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

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

A modular monolith MCP server connecting multiple providers (Redash, PostgreSQL, GitHub) with unified permission, security, and auditing, enabling secure data access and tool execution.

Provides Claude with a persistent, auditable memory stored as markdown and YAML files in a private GitHub repo. Enables reading, appending, organizing, and messaging between agent conversations through MCP tools.

Serves a git-backed folder of Markdown notes over MCP so AI agents can search, read, write, move and delete them, with every write recorded as a git commit attributed to the calling client. Supports full-text section search with snippets, wikilinks and typed relations, LFS-backed searchable attachments, optimistic concurrency for multiple agents, and per-client token or OAuth 2.1 access.

A git-backed per-repo memory layer for Claude Code, enabling persistent, version-controlled storage and retrieval of memories to build a self-evolving skill.

Manages knowledge graph data synchronized with GitHub repositories, enabling remote storage and collaboration of memory entities, relationships, and observations.

Bridges disconnected AI sessions with persistent project memory and automatic session handoff, integrating GitHub workflows for context-aware development.

Enables AI coding assistants to persist context across sessions by saving, searching, checkpointing, restoring, and organizing decisions, progress, files, and Git-related state.

Enables Git repository operations and real-time monitoring via MCP tools, with support for WebSocket events, authentication, and observability.

Enables deterministic behavioral regression review of pull-request diffs by checking changed code against approved incident-derived contracts. It exposes read-only tools to assess diffs and pull requests, list and fetch contracts, and report outcomes over stdio without mutating repositories.

Enables Codex and Claude to share Git-backed Markdown memories, assistant handoffs, and reusable skills through read-only and write-enabled MCP endpoints, while owners review revisions, conflicts, and deletion requests in a private GUI.

Enables Claude to read and write GitHub repositories and persist structured memory entries—prompt, plan, and result—on Turso, with search, timeline, retrieval, and soft deletion while redacting secrets.

A persistent, PostgreSQL-backed repository management system and semantic memory MCP server that stores the entire Git DAG natively in PostgreSQL with temporally-decayed semantic vector embeddings for AI IDEs.

Local-first memory layer for AI coding agents — Markdown as source of truth, MCP server + CLI, human-reviewed capture, team knowledge via git PRs

Enables AI coding agents to persist structured long-term memory (gotchas, architecture, API notes) in a .context folder and sync across devices and agents via Git.

Lets agents read a GitHub repository's live issues through read-only tools for listing, filtering, fetching details with comments and cross-references, searching, and exploring labels and milestones, with transparent pagination and provenance notes.

Universal Git-powered persistent memory, context rules & native MCP server for AI coding agents. Prevents context amnesia with stateful workflows, Git Notes, and cross-model review gates across Claude, OpenAI, Gemini & DeepSeek in Cursor, Claude Code & VS Code.

Enables Codex to delegate routine repository exploration, implementation, refactors, tests, and fixes to DeepSeek Harness in isolated Git worktrees, returning compact results and patches for review while keeping the main workspace protected.

MCP server for exploring GitHub public data. It provides tools to fetch user profiles, list top repositories, and calculate language usage statistics, which AI agents can invoke dynamically.

A technical interviewer that ingests GitHub repos, teaches you your own code, and conducts mock interviews with persistent memory of your weak spots.

Quilt gives every AI agent line-level authorship in a shared Git checkout, so multiple agents work in one repo, and each commits only its own lines, with symbol-level claims that block collisions before any bytes change.

Repository-native protocol and MCP server for coordinating work items, documentation, changelogs, and project memory between humans and AI agents, using Markdown files in a Git repository as the canonical data source.

Git-native decision memory for coding agents: stores constraints, ruled-out alternatives, and warnings as git trailers and refs/notes, returning only records still in force for the file path being edited.

Enables detection and resolution of Git merge conflicts in repositories through MCP, providing tools to identify conflicting files and assist with conflict resolution workflows.

Open-source team memory layer for AI coding agents. Markdown-in-git, user/team/org hierarchy, MCP. Apache-2.0.

Persistent memory for AI coding agents. Builds semantic memory from git history and codebase, searchable via MCP tools.

Bridges Gitee, China's largest code hosting platform, to MCP for exploring trending repos, searching users/repos, and translating Chinese content with a local LLM.

A token-efficient MCP server for exploring GitHub repositories using tree-sitter AST parsing to extract symbol signatures and summaries. It enables users to search and retrieve specific code components while significantly reducing token consumption compared to raw file dumps.

Makes git commits on behalf of AI by appending "(aider)" to the committer's name, allowing tracking of AI contributions in your codebase.

A unified MCP server that combines GitHub, local Git, Slack, web fetching, persistent memory, and filesystem tools into a single configuration entry, with dangerous capabilities like shell execution disabled by default.