Stop your agents from going rogue.
Prismor is an open-source, independent control plane for AI agents. It helps enterprises control agent identity, access, and runtime actions by intercepting every tool call before execution, enforcing policy, protecting secrets, and recording a full audit trail across coding agents, SDKs, and MCP workflows.
| Repository | Description |
|---|---|
| prismor | Open-source runtime control plane for AI agents. Intercepts tool calls before execution to allow, block, mask, or request approval, with policy-as-code and a full audit trail. |
| patchbot | Vulnerability scanning with your own scanners and threat feeds, plus a coding agent that opens fix PRs. Available as a CLI, GitHub Action, or scheduled managed-agent deployment. |
| product-sbom-vex | Last-mile EU CRA compliance tooling. Generate product-level SBOMs and VEX documents based on CSAF 2.0. |
| security-playbook | Security skill pack for AI coding agents: OWASP code and LLM rules, behavioral guardrails, static analysis guidance. |
| tagdiff | Aggregates changelogs across GitHub releases between two versions. |
PRs are welcome across all repos. See each repository's README for setup and contribution guidance. Open an issue first if you are unsure where something fits, and run the relevant test suite before opening a PR.
- Discord - questions, ideas, and discussion
- X / Twitter - updates and announcements
- prismor.dev - docs and product info
- contact@prismor.dev - everything else