← Back to Skills Marketplace
719
Downloads
2
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install venice-router
Description
Supreme model router for Venice.ai — the privacy-first, uncensored AI platform. Automatically classifies query complexity and routes to the cheapest adequate...
Usage Guidance
This skill appears to do what it says: it needs a Venice.ai API key and Python and routes prompts to Venice.ai models. Before installing, consider: (1) Where you store VENICE_API_KEY — putting it in ~/.openclaw/openclaw.json or exporting it will persist the secret on disk; prefer a scoped key and store it with appropriate filesystem permissions. (2) Use VENICE_PRIVATE_ONLY if you must keep data on Venice-hosted private models; otherwise some requests may be proxied to external providers (the README labels those as "anonymized"). (3) The skill may read conversation JSON or tools JSON files you point it to — do not pass files with secrets unless you understand which model/tier will receive them. (4) The installer copies files into ~/.openclaw workspace and requires network access for API calls (api.venice.ai and, optionally, web-search endpoints). Review the included scripts if you have elevated threat concerns and monitor API key usage (billing/spending) after enabling the skill.
Capability Analysis
Type: OpenClaw Skill
Name: venice-router
Version: 1.5.0
The OpenClaw AgentSkills skill bundle for 'venice-router' is classified as benign. The `venice-router.py` script, which is the core of the skill, performs its stated purpose of routing LLM prompts to the Venice.ai API. It securely handles the `VENICE_API_KEY` from environment variables, accesses the network only to `https://api.venice.ai`, and manages local cost tracking data within the user's home directory (`~/.venice-router/costs/`). The `install.sh` script copies local files and does not fetch external payloads. Crucially, the Python script explicitly states 'stdlib only, no pip dependencies', significantly reducing supply chain risks. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection against the OpenClaw agent itself. All file and network access is aligned with the skill's described functionality.
Capability Assessment
Purpose & Capability
Name/description, required binaries (python3), required env var (VENICE_API_KEY), and optional VENICE_* settings all align with a Venice.ai model-routing CLI/skill. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md and the Python script instruct the agent to call the Venice.ai API, optionally read conversation JSON or tools JSON files, and perform optional web-search/web-scraping. These behaviors are coherent with the stated purpose, but reading/uploading conversation or tools files and enabling web-scraping will transmit user data to Venice (or proxied providers) — users should avoid supplying sensitive files unless using private-only models and trust the provider.
Install Mechanism
Install uses a simple local install.sh (copies files into the user's OpenClaw workspace) and offers a brew formula to ensure Python exists. No downloads from arbitrary or untrusted URLs or extracted archives are present.
Credentials
Only VENICE_API_KEY is required (declared as primary), and the rest are optional VENICE_* flags relevant to routing/budgeting. One consideration: SKILL.md suggests storing the API key in ~/.openclaw/openclaw.json, which will persist the key on disk and could be readable by other local processes/users — this is expected but worth noting for users handling sensitive credentials.
Persistence & Privilege
always is false and the skill installs into its own OpenClaw skill directory. The installer does not modify other skills or system-wide settings beyond copying files into the user's OpenClaw workspace.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install venice-router - After installation, invoke the skill by name or use
/venice-router - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.5.0
v1.5.0: thinking/reasoning mode (--thinking flag, Qwen3 235B Thinking + Kimi K2 Thinking/K2.5), 5 new models (GPT-5.2 Codex, Gemini 3.1 Pro 1M ctx, Hermes 3 405B), fix budget-medium classifier gap, SKILL.md spec polish (YAML metadata, cliHelp, os field)
v1.4.1
Bundle scripts in package (fix missing code files)
v1.4.0
v1.4.0: Conversation-aware routing, cost budget tracking, function calling, Cloudflare fix, full security scan compliance.
v1.2.1
Fix ClawdHub security scan: bundle all scripts, declare optional env vars, add source URL, add install spec. Also: conversation-aware routing, cost budgets, function calling, Cloudflare 403 fix.
Metadata
Frequently Asked Questions
What is Venice.Ai Router Openclaw?
Supreme model router for Venice.ai — the privacy-first, uncensored AI platform. Automatically classifies query complexity and routes to the cheapest adequate... It is an AI Agent Skill for Claude Code / OpenClaw, with 719 downloads so far.
How do I install Venice.Ai Router Openclaw?
Run "/install venice-router" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Venice.Ai Router Openclaw free?
Yes, Venice.Ai Router Openclaw is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Venice.Ai Router Openclaw support?
Venice.Ai Router Openclaw is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, macos).
Who created Venice.Ai Router Openclaw?
It is built and maintained by Badmuff (@plusone); the current version is v1.5.0.
More Skills