by Bucha11 · Agent Tool · ★ 27
axor-core Execution governance kernel for AI agents. Axor places a policy membrane between agent intent and tool execution. Instead of trying to detect malicious prompts, Axor governs what actions are allowed to cross the execution boundary. The Problem Raw agent execution has no defense layer. A production LLM agent can: call shell tools it was never meant to have read files far outside the task scope spawn uncontrolled child agents down arbitrary call trees carry tainted external content through N subsequent intents without any signal export intermediate reasoning that should never leave...
| Stars | 27 |
| Forks | 0 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 63.5804726821632/100 |
| Open Issues | 1 |
| Last Updated | 2026-07-03 |
| Created | 2026-04-13 |
| Platforms | python |
| Est. Tokens | ~18k |
These tools work well together with axor-core for enhanced workflows:
Explore other popular agent tool tools:
axor-core is Governance kernel for agent systems with policy-based execution, context control, and traceable tool usage.. It is categorized as a Agent Tool with 27 GitHub stars.
axor-core is primarily written in Python.
You can find installation instructions and usage details in the axor-core GitHub repository at github.com/Bucha11/axor-core. The project has 27 stars and 0 forks, indicating an active community.
axor-core is released under the MIT license, making it free to use and modify according to the license terms.