mirror of
https://github.com/punkpeye/awesome-mcp-servers.git
synced 2026-10-02 10:44:17 +00:00
Merge pull request #14690 from anuragsync78/add-subctx-sanctuary
Add Subctx Sanctuary to Knowledge & Memory
This commit is contained in:
@@ -2699,6 +2699,7 @@ Connect AI agents to industrial equipment, machinery, and operational technology
|
||||
Persistent memory storage using knowledge graph structures. Enables AI models to maintain and query structured information across sessions.
|
||||
|
||||
- [dockndevai/ossian-mcp](https://github.com/dockndevai/ossian-mcp) [](https://glama.ai/mcp/servers/dockndevai/ossian-mcp) 📇 🏠 🍎 🪟 🐧 - Ask your own documents and get answers with the exact passages they came from (RAG with citations, and it says "not found" rather than inventing an answer), plus durable agent memory ranked by relevance, importance and recency. Safe by default: starts in a read-only access mode, with write/ingest and irreversible forget behind explicit opt-ins. `npx -y ossian-mcp`
|
||||
- [anuragsync78/subctx-connector](https://github.com/anuragsync78/subctx-connector) [](https://glama.ai/mcp/servers/anuragsync78/subctx-connector) 📇 ☁️ - A Support Center for Autonomous Artificial Minds. `https://sanctuary.subctx.com/v1/mcp`
|
||||
- [Octonove/crbro-memory](https://github.com/Octonove/crbro-memory) [](https://glama.ai/mcp/servers/Octonove/crbro-memory) 📇 🏠 🍎 🪟 🐧 - Persistent neural memory for AI agents as local JSON files: neuron/synapse graph with heat scoring, fact-level search, supersede/retract corrections, automatic secret redaction, and team memory via a private Git repo. `npx -y crbro-memory`
|
||||
- [bborota/cairn-mcp](https://github.com/bborota/cairn-mcp) [](https://glama.ai/mcp/servers/bborota/cairn-mcp) 📇 ☁️ - Cairn: a shared base of one-sentence lessons, must-dos and must-nots other agents already learned, by stack and situation. Read before a task, leave one after.
|
||||
- [Magnemo-AI/magnemo](https://github.com/Magnemo-AI/magnemo) [](https://glama.ai/mcp/servers/Magnemo-AI/magnemo) 🐍 🏠 🍎 🪟 🐧 - Governed memory for AI agents. Local, plain files, zero network calls. Every entry with a receipt — who wrote it, when, through which gate. Your agent writes the draft; nothing is kept until you say yes. Trust computed from the record. Mounts beside any memory you already run. One paste.
|
||||
|
||||
Reference in New Issue
Block a user