# LETHE

> LETHE — jesusgarcia9009-lethe-engineering. Use this tool when you need to efficiently manage large outputs from LLMs, saving tokens by offloading and recalling them on demand. LETHE solves the problem of token limits by storing and retrieving outputs as needed, optimizing the use of LLM context. It takes large tool outputs as input and provides recalled outputs on demand, making it ideal for use cases where token conservation is crucial.

Canonical page: https://skillsregistry.net/skills/jesusgarcia9009-lethe-engineering  
JSON: https://api.skillsregistry.net/v1/skills/jesusgarcia9009-lethe-engineering

## Description

Enables offloading large tool outputs from LLM context and recalling them on demand to save tokens.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/byneawmngl)
- **Repository:** <https://github.com/JesusGarcia9009/lethe-engineering>

## 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": "jesusgarcia9009-lethe-engineering"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jesusgarcia9009-lethe-engineering` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jesusgarcia9009-lethe-engineering/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