"Hermes" matching MCP servers:

Transforms internal Hermes documents (PRDs, RFCs, specs) into agent tools for relevance search, metadata, and full content retrieval, plus a skill to cross-check specs against code.

Bridges Hermes Agent to the Hermes Intelligence Platform API, enabling tools to read/write learning loop data (context, feedback, signals, memory, etc.) via stdio.

Enables persistent project memory for Hermes Agent by storing and retrieving wiki, code, and learning layers locally, with tools to recall, learn, retire, and ingest information beyond the context window.

Enables capturing, searching, and organizing Obsidian notes from Telegram via Hermes Agent (MCP).

Provides a single localhost MCP endpoint aggregating Context Mode, a curated allowlist of Hermes web/browser/vision/skill tools, and Hermes/Honcho memory without patching upstream sources.

MCP server bridging Hermes Agent and Buzz's Nostr-based event log, enabling cross-session memory, channel collaboration, messaging, reactions, and workflow automation.

Enables saving URLs, local files, plain text, and platform content (WeChat, X, YouTube, PDF, images, audio/video, Telegram) as structured Markdown knowledge cards in an Obsidian vault, with optional AI-powered classification and tagging.

Connects Claude to a Nextcloud-hosted Obsidian vault, enabling team members to search, read, list, and get status of notes using existing seats with no API cost.

A local enhanced memory system with self-evolution capabilities, enabling automatic skill creation, periodic memory maintenance, and trajectory training for reinforcement learning.

Provides an isolated MCP bridge giving Codex Hermes-style long-term memory, checkpoints, and optional tools, while keeping Hermes and Codex data read-only and requiring human approval for skill proposals.

Enables interaction with GLPI (ITSM) through 71 tools covering tickets, assets, problems, changes, knowledge base, projects, users, and more, using SSE or stdio transport.

A cross-AI-agent local task context sharing MCP server that allows clients like Codex, Claude Code, Hermes, and VS Code to read and write the same task state, enabling task tracking and context distillation.

Cross-tool memory for AI that enables deterministic recall-first memory across multiple tools (Claude Code, Desktop, ChatGPT, etc.) with honest abstention when it doesn't know.

Persistent memory layer for MCP-compatible AI agents. Implements save/recall/search over a local SQLite session store via 14 MCP tools. Auto-loads relevant context at session start. No cloud dependency. Works with Claude, Cursor, Codex, Hermes Agent. Free (50 sessions) / Pro ($8/mo).

Versioned document vault system for MCP-compatible AI agents. Organizes reference knowledge (specs, contracts, rules) into per-project vaults with 36 MCP tools for inject, search, link, and version operations. Local SQLite backend. Works with Claude, Cursor, Codex, Hermes Agent. Free (3 vaults) / Pro ($9/mo).

A local-first shared memory layer for MCP-aware agents like Claude, Codex, and Hermes, enabling persistent memory across chats and clients via Markdown files and SQLite FTS.

A local shared-memory MCP server for Claude, Codex, Hermes, and other MCP-aware agents, providing a durable memory layer with Markdown files and SQLite fact store.

Open, local-first engram memory for AI agents: read, correct, and delete what your agent remembers. Works across Claude Code, Hermes, OpenClaw, and Cursor over MCP.

MCP server for Obsidian vaults — multi-brain manager with templates, persistent registry, search, CRUD, frontmatter, wikilinks and context bundling. Works with Hermes Agent and Claude Code simultaneously.

Enables users to expose temporal architectural memory, privacy sanitization, and local test-runner capabilities as MCP tools so clients like Claude Desktop, Cursor, and Hermes Agent can query decisions, sanitize prompts, and verify code changes.