"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

An MCP server that grants image recognition to text-only models like DeepSeek by forwarding images to vision models and returning text descriptions. Supports clipboard, pasted session images, and batch folder image recognition.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

Enables AI coding agents like Claude Code or Codex to delegate tasks to a DeepSeek Harness subagent with its own context window, providing tools for task delegation, result waiting, continuation, and supervision with sandboxed execution.

Enables a Codex/GPT conversation to request independent second opinions from DeepSeek through a local stdio MCP tool and receive provider-reported model metadata for response or synthesis.

MCP server for DeepSeek AI models (Chat + Reasoner). Supports multi-turn sessions, model fallback with circuit breaker, function calling, thinking mode, JSON output, multimodal input, and cost tracking.

Generates or reviews Git unified diffs via DeepSeek API with local path validation, enabling secure patch suggestions without scanning repositories.

Enables users to describe their LLM fine-tuning job once and get the cheapest, fastest, and most balanced GPU options across a dozen cloud providers in seconds.

A Model Context Protocol (MCP) server that provides access to DeepSeek-R1's reasoning capabilities, allowing non-reasoning models to generate better responses with enhanced thinking.

This MCP server gives pure-text LLM agents vision capabilities by integrating the free GLM-4.6V-Flash visual model, enabling image, video, and file understanding through standard MCP tools.

Provides vision capabilities to text-only LLMs by acting as a cloud vision adapter layer, enabling image understanding and OCR text extraction through a single MCP tool.

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.

MCP server providing persistent memory for AI applications, enabling Claude to store and recall memories with hybrid search and knowledge graph.

Enables any MCP-compatible AI coding client such as Claude Code, Codex, or Cursor to run web searches and fetch pages as Markdown through a self-built search engine, with per-day and per-month spend caps, prompt-injection fencing on retrieved content, and local usage/cost reporting. Search results can be filtered by site, language, and date, and repeated page fetches within a short window are not billed twice.

Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely.

A vendor-agnostic cognitive persistence layer for AI agents. Eliminate the "repetition tax" by transporting your context, preferences, and history across sessions. Features an auto-adaptation engine that syncs global instructions to ensure operational cohesion and optimize token usage across any LLM or multi-agent workflow.

Basic Memory is a knowledge management system that allows you to build a persistent semantic graph from conversations with AI assistants. All knowledge is stored in standard Markdown files on your computer, giving you full control and ownership of your data. Integrates directly with Obsidan.md

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

Persistent knowledge graph MCP server with SQLite backend, offering graph traversal, fuzzy search, and temporal queries for entities and relations. It serves as a drop-in replacement for the npm mcp-server-memory with enhanced capabilities.

A zero-dependency, file-based persistent memory system for AI agents with tiered memory, Ebbinghaus decay, and keyword retrieval.

An MCP server providing long-term memory for LLMs via hybrid search (FTS5 + vector) stored in SQLite, with time-decay scoring and support for multiple AI assistants.

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 layer for MCP agents with hybrid search, file ingestion, and GDPR compliance.

Enables MCP clients to run web searches and fetch web page contents through DeepSeek's Search and Fetch APIs, returning structured JSON results with configurable tool names and multiple transport options.

Enables integration of DeepSeek's language models with MCP-compatible applications, offering features like chat completion, custom model selection, and parameter control for enhancing language-based interactions.

Provides persistent memory for Claude with hierarchical categorization, cross-corpus recall, session journals, and customizable persona, enabling memory continuity across sessions.

Adds image understanding to text-only coding agents via two tools: describe_image for detailed descriptions and describe_ui for structured UI reports.

Two-layer memory for AI agents. Episodes compress into identity. The only MCP memory server with an immune system. Patterns earn permanence through evidence, false knowledge gets caught and demoted, and stale information fades — so your agent's memory gets smarter over time, not just bigger. Zero dependencies. 5 tools. Works with any MCP client.

Provides AI agents with persistent, long-term memory via OKF-formatted markdown and SQLite indexing, enabling stateful storage, retrieval, and search across sessions.

MCP server for persistent, cross-session, local-first memory for AI agents, storing memories as Markdown files with SQLite indexing for hybrid search.

Provides persistent memory with semantic search for MCP-based AI agents, enabling them to store and recall information across sessions using vector embeddings.