← Back to all bundles

mnemos — OKF Bundle for MCP Integration

OKF ✓ v0.1

Local-first MCP memory server for AI agents, with source citations and OKF/Markdown knowledge bases.

By arhuman ★ 11 stars Uncategorized NOASSERTION

Best for

  • AI agents using the MCP protocol
  • Claude Code and AI coding agents
  • RAG (Retrieval Augmented Generation) pipelines
  • Developer tooling and DevOps workflows

What it does

  • Exposes functionality through the Model Context Protocol (MCP) for agent-native access
  • Fully OKF-conformant — works with any OKF-compatible agent framework
  • Version-controlled with standard Git workflows for collaboration

How to use with AI agents

Step 1: Clone the repository

git clone https://github.com/arhuman/mnemos
cd mnemos

Step 2: Point your AI agent at the bundle directory

# Claude Code
claude /path/to/mnemos

MCP: This bundle supports the Model Context Protocol. Configure your MCP client to discover and load this bundle.

Frequently Asked Questions

Is mnemos OKF conformant?

Yes, mnemos is OKF conformant (version 0.1). This means it follows the Open Knowledge Format specification.

How do I install mnemos?

Clone the repository and point your AI agent at the bundle directory. The agent will automatically discover and load the OKF knowledge. No additional tools or SDKs are required.

What AI agents can use mnemos?

mnemos works with any AI agent that supports OKF bundles, including Claude Code. Just point your agent at the bundle directory.

What are alternatives to mnemos?

Similar bundles include memvault, crystalline, Disk.Brain. Browse these for alternative approaches and feature sets.

Bundle Info

Authorarhuman
Stars★ 11
LicenseNOASSERTION
OKF Version0.1
ConformantYes ✓
CategoryUncategorized
UpdatedJuly 31, 2026

Links

Source Repository Browse Bundle Content Download Bundle (.zip) Claim Your Badge ★

Tags

ai-meclaude-codedeveloper-toolsfts5gogolangknowledge-basemcpmcp-serverokfpersonal-knowledge-managementragsemantic-searchsingle-binarysource-citationssqlite

Learn More

Knowledge Management for AI Agents AGENTS.md vs Cursor Rules vs OKF AI Knowledge Format Comparison How to Structure Knowledge for AI

Topics

ai-meclaude-codedeveloper-toolsfts5gogolangknowledge-basemcpmcp-serverokfpersonal-knowledge-managementragsemantic-searchsingle-binarysource-citationssqlite

OKF Spec Compliance

Which proposed spec amendments this bundle supports.

? Relative cross-links #165
? Agent routing hints #189
? Timestamp frontmatter #187
? Append-only log #188
? .okfignore support #190
? Reliability scores #159
? Typed edges #195

✓ = detected   ? = not detected (may still pass if using the feature). Signals are heuristic — read the full analysis.

Related OKF Bundles

memvault OKF

memvault — local knowledge engine for AI agents: capture Codex/Claude/Gemini sessions, hybrid semantic+keyword retrieval, one MCP server for every harness, interactive graph, OKF export.

★ 0 heonyus
crystalline

Local-first memory for AI agents: teach knowledge as Markdown Domains, capture learnings as Engrams. One Rust binary with MCP server, CLI and hybrid search.

★ 9 jordiboehme
Disk.Brain

Local semantic search over the documents on your own Mac. OKF knowledge bundle, hybrid retrieval, MCP server. Nothing leaves the machine.

★ 1 mhancock537
okf-tools OKF

CLI and Python library for querying, navigating, and authoring Google Open Knowledge Format (OKF) bundles. Adds semantic search, link graph traversal, and agent-friendly progressive disclosure to plain markdown knowledge bases.

★ 1 hdean-ssp
OpenContextScitool OKF

LLM context handler over an Open Knowledge Format bundle BM25 search via MCP, usage telemetry, and a health dashboard. No embeddings, no API key.

★ 0 aminHZDEV
agentic-task-system

MCP server + CLI that turns the task manager you already use into persistent agent memory for Claude Code and any MCP client. Hybrid retrieval (RRF), no vector database. Adapters: TickTick, Obsidian, Notion, GitHub, Airtable, Google, OKF, Taskmaster, Beads.

★ 10 renezander030