Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Finsliparn

БесплатноНе проверен

Transforms single-attempt coding into a multi-attempt, test-validated refinement loop by running your actual test suite and feeding failures back to the LLM as

GitHubEmbed

Описание

Transforms single-attempt coding into a multi-attempt, test-validated refinement loop by running your actual test suite and feeding failures back to the LLM as structured directives.

README

Swedish: the honer — from finslipa, meaning "to hone", "to fine-tune" or "to put the finishing touches on."

Finsliparn is a Bun-native MCP Server and Claude Code Plugin that transforms single-attempt coding into a multi-attempt, test-validated refinement loop. It adapts the philosophy of Poetiq's ARC-AGI solver to general software development.


🎯 Core Value Proposition

LLMs often generate code that looks correct but fails in edge cases. Finsliparn solves this by enforcing a Refinement Loop:

  1. Iterate: The LLM implements a solution.
  2. Validate: Finsliparn runs your actual test suite (not just a syntax check).
  3. Feedback: Test failures are fed back to the LLM as structured, actionable directives.
  4. Select: If multiple attempts are made, the best one (highest score, lowest complexity) is selected.

"Test results are the objective truth—not diffs, not prompts, not opinions."


🏗 Architecture

Finsliparn uses a Filesystem-as-IPC architecture to support multiple AI platforms with a single core engine.

graph LR
    subgraph "AI Client"
        Claude[Claude Code]
        Copilot[GitHub Copilot]
    end

    subgraph "Finsliparn Core"
        MCP[MCP Server]
        Directive[Directive.md]
        Tests[Test Runner]
    end

    Claude --"Hooks"--> MCP
    Copilot --"Agent"--> MCP
    MCP --"Writes"--> Directive
    Directive --"Reads"--> Claude
    Directive --"Reads"--> Copilot
    MCP --"Executes"--> Tests
  • directive.md: The single source of truth. It tells the LLM exactly what to do next (e.g., "Fix failing tests in src/foo.ts").
  • Git Worktrees: Every iteration runs in an isolated worktree, ensuring your main branch stays clean until a solution is verified.

🚀 Getting Started

Prerequisites

  • Bun v1.3+
  • Git

Installation (Development)

# Clone the repository
git clone https://github.com/jgabor/finsliparn.git
cd finsliparn

# Install dependencies
bun install

# Link the plugin (for Claude Code)
# (Coming soon)

📖 Documentation


🛠 Usage

With Claude Code

# Start a refinement session
/finslipa Implement a fibonacci function in src/math.ts

Finsliparn will automatically intercept your edits, run tests, and guide you until the tests pass.

With GitHub Copilot CLI

# Start the agent
copilot run --agent finsliparn "Implement a fibonacci function"

The agent will autonomously loop through the directive.md instructions until completion.


Author

Jonathan Gabor

from github.com/jgabor/finsliparn

Установка Finsliparn

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/jgabor/finsliparn

FAQ

Finsliparn MCP бесплатный?

Да, Finsliparn MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Finsliparn?

Нет, Finsliparn работает без API-ключей и переменных окружения.

Finsliparn — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить Finsliparn в Claude Desktop, Claude Code или Cursor?

Открой Finsliparn на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare Finsliparn with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории ai