"Cursor Not Losing Memory or State" matching MCP servers:

Enables remote control of the Cursor AI agent via chat platforms like GitHub Issues or Telegram, allowing users to start sessions and receive summaries and prompts in a chat thread.

Scoped, low-latency persistent memory layer for AI agents, Cursor, and Claude Code over Model Context Protocol with sub-50ms hybrid search.

Enables MCP clients like Claude Code and Codex to delegate coding tasks to Cursor's CLI agent, which implements changes in the workspace and returns clean, structured results for review.

A FastMCP server for Cursor platform APIs enabling spend guardrails, cloud agent monitoring, and inter-agent inbox messaging.

Hosted memory for AI agents that learns from outcomes, with shared rooms. One key across Claude, Cursor & ChatGPT.

Hand a project over — to your next session, to Cursor/Codex/Gemini, to your successor — with the reasons attached. Local-first memory MCP for coding agents: decisions re-injected before the agent acts, drift detection across every project you run. One SQLite file, nothing leaves your machine.

Monitors your Cursor usage and provides a conserve flag to the agent, helping you manage request quota by batching questions, preferring defaults, and cutting unnecessary confirmations.

A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep

MARM MCP provides persistent memory and structured session context beneath any AI tool, so your agents learn, remember, and collaborate across all your workflows.

Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware and secret-safe.

Persistent, local memory for AI coding agents that learns how you work, not just what you said. Supports Claude Code, Codex CLI, Cursor, and any MCP client.

Enables cost-effective repository analysis, code search, file editing, and task planning by wrapping the cursor-agent CLI through focused tools. Reduces token usage by offloading heavy thinking tasks from Claude to specialized operations with configurable output formats.

Enables AI agents to persist and restore checkpoint state, supporting crash recovery and replay for LangGraph-based workflows.

A persistent, project-scoped memory layer for AI coding agents, providing 39 tools for capturing, searching, deduplicating, relating, and maintaining memory records across long-running coding sessions.

Persistent long-term memory for MCP clients. Store and recall semantic facts, episodic events, and task state with vector-based relevance search. Write what matters, retrieve what's needed — memory that persists across sessions and agents, backed by a local SQLite store with optional embeddings for meaning-based lookup. Simple file-based storage, no external services required.

Enables AI agents to commit stateful workflow checkpoints by calculating state hashes and rollback points through the Model Context Protocol. It provides deterministic, dependency-free checkpoint management for autonomous agent execution.

A long-term memory system built for AI Agents. Agent wakes up already knowing who he is, not querying "who am I?" every session. Every turn calling back accurate memory context. Achieving accurate memory hits while also preventing memory from expanding at scale. No compression, no forgetting.

A local MCP server that gives AI assistants persistent long-term memory using a biological neural architecture with cortex, synapses, and hippocampus.

Embedded, local-first agent memory: facts extracted into a per-namespace SQLite file (vec0 + FTS5) with hybrid retrieval and point-in-time (time-travel) queries. ADD-only history over stdio — no server process, no cloud dependency.

Local memory for coding agents that can refuse, not only recall. A rule carrying a machine-checkable proof blocks the matching command before it runs, while prose-only rules can warn but never block.