Stiahnuť FylloCode 0.15.5 pre Windows

In this new era, the work that really needs our attention is no longer repetitive coding, but higher-level business understanding and architecture design. The future workflow I have in mind is: understand the business → think through the architecture → write a Proposal → review the Proposal → let the Agent implement it automatically, then move on to the next Proposal. That thinking led me to build FylloCode — a step from Vibe Coding toward Agentic Coding.

How FylloCode Solves It FylloCode enforces a structured workflow that separates thinking from doing: ┌──────────┐ ┌────────────────┐ ┌───────────┐ ┌───────────┐ │ Task │ ──→ │ Chat/Proposal │ ──→ │ Apply │ ──→ │ Archive │ │ │ │ │ │ │ │ │ │ What to │ │ Agent explores │ │ Agent │ │ Specs │ │ work on │ │ codebase and │ │ implements│ │ updated, │ │ │ │ writes a plan │ │ the plan │ │ change │ │ │ │ │ │ │ │ recorded │ │ │ │ ➜ YOU REVIEW │ │ │ │ │ └──────────┘ └────────────────┘ └───────────┘ └───────────┘ Task — Pick a task from your local list or synced from platforms like Yunxiao. One click sends it to Chat. Chat / Proposal — The Agent explores your codebase, asks clarifying questions, and produces a structured proposal (what to change, which files, acceptance criteria). The Agent is prohibited from writing code in this stage. You review, edit, and approve the proposal before anything else happens. Apply — A fresh Agent session implements the approved proposal task-by-task. It reads only the proposal artifacts — not the Chat history — so every decision must be captured in writing, not left in context-window memory. Archive — Specs are updated, the change is recorded with full traceability. Your project's knowledge base grows with every shipped change. Why Separating Thinking from Execution Matters Most Coding Agents understand a task and write code in the same session. Any misunderstanding becomes code directly, and code is expensive to review. FylloCode physically separates understanding from execution. Misunderstandings can only become proposal text — and text is cheap to review. A 2-minute proposal review catches problems that would take 20 minutes to find in a diff.

Features

Agent Protocol (ACP) FylloCode connects to any Coding Agent through ACP (Agent Client Protocol). Claude Code, Codex, or any ACP-compatible agent — one protocol, one interface, without juggling a pile of terminal windows. There are currently 35 agents available in the ACP Registry, with support for parallel chats and parallel Proposal Apply runs.

Popis od výrobcu (angličtina)

Popis projektu na GitHube: “FylloCode 是一个开源桌面应用，把 Claude Code、Codex 等本地 Coding Agent 接进项目工作流。派任务、审方案、追溯每一次改动，积累下来的规范和结论，换一个 Agent 也能继承。”

Výhody / Nevýhody

V skratke: FylloCode je program pre Windows s otvoreným zdrojovým kódom (kategória „AI asistenti a LLM“); zostavenia: 64-bit. Správcovia ho môžu nasadiť bezobslužne.

Je stiahnutie programu FylloCode bezpečné?

• Súbor sa sťahuje z domény výrobcu (github.com)
• Odkaz na stiahnutie používa HTTPS
• Hash SHA256 je zverejnený – súbor sa dá overiť: CB4C8074DE71A6D651D169A3AD097496A5CE777E61ED0F8DAC735D5A95F318B6 · Otvoriť správu VirusTotal pre tento hash
• Odkaz zatiaľ nebol overený
• Otvorený zdrojový kód
• ExeAtlas inštalátory neukladá, nebalí ani nemení

Súvisiaci návod: Ako vo Windows overiť hash SHA256 súboru

Súvisiaci návod: Ako používať winget: inštalácia a aktualizácia programov

Informácie

Výrobca

Fio

Kategória

AI asistenti a LLM

Licencia

AGPL-3.0

Cena

Zadarmo

Zdrojový kód

github.com/Fioooooooo/FylloCode

Programovací jazyk

TypeScript

Požiadavky

Windows 11 / 10

Architektúra

64-bit

Inštalátor

EXE (NSIS)

Verzia

0.15.5

Dátum vydania

24. augusta 2026

Pridané do katalógu

1. júna 2026

Verzií v katalógu

21

Hviezdičky na GitHube

28

Forky na GitHube

4

Web

github.com

ID winget

Fioooooooo.FylloCode

Hodnotenia a recenzie

Zatiaľ žiadne recenzie. Hodnotenie môžete pridať ako prví.

• 
  Claude Code2.1.302AI asistenti a LLM · Anthropic PBC
  Proprietárna67,1 tis. ↓
• 
  Codex CLI0.161.0AI asistenti a LLM · OpenAI, Inc.
  Open source16,6 tis. ↓
• 
  oh-my-pi18.12.6AI asistenti a LLM · Can Bölük
  Open source654 ↓
• 
  ChatGPT1.1.0AI asistenti a LLM · lencx
  Open source17,1 tis. ↓
• 
  GPT4All3.10.0AI asistenti a LLM · Nomic
  Open source8,7 tis. ↓
• 
  Jan0.8.7AI asistenti a LLM · Jan
  Open source3,3 tis. ↓
• 
  OpenWork0.18.62AI asistenti a LLM · differentai
  Open source333 ↓
• 
  WSL Manager2.5.0.0AI asistenti a LLM · Bostrot
  Open source14 tis. ↓

Táto stránka v ďalších jazykoch

• English
• Türkçe
• Deutsch
• Français
• Español
• Português (Brasil)
• Italiano
• Русский
• Polski
• Nederlands
• 日本語
• 简体中文
• 한국어
• Bahasa Indonesia
• Tiếng Việt
• العربية
• Українська
• Čeština
• Magyar
• Ελληνικά
• Svenska
• Dansk
• Suomi
• Norsk bokmål
• Română
• ไทย
• हिन्दी
• தமிழ்
• বাংলা
• עברית
• فارسی
• اردو
• Català
• Srpski
• Slovenščina
• Eesti
• Bahasa Melayu
• Oʻzbekcha
• Қазақ тілі
• Български
• Hrvatski
• Lietuvių
• Latviešu
• Shqip
• Azərbaycan dili
• ქართული
• Հայերեն
• Беларуская
• Íslenska
• Afrikaans
• Kiswahili
• አማርኛ
• मराठी
• తెలుగు
• ਪੰਜਾਬੀ
• नेपाली
• မြန်မာ
• پښتو
• 繁體中文