Metadata-Version: 2.4
Name: cascade-lattice
Version: 0.1.2
Summary: Universal AI provenance layer — cryptographic receipts for every LLM call
Author: Jeff Towers
License-Expression: MIT
Project-URL: Homepage, https://huggingface.co/spaces/tostido/Cascade
Project-URL: Documentation, https://huggingface.co/spaces/tostido/Cascade
Project-URL: Repository, https://huggingface.co/spaces/tostido/Cascade
Project-URL: Issues, https://huggingface.co/spaces/tostido/Cascade/discussions
Keywords: ai,llm,provenance,observability,tracing,openai,anthropic,langchain,mlops,cryptographic,receipts,ipfs,web3,monitoring,neural-networks,machine-learning,deep-learning
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: System :: Monitoring
Classifier: Topic :: Software Development :: Debuggers
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: aiohttp>=3.8.0
Requires-Dist: rich>=12.0.0
Provides-Extra: openai
Requires-Dist: openai>=1.0.0; extra == "openai"
Provides-Extra: anthropic
Requires-Dist: anthropic>=0.18.0; extra == "anthropic"
Provides-Extra: huggingface
Requires-Dist: transformers>=4.30.0; extra == "huggingface"
Requires-Dist: huggingface-hub>=0.20.0; extra == "huggingface"
Provides-Extra: ollama
Requires-Dist: ollama>=0.1.0; extra == "ollama"
Provides-Extra: litellm
Requires-Dist: litellm>=1.0.0; extra == "litellm"
Provides-Extra: langchain
Requires-Dist: langchain>=0.1.0; extra == "langchain"
Provides-Extra: ipfs
Requires-Dist: ipfshttpclient>=0.8.0; extra == "ipfs"
Provides-Extra: all
Requires-Dist: openai>=1.0.0; extra == "all"
Requires-Dist: anthropic>=0.18.0; extra == "all"
Requires-Dist: transformers>=4.30.0; extra == "all"
Requires-Dist: huggingface-hub>=0.20.0; extra == "all"
Requires-Dist: ollama>=0.1.0; extra == "all"
Requires-Dist: litellm>=1.0.0; extra == "all"
Requires-Dist: langchain>=0.1.0; extra == "all"
Requires-Dist: networkx>=2.6; extra == "all"
Requires-Dist: datasets>=2.14.0; extra == "all"
Requires-Dist: sentence-transformers>=2.2.0; extra == "all"
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: pytest-cov>=4.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: black>=23.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"
Requires-Dist: mypy>=1.0; extra == "dev"
Dynamic: license-file

# cascade-lattice

**Universal AI provenance layer. Cryptographic receipts for every LLM call.**

[![PyPI](https://img.shields.io/pypi/v/cascade-lattice.svg)](https://pypi.org/project/cascade-lattice/)
[![Python](https://img.shields.io/pypi/pyversions/cascade-lattice.svg)](https://pypi.org/project/cascade-lattice/)
[![License](https://img.shields.io/badge/license-MIT-green.svg)](https://huggingface.co/spaces/tostido/Cascade/blob/main/LICENSE)

---

## What is CASCADE?

CASCADE creates tamper-proof receipts for AI interactions. Every LLM call—input, output, model, timestamp—gets hashed into a cryptographic chain anchored to IPFS.

**One line of code. Every AI call recorded. Forever.**

```python
import cascade
cascade.init()

# That's it. Every LLM call now emits a receipt.
```

---

## Installation

```bash
pip install cascade-lattice
```

With provider support:
```bash
pip install cascade-lattice[openai]      # OpenAI support
pip install cascade-lattice[anthropic]   # Anthropic support
pip install cascade-lattice[all]         # All providers
```

---

## Quick Start

### Option 1: Auto-Patch (Zero Code Changes)

```python
import cascade
cascade.init()

# Now use any LLM library normally
import openai
client = openai.OpenAI()
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)
# ✓ Receipt automatically emitted to lattice
```

### Option 2: Proxy Mode (Any Language)

```bash
# Terminal 1: Start the proxy
cascade proxy

# Terminal 2: Point your app at it
export OPENAI_BASE_URL=http://localhost:7777/v1
export ANTHROPIC_BASE_URL=http://localhost:7777/anthropic

# Run any app - Go, Rust, JavaScript, Python, anything
./your_agent
# ✓ All AI calls observed through proxy
```

### Option 3: Manual Observation

```python
from cascade import sdk_observe

sdk_observe(
    model_id="openai/gpt-4",
    input_data="What is 2+2?",
    output_data="4",
    metrics={"tokens": 10}
)
```

---

## How It Works

```
┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│   Your App  │────▶│   CASCADE   │────▶│   OpenAI    │
│             │◀────│   (observe) │◀────│   Anthropic │
└─────────────┘     └──────┬──────┘     │   etc...    │
                           │            └─────────────┘
                           ▼
                    ┌─────────────┐
                    │   Lattice   │
                    │  (receipts) │
                    └──────┬──────┘
                           │
                           ▼
                    ┌─────────────┐
                    │    IPFS     │
                    │ (permanent) │
                    └─────────────┘
```

Every observation creates a **receipt** containing:
- Input hash
- Output hash  
- Model identifier
- Timestamp
- Merkle proof linking to genesis

Receipts are stored locally in the **lattice** and can be pinned to IPFS for permanent, decentralized storage.

---

## Supported Providers

| Provider | Auto-Patch | Proxy |
|----------|------------|-------|
| OpenAI | ✓ | ✓ |
| Anthropic | ✓ | ✓ |
| HuggingFace | ✓ | ✓ |
| Ollama | ✓ | ✓ |
| LiteLLM | ✓ | ✓ |
| Cohere | - | ✓ |
| Mistral | - | ✓ |
| Any OpenAI-compatible | - | ✓ |

---

## CLI Commands

```bash
# Start proxy server
cascade proxy [--port 7777]

# View lattice stats
cascade stats

# List recent observations
cascade list [--limit 10]

# Pin observation to IPFS
cascade pin <merkle_root>
```

---

## Genesis

CASCADE is anchored to a permanent genesis block on IPFS:

```
Genesis Root: 89f940c1a4b7aa65
CID: bafkreidixjlzdat7ex72foi6vm3vnskhzguovxj6ondbazrqks7v6ahmei
```

Every receipt chains back to genesis. The lattice grows. Discovery is reading the chain.

---

## Why CASCADE?

- **Provenance**: Prove what model produced what output
- **Auditability**: Cryptographic trail of all AI interactions  
- **Compliance**: Meet emerging AI transparency requirements
- **Research**: Build datasets from cumulative observations
- **Trust**: Tamper-proof records for AI accountability

---

## Links

- [Live Demo](https://huggingface.co/spaces/tostido/Cascade)
- [Source Code](https://huggingface.co/spaces/tostido/Cascade/tree/main)
- [Genesis on IPFS](https://storacha.link/ipfs/bafkreidixjlzdat7ex72foi6vm3vnskhzguovxj6ondbazrqks7v6ahmei) *(MessagePack binary - machine-readable)*

---

## License

MIT License

---

*"even still, i grow, and yet, I grow still"*
