Find keyword mentions in AI model outputs from ChatGPT and Google AI. Returns mention context and sources.
MIT
180,147 tools. Last updated 2026-06-04 11:33
"A system like ChatGPT with memory to provide past query context in conversations" matching MCP tools:
- List memory stores with summaries to identify the agent's persistent memory, attach it at session start to preserve history and context. Paginate via next_page.MIT
- Assembles a complete system prompt with database schema, object classes, properties, codelists, spatial context, and optional SQL examples and query guidelines.Apache 2.0
- Execute SELECT SQL queries on Hologres databases using serverless computing resources to handle memory-intensive operations and avoid query memory limitations.Apache 2.0
- Store memory observations with tags, importance, context, and optional auto-expiration. Persist AI agent knowledge with configurable TTL.MIT
- Find past experiences that match your current task by searching episodic memory with vector similarity.MIT
Matching MCP Servers
- -license-quality-maintenanceEnables AI assistants to maintain persistent conversations and context between sessions through automated saving and global installation across projects. Provides zero-configuration memory persistence with automatic conversation history preservation.Last updated
- Flicense-qualityCmaintenanceProvides an intelligent, graph-based memory system for LLM agents using the Zettelkasten principle, enabling automatic note construction, semantic linking, memory evolution, and autonomous graph maintenance with background optimization processes.Last updated9
Matching MCP Connectors
An interactive portfolio built for AI conversations. Browse work, services, and book calls.
Stop re-explaining yourself to Agents. Give it the right context, right when needed.
- Assembles a smart context block from stored memories, returning a pre-formatted string for system prompt injection. Enables persistent memory across tools.MIT
- Retrieve relevant memory patterns from past interactions to understand user context. Use natural language queries to recall previous knowledge about a user.MIT
- Store information with optional context, importance score, and tags for later retrieval and analysis across conversations.MIT
- Search system JSON files by query to find matching documents with relevance scores for enhanced reasoning workflows.MIT
- Retrieves relevant context for a query, limited by token budget, to inject memory efficiently.MIT
- Add new observations to an existing entity in a knowledge graph memory. Append facts like 'Lives in Seattle' to a person or project, with optional context and location settings.MIT
- Find relevant past conversations and indexed content quickly. Apply filters for project, date, source, and sort order. Results prioritize current session and project.MIT
- Search within related memories using a specific memory as context root to find solutions in relevant knowledge without external leakage.
- Search past conversations and memories using time filters and categories to retrieve previous decisions, preferences, or facts from your workspace.AGPL 3.0
- Export memories from Project Tessera to migrate knowledge to other AI platforms like ChatGPT or Gemini using supported formats.AGPL 3.0
- Search past memory notes by similarity to a new visual goal, ranking results by query overlap with title, intent, tags, and body. Retrieve ranked hits with vault paths, scores, and matched terms to reuse prior recipes and parameters.MIT
- Retrieve past NotebookLM queries and answers to review research sessions, find specific information, and track notebook usage with enterprise-grade security.MIT
- Send messages to a deployed solution and continue multi-turn conversations. Auto-routes to the correct skill; pass actor_id to maintain context.MIT
- Query inline bots like @gif or @bing within a chat context and retrieve a structured result list with a queryId for further selection.MIT