by panaversity · MCP Server · ★ 223
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ksor safe to install? View the security audit →
Watch the video: KSoR Introduction KSoR Open, vendor-neutral knowledge infrastructure for predictable enterprise and education agentic systems. A company cannot expect predictable AI-agent behavior if its agents operate from scattered, conflicting, or outdated knowledge. An education institution cannot deliver an organized AI-assisted course if its tutors, teaching assistants, and assessment agents operate from different curricula, sources, or rules. You cannot build predictable AI systems on an undefined source of truth. A Knowledge System of Record (KSoR) solves that problem by giving an organization one governed, authoritative knowledge record that humans and AI agents operate from. For an enterprise, that record can contain approved: policies, procedures, rules, methods, standards, definitions, controls, decision criteria, and institutional knowledge. For an education institution, it can contain approved: curriculum, learning objectives, concepts and definitions, pedagogy, course sequence, source material, assessment rules, grading criteria, and the current course version. The AI can still reason, explain, personalize, and adapt. What it should not hav
npx @panaversity/ksor@latest init my-knowledge-sor
pnpm dlx @panaversity/ksor@latest init my-knowledge-sorTaken from the project's README on GitHub. Check the security audit before running it.
No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 223 |
| Forks | 45 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 62.2289234674179/100 |
| Open Issues | 18 |
| Last Updated | 2026-10-01 |
| Created | 2026-08-17 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~26k |
These tools work well together with ksor for enhanced workflows:
Looking for a ksor alternative? If you're comparing ksor with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple S
HazelJS Agent OS — durable TypeScript agents (DNA, Skillgate, Gatekeeper, crash-safe HITL) in your Node backen
Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable
Aser is a lightweight, self-assembling AI Agent frame.
Remote approvals, policy checks, and execution evidence for unattended AI agents.
Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools,
Explore other popular mcp server tools:
ksor is KSoR (Knowledge System of Record) is an open-source SDK for building governed, authoritative knowledge systems for humans and AI agents. It is a foundation of an AI-native knowledge platform.. It is categorized as a MCP Server with 223 GitHub stars.
ksor is primarily written in TypeScript. It covers topics such as agents, ai-agents, ai-data.
The README on GitHub (github.com/panaversity/ksor) gives: npx @panaversity/ksor@latest init my-knowledge-sor , then pnpm dlx @panaversity/ksor@latest init my-knowledge-sor. Usage details are in the same README.
ksor is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to ksor on Agent Skills Hub include Wax, hazeljs, busabase. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: