# maker-rs

> maker-rs — zircote-maker-rs. Use this tool when you need to execute Large Language Models (LLMs) with zero-error guarantees, particularly in long-horizon AI agent tasks. The maker-rs library and server utilize SPRT voting for mathematically-grounded error correction, providing a reliable solution for high-stakes applications. Ideal for research experiments and tasks requiring precise LLM outputs, maker-rs offers a robust interface for inputting tasks and receiving error-corrected outputs.

Canonical page: https://skillsregistry.net/skills/zircote-maker-rs  
JSON: https://api.skillsregistry.net/v1/skills/zircote-maker-rs

## Description

Zero-error LLM execution via SPRT voting. Rust library and MCP server implementing the MAKER algorithm for mathematically-grounded error correction in long-horizon AI agent tasks. Research experiment based on arXiv:2511.09030

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/zircote/maker-rs)

## 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": "zircote-maker-rs"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zircote-maker-rs` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zircote-maker-rs/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