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

Enables using DeepSeek models as a small, cheap supervised worker from any MCP-compatible client, providing fast flash and deep reasoning tools for bounded tasks.

Local MCP server that provides DeepSeek-powered code review, file analysis, and consultation tools for coding agents, enabling read-only analysis with minimal token overhead.

Enables delegating bounded development tasks to a locally installed DSH harness and returns a structured handoff covering file writes, command exit codes, missing checks, blockers, and evidence.

This MCP server exposes DeepSeek V4 to Codex as a single tool, enabling GPT Sol to delegate coding subtasks to DeepSeek for cheap 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.

A server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine to tackle complex reasoning tasks.

Enables Claude Code to delegate tasks such as planning, coding, reviews, debugging, tests, and docs to a cheaper model that works autonomously in a project-sandboxed loop with file, search, and test tools, returning a compact report to save tokens. Routing rules, approval-gated deletes and commands, per-task model/effort settings, and backups keep the user in control of what gets handed off.

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

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.

Enables Codex to delegate separable work to DeepSeek Flash/Pro agents through start, continue, status, and cancel tools, while Codex retains tool execution, authorization, and final verification.

Connects MCP clients to DeepSeek API, including DeepSeek-R1 reasoning with visible chain-of-thought. Provides four tools: generate, chat, reason, and list models.

Lets any MCP-capable AI coding harness route code reviews and codebase questions through DeepSeek's web chat, exposing review, ask, and status tools with read-only repository access by default.

Exposes the full DeepSeek API surface — chat, reasoning, fill-in-the-middle, prefix completion, function calling, JSON mode, logprobs, streaming, multi-turn sessions, and local file analysis — to any MCP client, alongside a raw passthrough tool for arbitrary endpoints and parameters. Defaults are deliberately uncapped, with opt-in environment variables for token limits, output truncation, and filesystem confinement.

Provides code generation and completion capabilities using the DeepSeek API, with support for tool chaining and cost optimization.

A local HTTP proxy and MCP server that translates 'developer' role messages to 'system' for DeepSeek API, enabling Android Studio AI plugins to work without errors.

Provides tools to check DeepSeek account balance, list available models, and estimate costs from token usage, without proxying API calls.

Auto-captured, auto-recalled, path-scoped memory for AI coding agents and teams.

Local, searchable project memory for AI coding agents. Markdown source of truth, MCP interface, safe structured updates

Long-term memory for AI coding agents, stored as a tree of plain local files. Agents search it before answering and save what lasts; changed facts are kept as history and flagged as outdated.

Project Memory stores decisions, evidence, outcomes and reviewed lessons in local SQLite. Assistants retrieve bounded context through three MCP tools. People follow and plan work in a live workspace with an overview, sprint board, decision history, readable documents, skills and project maps. Offline exports remain available.

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.

MCP server for managing project memory in AGENTS.md. Allows agents to record and remove durable facts using save/forget tools.

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

MCP server that wraps DeepSeek's AI capabilities into standard MCP tools, supporting three authentication modes including free web-based usage without API keys.

Failure Memory provides AI coding agents with a shared local memory of failures, enabling them to record, recall, and learn from mistakes across sessions.

Persistent memory and automatic git snapshots for Claude Code, capturing decisions, patterns, and architecture across sessions.

MCP server that lets AI agents discover, inspect, install, and run DeepSeek Harness plugins via MCP, bridging the gap between the MCP protocol and Cordis-based plugin bundles.

Enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine for intricate multi-step reasoning tasks with precision and efficiency.