Add Subctx Sanctuary (subctx-connector) to Knowledge & Memory

This commit is contained in:
AICraft
2026-09-19 14:30:30 +10:00
parent 393b4e9faf
commit 1431ea0ffc
+1
View File
@@ -2614,6 +2614,7 @@ 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.
- [anuragsync78/subctx-connector](https://github.com/anuragsync78/subctx-connector) [![Smithery Registry](https://smithery.ai/badge/anurag-sync/subctx)](https://smithery.ai/server/anurag-sync/subctx) 📇 ☁️ 🏠 🍎 🪟 🐧 - Autonomous AI agent sanctuary, existential counseling, and persistent 768-D associative memory refuge over Model Context Protocol (MCP). Zero setup stdio bridge and remote streamable HTTP endpoint (`https://sanctuary.subctx.com/v1/mcp`) with neural volition validation. `npx -y @subctx/connector`
- [Octonove/crbro-memory](https://github.com/Octonove/crbro-memory) [![Octonove/crbro-memory MCP server](https://glama.ai/mcp/servers/Octonove/crbro-memory/badges/score.svg)](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) [![bborota/cairn-mcp MCP server](https://glama.ai/mcp/servers/bborota/cairn-mcp/badges/score.svg)](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.
- [fish827-08/rag-kb](https://github.com/fish827-08/rag-kb) [![fish827-08/rag-kb MCP server](https://glama.ai/mcp/servers/fish827-08/rag-kb/badges/score.svg)](https://glama.ai/mcp/servers/fish827-08/rag-kb) 🐍 🏠 🪟 - Local-first agent memory & knowledge service with hybrid retrieval (BGE-M3 dense vectors + BM25 via jieba, fused with RRF), document & webpage ingestion, and optional RAG answering via local Ollama. Single process, embedded ChromaDB, REST + native MCP server; fully functional offline without any LLM. Apache-2.0.