Fidelis Memory MCP Server

Your agent can forget a summary. Fidelis brings back the note. Local memory for Codex, Claude Code, and other agents: save text across sessions and retrieve the original passage when it matters.

People who work with rag, retrieval and hermes labs and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-29 · ★ 23 · #61 OF 321 MAINTAINED MEMORY · VERIFIED 2026-09-30

Apache-2.0 · Python servers · how we verify → /methodology

01 · Install Fidelis Memory

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

claude mcp add hermes-labs-ai-fidelis -- uvx fidelis-memory

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "hermes-labs-ai-fidelis": {
      "command": "uvx",
      "args": [
        "fidelis-memory"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license Apache-2.0 - declared in the repository

pypi package fidelis-memory - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.hermes-labs-ai is GitHub-verified and matches the repo owner

03 · What Fidelis Memory can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.2.0 · 2026-09-20

Why this release · Fidelis 0.2.0 makes local service startup safer around existing installs and lets protocol and health inspection succeed before a local Ollama store is available. · Who it is for · Local-first macOS…

v0.1.0 · 2026-09-13

Promote Fidelis Memory from the 0.0.x sequence to its first minor release. · The supported product contract is local-first, verbatim memory retrieval for · Codex, Claude Code, GitHub Copilot CLI, Gemini CLI, and…

v0.0.97 · 2026-09-12

Release the Gemini CLI extension: v0.0.96 was tagged before · gemini-extension.json landed, so the bare-URL install resolved the latest · GitHub release and failed with "Configuration file not found". v0.0.97 is the…

04 · Who maintains Fidelis Memory

Fidelis Memory is maintained by hermes-labs-ai. We track 2 MCP servers from hermes-labs-ai - 2 actively maintained, 25 combined GitHub stars, oldest repo from Mar 2026. Full record: all servers from hermes-labs-ai.

  1. Hermes Prime Read-only stdio MCP server for a versioned convention card in Claude Code. ★ 2

05 · Facts

category
memory - ranked #61 of 321 actively-maintained memory servers as of 2026-09-30.
release cadence
7 releases in the last 90 days (latest 2026-09-20)
registry
io.github.hermes-labs-ai/fidelis-memory (active, first published 2026-09-02 · 6 versions)
packages
pypi:fidelis-memory

06 · Fidelis Memory FAQ

What is Fidelis Memory?

Your agent can forget a summary. Fidelis brings back the note. Local memory for Codex, Claude Code, and other agents: save text across sessions and retrieve the original passage when it matters.

Is Fidelis Memory still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-29 and it shipped 7 releases in the last 90 days. We re-verify nightly.

How do I install Fidelis Memory?

Run `uvx fidelis-memory`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does Fidelis Memory run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Fidelis Memory

Pairs well with

Servers that cover what Fidelis Memory doesn't - only shown when the pairing reason fits the companion.

  1. Server Filesystem → filesystem companion filesystem · ★ 39,168
  2. Pdf MCP → filesystem companion filesystem · ★ 145