zames_pro
Terminal coding agent that drives a real browser to chat with DeepSeek, Qwen or GLM — no API key required. Reads and edits files, runs commands, commits to git, like Claude Code / Codex CLI.
No outside reports on file
This tool gives an AI agent full control over your computer—files, commands, browser, and identity—so only use it in isolated environments or with trusted, well-monitored inputs, and assume any injected prompt could cause damage.
Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionRuns shell or system commandsREVIEW
- Network reachFetches arbitrary web URLsREVIEW
- CredentialsRequires API key or tokenREVIEW
- Package sourcenpm (zames_pro)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y zames_proEverything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: D (from public signals such as stars and downloads, not a code review). Graded 2026-10-27.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Zames Pro
This tool acts as a coding agent that opens a real web browser to chat with AI models (DeepSeek, Qwen, or GLM) without needing API keys. It can read and edit files on your computer, run terminal commands, and make git commits—similar to Claude's code execution features but through a browser interface.
Who it’s for
Developers who want browser-based AI coding assistance without API credentials, or those experimenting with alternative AI models. It's designed for people comfortable running terminal tools and managing their own AI model access.
Alternatives
- Claude Desktop with MCP servers — local AI coding with more controlled permissions and official support
- GitHub Copilot CLI — browser-free terminal assistant with GitHub integration
- LocalAI or Ollama — self-hosted models with local API access, no web browser needed
- Continue IDE extension — VS Code plugin for AI-assisted coding with better sandboxing
Setup
Check these steps against the project’s own instructions before running anything.
Install via npm:
npm install zames_pro
Follow the project's README for specific configuration and how to connect it to your chosen AI model.
Why this grade
Signal-based grade (1/7 points): no public source code found. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- Weekly npm downloads
- 43.3k
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Browser automation risk: Opens a real browser controlled by the AI, which could visit malicious websites or perform unintended actions if the AI is compromised or misled
- File system access: The tool can read and edit any files your user account can access; malicious prompts might trick it into deleting or exposing sensitive data
- Command execution: It runs arbitrary terminal commands, potentially letting an attacker modify system files, install malware, or access credentials stored locally
- Git commit abuse: Could make unauthorized commits with your identity if the AI is manipulated or the tool is compromised
- No API authentication: Bypassing API keys means less oversight; the AI's requests go directly through your browser without rate limiting or usage tracking from the model provider
How to lower the risk
Least-privilege permissions
- Run it in a dedicated user account with minimal file access
- Avoid storing passwords, tokens, or secrets in directories it can reach
Network isolation
- Run on a machine without sensitive network access or production systems
- Consider using a virtual machine or container to isolate it from the rest of your setup
Monitoring
- Watch terminal output and browser behavior for unexpected commands or visits
- Log all file changes and git commits the tool makes
Red flags to watch for
- Prompts asking it to visit URLs, fetch files, or execute code without explanation
- Sudden git commits or file edits you didn't request
- Browser opening to unfamiliar websites or performing unusual actions
Questions
How do I install Zames Pro?
Run npx -y zames_pro in your terminal, or add the server entry to your claude_desktop_config.json or .cursor/mcp.json as shown in the Setup section on this page.
Are there security reports about Zames Pro?
No reports found for this package in our research (last checked 2026-10-30). Zames Pro currently holds Grade D (High risk signals) based on public adoption and transparency signals. Key risk areas to watch include browser automation risk, file system access, command execution.
Is Zames Pro actively maintained?
Zames Pro has 43.3k weekly npm downloads. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues before pinning it in production.
What are alternatives to Zames Pro?
Notable alternatives to Zames Pro include Claude Desktop with MCP servers (local AI coding with more controlled permissions and official support), GitHub Copilot CLI (browser-free terminal assistant with GitHub integration), LocalAI or Ollama (self-hosted models with local API access, no web browser needed), Continue IDE extension (VS Code plugin for AI-assisted coding with better sandboxing). You can also compare Zames Pro side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Zames Pro? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/viqto0r-zames-pro)HTML embed:
<a href="https://agentarmorhq.com/skills/viqto0r-zames-pro"><img src="https://agentarmorhq.com/api/badge/viqto0r-zames-pro" alt="AgentArmorHQ Risk Grade for Zames Pro" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "viqto0r-zames-pro"Share with your security lead
Need sign-off to use zames_pro? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: zames_pro
- **Listing URL:** https://agentarmorhq.com/skills/viqto0r-zames-pro
- **Type:** App connector
- **Risk Grade:** Grade D (High risk signals)
- **Outside Security Advisories on File:** 0
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** Runs shell or system commands
- **Network reach:** Fetches arbitrary web URLs
- **Credentials:** Requires API key or token
- **Package source:** npm (zames_pro)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts zames_pro`
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Install command
- npm install zames_pro
- Est. context load
- ~700 tokens / turn (~4 tool schemas, 0.35% of 200k context)
- Popularity
- 43.3k weekly npm downloads
- Last updated
- 2026-10-30
- Last graded
- 2026-10-27
Community
Discussions for Zames Pro
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude