node9-ai / node9-proxy
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
Why this job: topics: agent-security, security-tools, security, ai-security, llm-security, prompt-injection, cybersecurity, ai-safety
What it does
A real Claude Code session with node9 installed. Every tool call is checked before it runs. Building a page and editing a button run. A request to the cloud metadata address is blocked, and the agent gets the reason and carries on. Deleting files waits for your approval, right in the chat.
Get started
brew tap node9-ai/node9 && brew install node9
# macOS / Linux
npm install -g node9-ai
# any platform - Maintenance
- Active
- Last commit yesterday
- Stars
- 225
- +2 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v2.56.0
- Released today
- Built with
- TypeScript
- 99% of the code
Is it looked after?
- Contributors
- 4
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 381 merged
- 1 waiting
- Releases
- 286
- 30+ in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| pipelab-org / pipelock | 987 | today | Apache-2.0 | Mac, Windows, Linux |
| NVIDIA / SkillSpector | 24,955 | 3 days ago | Apache-2.0 | No downloads |
| Tencent / AI-Infra-Guard | 7,441 | 4 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- TypeScript 99%
- JavaScript 1%
- Shell <1%
Topics
- ai-safety
- ai-security
- claude-code
- llm-agent
- agent-security
- dlp
- github-actions
- mcp-security
- mcp-servers
- prompt-injection
- ssrf
- ai-agents
Project record
- JobAI security
- StatusListed
- Commits2,311
- Forks21
- Watching0
- Stars in 28 days+6
- CreatedFeb 27, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026