Autonomous dependency upgrade agent
Project description
Patchwork — Autonomous Dependency Surgery
Patchwork is an autonomous agent designed to handle the "grunt work" of dependency upgrades. It doesn't just bump versions; it analyzes changelogs, identifies breaking changes, applies codemods, and verifies the upgrade with your test suite.
🚀 Pitch
Stop wasting hours on v1 → v2 migrations. Let Patchwork perform the surgery.
🛠 Architecture
+-----------+ +-------------------+
| CLI/Web | <---> | Agent Loop |
+-----------+ | (Plan-Patch-Test) |
^ +---------+---------+
| |
+-------+-------+ +-------+-------+
| Episodic Mem | | Semantic Mem |
| (SQLite/FTS) | | (Chroma/Code) |
+---------------+ +---------------+
| |
+-------+-------+ +-------+-------+
| LLM Gateway | <---> | Tools |
| (Anthropic,..) | | (AST, Git,..) |
+---------------+ +---------------+
📦 Installation
pip install patchwork-cli
# or via poetry
poetry add patchwork
⚡ Quickstart
- Initialize Config:
patchwork init - Scan for Upgrades:
patchwork detect - Perform Surgery:
patchwork upgrade pydantic --provider anthropic
⚙️ Configuration
| Provider | Status | Config Key | Env Var |
|---|---|---|---|
| Anthropic | Native | anthropic |
ANTHROPIC_API_KEY |
| Mistral | Native | mistral |
MISTRAL_API_KEY |
| Groq | Native | groq |
GROQ_API_KEY |
| Ollama | Native | ollama |
- |
💰 Cost Transparency
Patchwork logs every token. Run patchwork cost to see exactly what you're spending on your migrations.
📄 License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file patchwork_ai-0.1.0.tar.gz.
File metadata
- Download URL: patchwork_ai-0.1.0.tar.gz
- Upload date:
- Size: 14.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
94f50b2435ff45e75397fec17ddd4a7f1b1079814316dcc70e9fda1662640c1a
|
|
| MD5 |
611c62d790ceca4c5c4e59abc06dde5c
|
|
| BLAKE2b-256 |
3a88fd39faad2e91dd5747366c0355142131b02b3bda9529632d013f844b7a84
|
File details
Details for the file patchwork_ai-0.1.0-py3-none-any.whl.
File metadata
- Download URL: patchwork_ai-0.1.0-py3-none-any.whl
- Upload date:
- Size: 21.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f00ca6bb0ffbe9130a535cb28c1be79995c537db2f27f64f4d839e17aebd70bc
|
|
| MD5 |
b5e783a4d68af454b0111311a1c8d829
|
|
| BLAKE2b-256 |
83440d92137ae3b8f91152647533eab4b1bdc6e036e5a6bedc8ff9b67d22c353
|