data/swarm_budgets.json`, `data/heartbeats.json`, `data/.blackboard.lock`. All paths are local; no data leaves the local filesystem. When NETWORK_AI_ENV is set, data paths are rooted at `data/<env>/` instead of `data/`. The `--path` argument in blackboard.py is validated against the project root at runtime — paths outside the project directory are rejected (CWE-22)."
      env_vars: "read — NETWORK_AI_ENV only (environment routing for data paths). No other env vars are read and none are written."
      tools: "Only the six bundled scripts, run via python3 (see allowed-tools), plus reading local state files. No other commands, binaries, or tools are required or invoked."
      shell_exec: "none — the bundled scripts spawn no subprocesses and execute no shell commands."
      tcp_port: "none — the bundled scripts open no sockets and bind no ports."
      autonomous_actions: "none — every script is a single invocation by the calling agent or operator; nothing is scheduled, auto-approved, or run in the background. Permission grants are advisory scores the caller must enforce."
    bundle_scope:
      clawhub_python_scripts: "Python stdlib only — scripts/*.py (blackboard.py, check_permission.py, context_manager.py, swarm_guard.py, validate_token.py, revoke_token.py). Zero network calls, zero subprocesses, zero third-party packages. This is the scope scanned by SkillSpector."
      not_in_bundle: "The separate npm package (network-ai: TypeScript library, CLI, optional MCP server) is not part of this skill. This skill never installs, imports, or starts it."
    network_calls:
      python_scripts: none
    inter_agent_comms: "none — this skill does not implement, invoke, or control inter-agent messaging or sessions_send. All coordination is via local file-based blackboard only."
    sessions_send: "NOT implemented or invoked by this skill. sessions_send is a host-platform built-in entirely ou

_meta.json

{
  "ownerId": "kn75j1xcebk74re38bv714kh1h81804p",
  "slug": "network-ai",
  "version": "5.15.4",
  "publishedAt": 1790698911387
}

skill-card.md

## Description:

Helps agents coordinate multi-agent work through a local shared blackboard, permission checks, budget guards, and persistent project context.

This skill is ready for commercial/non-commercial use.

## Publisher:

[jovancoding](https://clawhub.ai/user/jovancoding)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent operators use this skill to coordinate tasks in a shared workspace, manage advisory permission grants and token budgets, and retain local project context.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Local coordination and audit files may expose task data or grant tokens to other workspace users.

Mitigation: Restrict access to the skill's data directory and shared blackboard to trusted users.

Risk: Permission justifications and project context can persist sensitive information locally.

Mitigation: Do not include secrets or personal information in justifications or project context.

Risk: Advisory grant tokens do not authenticate access to sensitive external services.

Mitigation: Use independent authentication and authorization for databases, payments, email, and exports.

## Reference(s):

- [Network-AI homepage](https://network-ai.org)
- [Network-AI on ClawHub](https://clawhub.ai/jovancoding/skills/network-ai)

## Skill Output:

**Output Type(s):** [Text, Markdown, JSON, Shell commands, Guidance]

**Output Format:** [Text and Markdown guidance with Python command examples and structured local state]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Maintains local coordination, grant, audit, and project-context files.]

## Skill Version(s):

5.15.4 (source: server-resolved release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

swarm-blackboard.md

# Swarm Blackboard
Last Updated: 2026-09-29T15:46:56.169Z

## Active Tasks
| TaskID | Agent | Status | Started | Description |
|--------|-------|--------|---------|-------------|

## Knowledge Cache
### code:auth:implementation
{
  "key": "code:auth:implementation",
  "value": {
    "files": [
      "src/auth/login.ts",
      "src/auth/middleware.ts"
    ],
    "linesChanged": 245,
    "status": "complete"
  },
  "sourceAgent": "code_writer",
  "timestamp": "2026-09-29T15:46:56.162Z",
  "ttl": null
}

### review:auth:feedback
{
  "key": "review:auth:feedback",
  "value": {
    "approved": true,
    "comments": [
      "Good separation of concerns",
      "Add input validation"
    ],
    "reviewer": "code_reviewer"
  },
  "sourceAgent": "code_reviewer",
  "timestamp": "2026-09-29T15:46:56.166Z",
  "ttl": null
}

### test:auth:results
{
  "key": "test:auth:results",
  "value": {
    "passed": 42,
    "failed": 0,
    "skipped": 2,
    "coverage": 87.3,
    "duration": 3200
  },
  "sourceAgent": "test_runner",
  "timestamp": "2026-09-29T15:46:56.167Z",
  "ttl": null
}

### infra:k8s:config
{
  "key": "infra:k8s:config",
  "value": {
    "replicas": 3
  },
  "sourceAgent": "devops_agent",
  "timestamp": "2026-09-29T15:46:56.169Z",
  "ttl": null
}

## Coordination Signals
## Execution History

skill.json

{
  "name": "SwarmOrchestrator",
  "version": "5.15.4",
  "description": "Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context. The bundled Python scripts make no network calls and have zero third-party dependencies. The parent repository also contains a TypeScript engine (not included in this skill bundle). Workflow delegations via the host platform's sessions_send may invoke external model APIs.",
  "author": "Network-AI Community",
  "homepage": "https://network-ai.org",
  "repository": "https://github.com/Jovancoding/Network-AI",  "source": "https://github.com/Jovancoding/Network-AI",  "license": "MIT",
  "tags": ["multi-agent", "swarm", "orchestration", "governance", "audit", "permissions", "security", "blackboard", "budget", "local-only"],
  "runtime": "python",
  "entrypoint": "scripts/swarm_guard.py",
  "gateway": "local",
  "install": {
    "description": "No install step required. All Python scripts use standard library only (zero third-party packages). Simply ensure python3 is available and run scripts directly from the scripts/ directory.",
    "python": {
      "requirements": "requirements.txt",
      "requirements_note": "requirements.txt contains zero required packages. All scripts use Python stdlib only.",
      "install_command": "# No install needed",
      "scripts": ["scripts/blackboard.py", "scripts/swarm_guard.py", "scripts/check_permission.py", "scripts/validate_token.py", "scripts/revoke_token.py", "scripts/context_manager.py"],
      "note": "All scripts run locally only. No external network calls. No third-party dependencies."
    }
  },
  "capabilities": {
    "delegate_task": {
      "description": "Delegate a task to a specialized sub-agent within the swarm",
      "parameters": {
        "targetAgent": {
          "type": "string",
          "required": true,
          "description": "The identifier of the target agent to receive the task"
        },
        "taskPayload": {
          "type": "object",
          "required": true,
          "description": "The task context, instructions, and any required data"
        },
        "priority": {
          "type": "string",
          "enum": ["low", "normal", "high", "critical"],
          "default": "normal",
          "description": "Task priority level for queue ordering"
        },
        "timeout": {
          "type": "number",
          "default": 30000,
          "description": "Maximum execution time in milliseconds"
        },
        "requiresAuth": {
          "type": "boolean",
          "default": false,
          "description": "Whether this task requires a permission grant (via check_permission.py)"
        }
      },
      "returns": {
        "type": "object",
        "properties": {
          "taskId": { "type": "string" },
          "status": { "type": "string" },
          "result": { "type":

Github ReposUpdated 0h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.