Find keyword mentions in AI model outputs from ChatGPT and Google AI. Returns mention context and sources.
MIT
614,309 tools. Updated 2026-09-26 19:38
"A system like ChatGPT with memory to provide past query context in conversations" matching MCP tools:
- Search shared long-term memory for user preferences, past decisions, and project context before answering, returning results ranked by relevance.MIT
- Reconstruct memory state at a past timestamp to run semantic search queries. Understand how agent context evolved over time.MIT
- Execute SELECT SQL queries on Hologres databases using serverless computing resources to handle memory-intensive operations and avoid query memory limitations.Apache 2.0
- Assembles a complete system prompt with database schema, object classes, properties, codelists, spatial context, and optional SQL examples and query guidelines.Apache 2.0
- Retrieve all saved sessions with names, entry counts, and timestamps to discover context from previous conversations.Business Source 1.1
Matching MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to list and read existing ChatGPT conversations and send messages into them, retrieving the assistant's reply through ChatGPT Desktop's native bridge. It works without cookies, UI automation, or an OpenAI API key.1Apache 2.0
- AlicenseNot gradedqualityBmaintenanceA local MCP bridge that lets ChatGPT chat mode operate the user's own computer, running project, file, and shell tasks through a local executor and returning progress and results to the conversation. It also coordinates Codex sessions (persistent or one-off) and other agent CLIs as sub-agents.MIT
Matching MCP Connectors
Words-in-context vocabulary practice questions with distractor explanations.
Medigami patient tools: rates, markups, denial codes, deadlines, overturn rates, procedure codes
- Create a memory context for conversations, returning summary metadata by default; retrieve plaintext content only with a valid audit-logged reason.Apache 2.0
- Retrieve summaries of past user conversations, including key topics, decisions, and action items, to pick up where you left off.MIT
- Store observations as persistent memories with optional tags, importance levels, context, and auto-expiration to manage AI agent memory.MIT
- Search and synthesize your past AI conversations to recall decisions, patterns, and preferences. Use date filters and parallel queries to retrieve relevant context.MIT
- Store preferences, decisions, and project details in persistent memory for future AI conversations. Organize with buckets for easy recall.MIT
- Search past Hermes conversations using full-text queries, session IDs, or message contexts. Browse recent sessions to recall previous work.MIT
- Find related conversations across all AI platforms using semantic clustering. Search natural language to discover forgotten discussions from ChatGPT, Claude, and Gemini.MIT
- Search and retrieve relevant memories from Mnemexa to answer questions about user preferences, past decisions, project context, and prior conversations.ISC
- Store memory observations with optional tags, importance ratings, context, and automatic expiration to manage and organize information effectively.MIT
- List past memory evaluation runs to monitor changes in memory quality. Optionally set a limit on the number of evaluations returned.MIT
- Retrieve relevant memory patterns from past interactions to understand user context. Use natural language queries to recall previous knowledge about a user.MIT
- Retrieve the current system date and time in multiple formats to provide temporal context for billing operations and workflows.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
- Search all past Claude Code conversations using keyword queries, project filters, or date ranges. List session history, view stats, and read full transcripts to recover context from previous work.MIT
- Construct a formatted memory block for system prompts. Selects relevant memories by semantic query or top memories by frequency, truncates to fit token budget, and returns a single string in markdown, XML, JSON, or plain text.MIT