← Back to Skills Marketplace
Network-AI
by
Jovan Marinovic
· GitHub ↗
· v5.15.1
· MIT-0
6651
Downloads
6
Stars
0
Active Installs
159
Versions
Install in OpenClaw
/install 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).
Usage Guidance
Install this only for trusted local workspaces where multi-agent coordination is actually needed. Do not put secrets, credentials, or PII in justifications, blackboard entries, or project context; protect or periodically clear the data directory. Treat grant tokens as advisory hints, not real authorization, and configure any host-level delegation or external API access with explicit limits.
Capability Assessment
Credentials
Runtime behavior is local file I/O under the skill data directory or env-scoped data subdirectories; imports and inspected code show no network, subprocess, package install, or credential-store access.
Install Mechanism
No install step or third-party dependency is required; requirements.txt is documentation-only and the scripts use Python standard library modules.
Instruction Scope
The manifest exposes broad orchestration concepts, but the skill documentation scopes use to complex trusted-workspace workflows, says the bundled Python does not spawn agents or make network calls, and instructs budget checks before delegation.
Persistence & Privilege
The skill intentionally persists blackboard entries, project context, audit logs, active grant records, and a local signing key. This is disclosed and purpose-aligned, but users should treat the data directory as sensitive.
Purpose & Capability
The stated purpose matches the artifacts: local blackboard coordination, budget/health checks, advisory permission scoring, and persistent project context for multi-agent workflows.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install network-ai - After installation, invoke the skill by name or use
/network-ai - Provide required inputs per the skill's parameter spec and get structured output
Version History
v5.15.1
v5.15.1 security patch: fix GHSA-743h-jr5x-mpcr (ClaudeHookBridge deny-pattern bypass via truncation before the security decision) and GHSA-9v4f-j8cv-fhxw (SandboxPolicy blocklist/approval-gate bypass via quote/whitespace matcher mismatch); 3638 tests across 41 suites
v5.15.0
v5.15.0 context signal-over-noise: ContextComposer (token-budgeted, relevance-ranked context assembly with recency decay and scope affinity) plus context_pack and blackboard_search MCP tools (24 tools total); 3603 tests across 40 suites
v5.14.0
v5.14.0 ecosystem expansion: Gemini, OpenAI Responses, and Claude Agent SDK adapters (32 total); Claude Code hooks gating via AuthGuardian; MCP elicitation approvals; A2A server mode; Gemini CLI extension; AGENTS.md; MCP Registry manifest
v5.13.4
Security fixes: GHSA-m4jg-6w3q-gm86 (ApprovalInbox auth+CORS) and GHSA-3jf7-33vc-hgf4 (APSAdapter fail-closed signature verification)
v5.13.3
fix: correct display name to Network-AI
v5.13.2
fix: correct ClawHub display name
v5.13.1
fix: reword audit-log privacy note to clear SkillSpector YARA false positive
v5.13.0
v5.13.0: model-interaction lifecycle governance — GovernedModelGateway (refusal->fallback->billing), ModelBudget fallback-credit repricing, RefusalTelemetry, EffortPolicy, per-sub-agent fallback, ThinkingBlockManager, OWASP Agentic Top 10 coverage matrix
v5.12.7
v5.12.7: fix recurring SkillSpector finding — comment.txt draft note no longer bundled (ClawHub honours .clawhubignore); added npm run clawhub:check bundle-hygiene guard; closed data/, .env, *.log and other bundle leaks
v5.12.6
v5.12.6: CodeQL security fixes — resolve #177 (indirect command injection in socket-check.js: spawnSync + semver validation), #176 and #175 (unused imports). New scripts/codeql-check.js monitor + npm run codeql:check. SKILL.md: 3 new SkillSpector by-design findings documented. RELEASING.md: CodeQL gate step added.
v5.12.5
v5.12.5: Supply-chain security hardening. Remove gptSecurity (debugAccess) alerts — replaced String.fromCharCode obfuscation pattern in blackboard-validator with named EVAL_FN constant. Explicit policy gate at shell exec call sites in bin/console.ts. SUPPLY_CHAIN.md sections 5a (shell surface) and 5b (telemetry). New scripts/socket-check.js score monitor. Supply Chain Score: 75 → ~80.
v5.12.4
5.12.4 - SkillSpector findings resolved (.clawignore excludes comment.txt, SKILL.md trigger hardening), Socket.dev scan gap closed (9 missing entries: d.ts decls, ESM adapter mirrors, example/run shellAccess). networkAccess 64, shellAccess 10.
v5.12.3
5.12.3 - Socket.dev supply-chain triage for the dual CJS+ESM build (gptSecurity console pipe-mode entry plus dist/esm networkAccess and shellAccess mirrors) and console pipe-mode approval hardening (fail-closed: approval-required operations are denied unless --auto-approve).
v5.12.2
5.12.2: Security patch - fix 5 CVEs: symlink escape in backup (GHSA-6x2m), restore() path traversal (GHSA-48x2), poisoned manifest pruning (GHSA-2fmp), sandbox path-prefix bypass (GHSA-jvcm), unauthenticated ApprovalInbox (GHSA-mxjx).
v5.12.1
5.12.1: OpenAI Codex MCP integration (.codex/config.toml), PRIVACY.md privacy policy, CI npm publish race fix, and version/doc resync. 3269 tests across 33 suites.
v5.12.0
v5.12.0 - Claude Code plugin support. Network-AI is now installable as a Claude Code plugin (self-hosted marketplace): /plugin marketplace add Jovancoding/Network-AI. Wires the existing network-ai-server MCP server (stdio) into Claude Code so all tools load natively. Version bump 5.11.0 to 5.12.0 across manifests and docs.
v5.11.0
ESM dual-build, McpStreamableServer MCP 2025-03-26 Streamable HTTP + resources/prompts, PhasePipeline checkpoint/resume, SemanticMemory file-backed persistence. 3,269 tests across 33 suites.
v5.10.2
v5.10.2: CodeQL #174 CWE-377 root cause fix — eliminate os.tmpdir() taint sources in test-claim-verifier.ts
v5.10.1
v5.10.1: CodeQL #174 CWE-377 fix (AuthGuardian trustConfigPath), SkillSpector FILE_EXPORT in HIGH_RISK_RESOURCES, ensure_data_dir() env-scope fix
v5.10.0
v5.10.0: ClaimVerifier Tier 1 agent honesty — HMAC-signed ExecutionReceipts, UNSUPPORTED_CLAIM/UNDISCLOSED_ACTION violations, trust decay, 3211 tests across 32 suites
Metadata
Frequently Asked Questions
What is 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). It is an AI Agent Skill for Claude Code / OpenClaw, with 6651 downloads so far.
How do I install Network-AI?
Run "/install network-ai" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Network-AI free?
Yes, Network-AI is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Network-AI support?
Network-AI is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Network-AI?
It is built and maintained by Jovan Marinovic (@jovancoding); the current version is v5.15.1.
More Skills