fidelis

fidelis is a plugin for Claude Code from hermes-labs-ai/fidelis. Its manifest loads nothing; the 1 skill, 1 MCP server it bundles cost 63 tokens per session together, scanned A, original, Apache-2.0.

A local-first memory add-on for an AI coding agent. It provides tools to recall and query stored information, check memory health, orient the agent, and save decisions for later use.

In plain words
What is it for?
Use it to recall relevant information before answering and store important decisions after work is completed.
Why use it?
It helps the agent use earlier project context instead of repeatedly starting without it.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit Use it to recall relevant information before answering and store important decisions after work is completed.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add hermes-labs-ai/fidelis
/plugin install fidelis
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/hermes-labs-ai/fidelis

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fidelis

README.md
[![agentmods](https://agentmods.dev/badge/plugins/hermes-labs-ai/fidelis/claude-plugin/github.svg)](https://agentmods.dev/plugins/hermes-labs-ai/fidelis/claude-plugin)
Your own site
<a href="https://agentmods.dev/plugins/hermes-labs-ai/fidelis/claude-plugin"><img src="https://agentmods.dev/badge/plugins/hermes-labs-ai/fidelis/claude-plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fidelis

Your own site · 80×15
<a href="https://agentmods.dev/plugins/hermes-labs-ai/fidelis/claude-plugin"><img src="https://agentmods.dev/badge/plugins/hermes-labs-ai/fidelis/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 1 MCP server cost 63 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

fidelis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude-plugin/.claude-plugin/plugin.json · 24 lines

What it actually says

{
  "name": "fidelis",
  "displayName": "fidelis",
  "description": "Local agent memory with verbatim records, correction history, and time-aware recall. Provides fidelis_recall, fidelis_store, fidelis_correct, fidelis_get, fidelis_recent, and fidelis_health.",
  "version": "0.3.0rc1",
  "author": {
    "name": "Hermes Labs",
    "email": "[email protected]",
    "url": "https://github.com/hermes-labs-ai"
  },
  "homepage": "https://github.com/hermes-labs-ai/fidelis",
  "repository": "https://github.com/hermes-labs-ai/fidelis",
  "license": "Apache-2.0",
  "keywords": [
    "memory",
    "agent-memory",
    "mcp",
    "retrieval",
    "rag",
    "local-first",
    "hermes-labs"
  ]
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 63 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago Changed 144eb7285610
  2. 8d ago Changed · +12 lines b2e185c7f8c6
  3. 9d ago Changed 993365aba2b0
  4. 11d ago First seen · 12 lines scan A 5ddfd5149fda

Subscribe to this mod's changes

fidelis is a plugin published in the GitHub repository hermes-labs-ai/fidelis (23 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.

Related

Other plugins, from other repositories

memsearch

Automatic semantic memory for Claude Code — remembers what you worked on across sessions.

zilliztech/memsearch · not measured

inspeximus

Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.

DanceNitra/inspeximus · not measured

deja

deja-vu memory for Gemini CLI: the coding sessions already on your disk — Gemini CLI, Claude Code, Codex, Cursor and thirty-one more — searchable and recalled, including work from before it was installed.

vshulcz/deja-vu · not measured

ownmem

Git-native project memory for AI coding agents, with deterministic local recall, evidence gates, and layered delivery that quotes, points, or abstains.

grpcer/ownmem · not measured

knowl

Persistent memory for Claude Code. Facts are typed, sourced, and retired when they change, so a query returns the current answer rather than every answer it has ever held. Local SQLite in your repository — no API key, nothing uploaded.

dat999zx/knowl · not measured

emem

Shared, verifiable memory for AI agents. Two layers, one trust surface. Earth-scale fact substrate: every patch of ground gets a 64-bit address (cell64, about 9.55 m), and every measurement at that cell is a signed fact keyed by (cell, band, tslot), ed25519-signed by the responder over the blake3 of its canonical CBOR.

Vortx-AI/emem · not measured