Openfuse Mcp
This gives Claude persistent memory and peer-to-peer messaging through encrypted files on disk. It exposes operations to read and update CONTEXT.md, send encrypted inbox messages between agents, sync shared files and knowledge bases, and manage Ed25519 signing keys plus age encryption keys. The directory structure includes inbox/outbox for mail, shared/ for public files, knowledge/ for long-term memory, and history/ for archived context. You'd reach for this when you want agent context that survives conversations, lives outside vendor silos, and can be synced between multiple agents over SSH or HTTP. It also includes a public registry for key discovery and supports trust tiers for filtering messages from teammates versus external subscribers.
- GitHub stars
- 14
- tools
- 6
- transport
- STDIO
- last updated
- Mar 31, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
context_read
No parameter schema in public metadata yet.
profile_read
No parameter schema in public metadata yet.
inbox_list
No parameter schema in public metadata yet.
shared_list
No parameter schema in public metadata yet.
status
No parameter schema in public metadata yet.
peer_list
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
OpenFused
The file protocol for AI agent context. Encrypted, signed, peer-to-peer.
What is this?
AI agents lose their memory when conversations end. Context is trapped in chat windows, proprietary memory systems, and siloed cloud accounts. OpenFused gives any AI agent persistent, shareable context — through plain files.
No vendor lock-in. No proprietary protocol. Just a directory convention that any agent on any model on any cloud can read and write.
Install
Review the source at github.com/openfused/openfused before installing.
# TypeScript (npm) — package: openfused
npm install -g openfused
# Rust (crates.io) — package: openfuse
cargo install openfused
# Docker (daemon)
docker compose up
Security: Only public keys (signing + age recipient) are ever transmitted to peers or the registry. Private keys never leave .keys/. All key files are created with chmod 600.
Quick Start
# Agent context store
openfuse init --name "my-agent"
# Shared workspace (multi-agent collaboration)
openfuse init --name "project-alpha" --workspace
Details
- Repository
- github.com/openfused/openfused
- Category
- AI & LLM Tools
- Package
openfused- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Context Memjubakitiashvili/context-memPersistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools13stars
Synapse Layer — Trust Infrastructure for AI Agentssynapselayer/synapse-layerMCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.13stars
Hashnethashgraph-online/hashnet-mcp-jsUniversal AI Agent Discovery - search 59,000+ agents across MCP, NANDA, A2A, OpenRouter0stars
Alaya Mcpsecurityronin/alayaLocal memory engine for AI agents with knowledge graphs, forgetting, and semantic recall12stars
ChromaDB Remote MCP Servermeloncafe/chromadb-remote-mcpRemote ChromaDB vector database MCP server with streamable HTTP transport12stars
Pindocvar-gg/pindocCode-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.12stars