# fidelis

> Use this tool when you need to efficiently store and retrieve information for AI agents without incurring retrieval taxes, ideal for applications requiring fast and fidelity-preserving memory. It solves problems related to slow and costly memory retrieval, providing a local-first solution with high recall accuracy. Input your data for secure and rapid storage, and retrieve it with minimal latency and $0/query retrieval cost.

Canonical page: https://skillsregistry.net/skills/hermes-labs-ai-fidelis  
JSON: https://api.skillsregistry.net/v1/skills/hermes-labs-ai-fidelis

## Description

Agent memory without the retrieval tax. Fidelity-preserving memory for Claude Code and AI agents — local-first, fast, and with no LLM in the default retrieval path. 83.2% R@1 on LongMemEval-S, $0/query retrieval.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-05-02

## Source

- **Source listing:** [GitHub](https://github.com/hermes-labs-ai/fidelis)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "hermes-labs-ai-fidelis"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hermes-labs-ai-fidelis` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hermes-labs-ai-fidelis/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt