It automates the tedious process of manually copying code from AI responses into project files, supports multiple AI providers, and offers diverse interaction modes including interactive chat, clipboard monitoring, and a desktop GUI—all with zero dependencies.
AI chat çıktısını gerçek proje dosyalarına dönüştür. / Turn AI chat output into real project files.
ChatGPT, Claude, Gemini, Qwen, DeepSeek — hangi yapay zeka olursa olsun, markdown çıktısındaki kod bloklarını otomatik algılar, doğru isimler ve klasör yapısıyla diske yazar.
Chisel parses the markdown output that AI assistants produce, detects every file embedded in it, and writes them to disk with the correct names and directory structure.
$ chisel ask "Flask REST API yaz, SQLAlchemy kullan" -o myapi/
chisel v2.0.0 — ask
openai · gpt-4o
──────────────────────────────────────
Here's a complete Flask REST API...
──────────────────────────────────────
Found: 7 files, ~180 lines
1. src/app.py (python) — 45 lines
2. src/models.py (python) — 32 lines
3. src/routes.py (python) — 28 lines
4. config.py (python) — 15 lines
5. requirements.txt — 6 lines
6. .env — 3 lines
7. Dockerfile — 8 lines
7 files created → myapi/
Sıfır bağımlılık — Zero dependencies. Pure Python stdlib.
pip install .
# veya / or
python -m chisel ask "birşeyler yap"
Python 3.8+ gerektirir / required.
chisel ask — Tek Seferlik / One-Shotchisel ask "React dashboard, Tailwind CSS ile" -o dashboard/
chisel ask "React dashboard with Tailwind CSS" -o dashboard/
| Flag | TR | EN |
|---|---|---|
-o DIR | Çıktı klasörü | Output directory |
-f | Üzerine yaz | Overwrite existing |
-n | Sadece listele | Dry run |
--clean | Yorumları temizle | Strip comments |
--local | Yerel model (Ollama) | Use local model |
chisel chat — Sohbet / InteractiveKalıcı konuşma geçmişiyle chat. / Chat session with persistent context.
chisel chat -o myproject/
Komutlar / Commands: /quit /clear /help /model
chisel watch — Pano İzleme / Clipboard WatchPanoyu izler, AI çıktısını yakalar. Qwen, ChatGPT Desktop, tarayıcı — fark etmez.
Monitors clipboard for AI output. Works with any desktop chat app.
chisel watch -o project/ # sor / ask before writing
chisel watch -o project/ --auto # direkt yaz / write immediately
chisel gui — Masaüstü Arayüzü / Desktop AppNative pencere — yapıştır, önizle, yaz. tkinter, ekstra kurulum yok.
Native window — paste,
AI chat çıktısını gerçek proje dosyalarına dönüştür
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.