osk-system: Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents

by lpaiu-cs · MCP Server · ★ 76

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Featured in: Knowledge Base & RAG · Obsidian for Claude Code & AI Agents

Security audit verdict: SAFE · quality 54/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

agent-memoryai-agentsdeveloper-toolsknowledge-managementllm-memorylong-term-memoryltmmcpobsidianrag

Quick Facts

Stars76
Forks11
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score54/100
Open Issues21
Last Updated2026-11-19
Created2026-05-25
Platformsmcp, python
Est. Tokens~13k

About osk-system

osk-system 에이전트의 장기 기억을 위한 지식 그래프 체계. Problem 에이전트가 쓰는 지식 저장소에서는 한 가지가 계속 흐려진다 — 무엇이 사용자가 확인한 것이고 무엇이 에이전트가 만든 후보인가. 그 구별이 흔들리면 저장소는 "그럴듯한 것이 쌓인 곳"이 되고, 회상은 신뢰할 수 없게 된다. osk-system은 그 구별을 사람의 기억이나 관행이 아니라 기계가 틀리지 않게 판정하도록 만든 체계다. 세 구조가 그것을 떠받친다. 권위를 노드 밖으로 뺐다. 승인은 노드 안의 필드가 아니라 별도 대장의 기록이다 — 사용자가 마지막으로 승인한 구획 전체의 상태(승인본)를 엔진이 따로 보존한다.

osk-system alternative? Top 6 similar tools

Looking for a osk-system alternative? If you're comparing osk-system 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.

  • ctxvault by Filippo-Venturini · ⭐ 69

    Local-first memory for AI agents: semantic, procedural and episodic vaults you compose, control and query. CLI

  • YourMemory by sachitrafa · ⭐ 272

    Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

  • agentopology by agentopology · ⭐ 108

    Harness as code — the Terraform for AI agents. Define your agent team AND its memory once, deploy to Claude Co

  • claude-mem-lite by sdsrss · ⭐ 68

    Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across

  • widemem-ai by remete618 · ⭐ 50

    Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; Ope

  • superlocalmemory by qualixar · ⭐ 278

    Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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:

View on GitHub → Browse MCP Server tools