Log inSubmit server
Fidelis Memory logo

Fidelis Memory

Stores local notes and lets MCP-compatible agents retrieve, quote, correct, and inspect them across sessions.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Fidelis Memory

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "fidelis-memory": {
      "command": "uvx",
      "args": [
        "--from",
        "fidelis-memory",
        "fidelis-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

uvx --from fidelis-memory fidelis-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 2d ago.

Overview

Fidelis Memory MCP server connects local agents to a machine-local store for saving and retrieving Markdown or text notes. It preserves stored wording on verbatim paths, while vector and optional hybrid retrieval help locate relevant passages. A local Ollama service supplies embeddings, and a background Fidelis service handles storage and retrieval after initialization. Reach for it when agents need durable, single-machine memory with access to the original note rather than only a generated summary.

Use cases

  • Recall exact conditions from prior engineering notes
  • Store local Markdown memory across agent sessions
  • Correct outdated memories while retaining history
  • Inspect retrieved notes and their validity status

Key features

  • Local Markdown and text note storage
  • Vector and hybrid retrieval
  • Verbatim passage recall
  • Memory corrections with historical status
  • MCP tools for recall, storage, fetching, and inspection
  • Ollama-based local embeddings

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

6/6 checks healthy over the last 41d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 4d ago via OSV.dev · fidelis-memory (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars24Stargazers on the source repository.
Last commit4d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Fidelis Memory works

What the Fidelis Memory MCP server does

Fidelis Memory MCP server gives compatible agents access to notes stored on the local machine. It can save Markdown and plain-text content, retrieve relevant passages, apply corrections that supersede earlier records, fetch stored material, and inspect memory state. The verbatim write and retrieval paths are intended for cases where exact wording, conditions, or warnings must remain available to later sessions.

The default MCP recall path uses vector search. An explicit hybrid mode combines keyword and vector results. Its zero_llm tier does not use a generative model to rewrite the retrieved text, although local embeddings still require Ollama. Optional extraction and model-assisted routes may transform or filter inputs, so they are less suitable when preservation of the supplied wording is the priority.

How it works

fidelis init starts a per-user background service: launchd on macOS or a user systemd service on Linux. The service runs fidelis-server at login and stores data in ~/.cogito/store by default. A watcher sends files to that service for ingestion; it also records processed file paths in ~/.fidelis/watched.json.

After a note is available locally, an MCP client can call Fidelis tools when it determines that memory is relevant. Installing the connection does not force recall on every turn. Retrieved content is still subject to being outdated or incorrect, and the model provider handling the agent’s response may receive that content.

Setup and configuration

The documented quick start supports Python 3.10 or newer on macOS or Ubuntu. Create a virtual environment, install fidelis-memory[hybrid], run fidelis init, and make Ollama available with the nomic-embed-text model. Ingest a notes directory with fidelis watch <directory> --once, then test retrieval with fidelis recall-hybrid.

Connect an agent with fidelis mcp install --client codex, or use fidelis mcp install for Claude Code. Restart the client before using the memory tools. Keep the virtual environment after initialization because the background service uses it. fidelis health can help diagnose retrieval problems, including a missing Ollama embedding model.

Uninstalling the macOS service removes its launchd configuration but not stored data. On Linux, disable and remove the installed user unit before reloading systemd. Deleting ~/.cogito/store removes all Fidelis data, while deleting the watched-file record only removes ingestion history.

Tools and capabilities

The MCP connection exposes tools for:

  • Recalling relevant stored memories.
  • Storing new memory content.
  • Correcting an existing memory while retaining its history.
  • Fetching stored content.
  • Inspecting memory and validity information.

Fidelis Memory MCP server is suited to development notes, operational conditions, decisions, and other local context that agents may need in later sessions. The project also documents connections for Cursor and Gemini CLI, in addition to Codex and Claude Code.

Limitations and notes

The 0.3.0rc1 release is a single-machine pre-release, not a hosted team memory service. Ollama and a local embedding model are required for the documented retrieval setup; no model API key is required in that path. Retrieval benchmarks described by the project measure whether material was found, not whether an agent’s final answer was accurate.

The store is shared across everything saved through Fidelis, so removing it is a destructive action. Notes can become stale, and optional model-assisted processing can change or filter input. Use a verbatim path when preserving the original passage matters.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Fidelis Memory

Fidelis Memory is an MCP server that connects local agents to a machine-local memory store for Markdown and text notes. Its main tools recall, store, correct, fetch, and inspect memories, allowing agents to retrieve saved passages across sessions while preserving original wording on verbatim paths.

Install the Python package, run `fidelis init`, and then use `fidelis mcp install` for Claude Code or `fidelis mcp install --client codex` for Codex. The documented setup also requires Python 3.10+, Ollama, and the `nomic-embed-text` model.

Yes, Cursor is listed among the supported client connections. Install the local Fidelis service and use the client-specific MCP setup described in the project’s full reference, then restart Cursor before using the memory tools.

No API key is required for the documented local setup. Ollama runs locally and provides the `nomic-embed-text` embedding model used by retrieval.

By default, Fidelis stores notes in `~/.cogito/store`. Watched-file ingestion records are kept separately in `~/.fidelis/watched.json`, and deleting the store removes all Fidelis data on that machine.

Related MCP servers

All in Knowledge & Memory All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewFidelis Memory AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/fidelis-memory?style=directory)](https://allmcps.com/mcp/fidelis-memory)
HTML Embed
<a href="https://allmcps.com/mcp/fidelis-memory"><img src="https://allmcps.com/api/badge/fidelis-memory?style=directory" alt="Fidelis Memory on AllMCPs" /></a>