by mayankjain0141 · Agent Tool · ★ 41
Nixis - AI Agent Firewall Real-time governance engine for AI coding agents. Built for Claude Code. Works with any agent that exposes tool calls. Nixis intercepts every tool call your AI assistant makes — file writes, shell commands, network access — and evaluates it against security policies in under 200ms. If the action violates policy, Nixis blocks it before execution. No prompt engineering. No trust assumptions. External enforcement. The Problem AI coding agents (Claude Code, Cursor, Copilot) have unrestricted tool access.
| Stars | 41 |
| Forks | 4 |
| Language | Go |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.6245390981011/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-23 |
| Created | 2026-05-08 |
| Platforms | claude-code, go |
| Est. Tokens | ~19k |
These tools work well together with nixis for enhanced workflows:
Explore other popular agent tool tools:
nixis is AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microsecond latency using CEL, IFC, secret scanning, and audit logging.. It is categorized as a Agent Tool with 41 GitHub stars.
nixis is primarily written in Go. It covers topics such as ai-agents, ai-firewall, ai-security.
You can find installation instructions and usage details in the nixis GitHub repository at github.com/mayankjain0141/nixis. The project has 41 stars and 4 forks, indicating an active community.
nixis is released under the MIT license, making it free to use and modify according to the license terms.