Socket
Book a DemoSign in
Socket
Book a DemoSign in

network-ai

Package Overview
Dependencies
Maintainers
1
Versions
95
Alerts
File Explorer

Advanced tools

License
Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

network-ai - npm Package Compare versions

Comparing version
4.11.0
 to
4.11.1
+1
-1
package.json
{
"name": "network-ai",
"version": "4.11.0",
"version": "4.11.1",
"description": "AI agent orchestration framework for TypeScript/Node.js - 17 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex, MiniMax, NemoClaw, APS + streaming variants). Built-in CLI, security, swarm intelligence, real-time streaming, and agentic workflow patterns.",

@@ -5,0 +5,0 @@ "homepage": "https://network-ai.org",

+1
-1
README.md

@@ -8,3 +8,3 @@ # Network-AI

[![CodeQL](https://github.com/Jovancoding/Network-AI/actions/workflows/codeql.yml/badge.svg)](https://github.com/Jovancoding/Network-AI/actions/workflows/codeql.yml)
[![Release](https://img.shields.io/badge/release-v4.11.0-blue.svg)](https://github.com/Jovancoding/Network-AI/releases)
[![Release](https://img.shields.io/badge/release-v4.11.1-blue.svg)](https://github.com/Jovancoding/Network-AI/releases)
[![npm](https://img.shields.io/npm/dw/network-ai.svg?label=npm%20downloads)](https://www.npmjs.com/package/network-ai)

@@ -11,0 +11,0 @@ [![Tests](https://img.shields.io/badge/tests-1684%20passing-brightgreen.svg)](#testing)

+17
-4
SKILL.md

@@ -8,5 +8,6 @@ ---

homepage: https://network-ai.org
bundle_scope: "Python scripts only (scripts/*.py). All execution is local."
network_calls: "none from bundled scripts; platform sessions_send delegations may invoke external models"
sessions_ops: "platform-provided"
bundle_scope: "Python scripts only (scripts/*.py). All execution is local. No TypeScript, Node.js, adapters, or CLI tools are included in this bundle."
network_calls: "none โ€” bundled scripts make zero network calls. The host platform's sessions_send (not part of this skill) may invoke external models."
sessions_send: "NOT implemented or invoked by this skill. sessions_send is a host-platform built-in. This skill only provides budget guards that run before the platform delegates."
sessions_ops: "platform-provided โ€” outside this skill's control"
requires:

@@ -22,2 +23,8 @@ bins:

description: "Local append-only JSONL file recording operation metadata. No data leaves the machine."
pii_warning: "Do not include PII, secrets, or credentials in justification fields. Log entries persist on disk."
data_directory:
path: data/
scope: local-only
files: ["audit_log.jsonl", "active_grants.json", "project-context.json"]
description: "All persistent state is local-only. No files are transmitted over the network."
---

@@ -27,4 +34,8 @@

> **Scope:** The bundled Python scripts (`scripts/*.py`) make no network calls, use only the Python standard library, and have zero third-party dependencies. Tokens are UUID-based (`grant_{uuid4().hex}`) stored in `data/active_grants.json`. Audit logging is plain JSONL (`data/audit_log.jsonl`). Workflow delegations that use the host platform's `sessions_send` may invoke external model APIs outside this skill's control.
> **Scope:** The bundled Python scripts (`scripts/*.py`) make **no network calls**, use only the Python standard library, and have **zero third-party dependencies**. Tokens are UUID-based (`grant_{uuid4().hex}`) stored in `data/active_grants.json`. Audit logging is plain JSONL (`data/audit_log.jsonl`).
> **Data-flow notice:** This skill does NOT implement, invoke, or control `sessions_send`. That is a host-platform built-in (OpenClaw runtime). The orchestration instructions below describe *when* to call the platform's `sessions_send` after budget checks pass โ€” but the actual network call, model endpoint, and data transmission are entirely the host platform's responsibility. If you need to prevent external network calls, disable or reroute `sessions_send` in your platform settings before installing this skill.
> **PII / sensitive-data warning:** The `justification` field in permission requests and the audit log (`data/audit_log.jsonl`) store free-text strings provided by agents. **Do not include PII, secrets, or credentials in justification text.** Consider restricting file permissions on `data/` or running this skill in an isolated workspace.
## Setup

@@ -521,2 +532,4 @@

> **Privacy note:** Audit log entries contain agent-provided free-text fields (justifications, descriptions). These are stored locally in `data/audit_log.jsonl` and never transmitted over the network by this skill. However, **do not put PII, passwords, or API keys in justification strings** โ€” they persist on disk. Consider periodic log rotation and restricting OS file permissions on the `data/` directory.
### What Gets Logged Automatically

@@ -523,0 +536,0 @@