n8n community node: DeepSeek Reasoner Chat Model (ZH) — DeepSeek 思考模式 Chat Model(繁中修正版)。完整保留 reasoning_content 以支援 AI Agent 多輪工具呼叫(修復 400 錯誤),並保留中文輸出。Fork of n8n-nodes-deepseek-reasoner (adcom, MIT)。
Storage, memory and knowledge management for agents.
n8n community node: DeepSeek Reasoner Chat Model (ZH) — DeepSeek 思考模式 Chat Model(繁中修正版)。完整保留 reasoning_content 以支援 AI Agent 多輪工具呼叫(修復 400 錯誤),並保留中文輸出。Fork of n8n-nodes-deepseek-reasoner (adcom, MIT)。
Persistent memory for AI coding agents. Knowledge graph with 4-tier taxonomy, confidence scoring, and MCP protocol support for Claude Code, Cursor, Gemini CLI, Windsurf, Cline, Codex, and OpenCode.
Geometric memory for AI coding agents. Installs the 'attention-matters' package.
Self-hosted Meta MCP connector covering Facebook Pages, Instagram, Threads, Ads Manager, Commerce, Conversions, and Insights.
Execution engine for GAFF workflows - executes intent graphs with memory-backed state management, parallel execution, and HITL support
Memory for AI coding agents: the plans, tasks, decisions, rules and bugs your agents work through, recorded automatically, shared with your team, readable by every agent through MCP, with a dashboard.
Monitor any AI agent system. Auto-detects failures, sends alerts, audits OS processes. Zero config, zero dependencies.
Local-first, persistent memory for AI coding agents — remember, recall, forget, and list, over MCP.
Multi-Scope Local Memory — local-first AI agent memory with personal/global/shared scopes. 7-channel retrieval, Fisher-Rao similarity, multi-scope RRF fusion.
Parser facts about a codebase: architecture, call graphs, control flow, effects, beliefs
Persistent multi-path memory for AI agents — vector + BM25 keyword + entity graph search with RRF fusion, credential scrubbing, auto-consolidation, multi-backend storage (Qdrant + SQLite/Postgres)
Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)
MCP Server for Planning Task - Full autonomous project management via Firebase Realtime Database
MUSUBIX Ontology Reasoning MCP - OWL 2 RL inference and SPARQL query
Structured graph capabilities for AI agents consuming Ontoly.
Compile your Markdown vault into a portable agent memory. One build, every agent: Claude, Codex, Cursor, MCP, llms.txt.
Obsidian vault adapter for Agentic Task System. Hybrid + RRF retrieval, the wiki layer, and the MCP server over the folder of markdown you already keep in Obsidian — adapter, not migration.
SSTIM reference for senses, stimuli, perception and scientific contributions.
Niro — one package: the niro CLI plus the Niro MCP server (code intelligence for AI coding assistants).
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol, vector search, git-based knowledge graphs, cloud backup. Never lose context again.