Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by aurda012 • Search & Retrieval
An MCP server that provides persistent, project-centric memory (short-term, long-term, episodic, and semantic) for developer-focused AI assistants to maintain continuous context across sessions.
Maintain persistent conversational and project state across sessions (messages, milestones, decisions).
Index and semantically search code, files, and snippets using vector embeddings and ANN search.
Unified, high-level tools to initialize/end conversations, check memory health, and retrieve consolidated context from multiple memory subsystems.
DevContext (formerly Cursor10x) is a Model Context Protocol (MCP) server that maintains persistent memory for AI assistants, indexing messages, active files, milestones, decisions, episodes, code structure, and vector embeddings. It uses a Turso database for persistence and advanced vector storage to enable semantic search and approximate nearest neighbor retrieval. The system exposes unified tools for initializing and finalizing conversations, health checks, memory statistics, vector management, and automatic code indexing to boost developer productivity. Benefits include continuous context awareness, relevance-ranked retrieval, and automated code cross-referencing to make agent assistance more accurate and efficient.
Generates a banner containing memory system statistics and status
Checks the health of the memory system and its database
Initializes a conversation by storing the user message, generating a banner, and retrieving context in one operation
Ends a conversation by storing the assistant message, recording a milestone, and logging an episode in one operation
Stores a user message in the short-term memory
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.