Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
Latest release v1.68.3 · 26 Oct 2026
10 files for Claude Code, Codex and OpenCode: prismor AGENTS.md, prismor CLAUDE.md, UserPromptSubmit, PreToolUse and 6 more — 5,259 tokens loaded in every session.
AGENTS.md C 4,567 tok CLAUDE.md A 692 tok .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — .claude/settings.json A — These files are PrismorSec/prismor's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.