Metadata-Version: 2.4
Name: agentrank
Version: 0.1.3
Summary: Temporal-aware embedding model for AI agent memory retrieval. The first embedder that understands WHEN memories happened.
Author-email: Vrushket More <vrushket2604@gmail.com>
License: Apache-2.0
Project-URL: Homepage, https://github.com/vmore2/AgentRank-base
Project-URL: Documentation, https://huggingface.co/vrushket/agentrank-base
Project-URL: Repository, https://github.com/vmore2/AgentRank-base
Project-URL: Issues, https://github.com/vmore2/AgentRank-base/issues
Keywords: embeddings,transformers,ai-agents,memory,retrieval,rag,vector-search,temporal,llm
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: torch>=1.9.0
Requires-Dist: transformers>=4.20.0
Requires-Dist: huggingface-hub>=0.14.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: black>=22.0.0; extra == "dev"
Requires-Dist: flake8>=4.0.0; extra == "dev"

# 🧠 AgentRank

**Temporal-aware embeddings for AI agent memory retrieval.**

[![PyPI version](https://badge.fury.io/py/agentrank.svg)](https://badge.fury.io/py/agentrank)
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![HuggingFace](https://img.shields.io/badge/🤗-Models-yellow)](https://huggingface.co/vrushket)

---

## The Problem

Standard embedding models (OpenAI, Cohere, MiniLM) treat **"yesterday"** and **"6 months ago"** identically. For AI agents with long-term memory, this breaks temporal reasoning completely.

**AgentRank solves this** with embeddings that understand:
- ⏰ **When** memories happened (temporal awareness)
- 📂 **What type** of memory it is (episodic, semantic, procedural)
- ⚡ **21% better retrieval** on agent memory benchmarks

---

## Installation

```bash
pip install agentrank
```

---

## Quick Start

```python
from agentrank import AgentRankEmbedder

# Load model
model = AgentRankEmbedder.from_pretrained("vrushket/agentrank-base")

# Encode with temporal context
embeddings = model.encode(
    texts=["User prefers Python for backend development"],
    temporal_info=[7],        # 7 days ago
    memory_types=["semantic"] # It's a preference
)

# Use embeddings for retrieval
print(embeddings.shape)  # [1, 768]
```

---

## Model Family

| Model | Type | Params | Use Case | HuggingFace |
|-------|------|--------|----------|-------------|
| **AgentRank-Base** | Embedder | 149M | Best quality retrieval | [vrushket/agentrank-base](https://huggingface.co/vrushket/agentrank-base) |
| **AgentRank-Small** | Embedder | 33M | Fast inference | [vrushket/agentrank-small](https://huggingface.co/vrushket/agentrank-small) |
| **AgentRank-Reranker** | Cross-encoder | 149M | Accurate reranking | [vrushket/agentrank-reranker](https://huggingface.co/vrushket/agentrank-reranker) |

---

## Two-Stage Retrieval Pipeline

For best results, use a two-stage pipeline:

```python
from agentrank import AgentRankEmbedder
from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch

# Stage 1: Fast retrieval with embedder
embedder = AgentRankEmbedder.from_pretrained("vrushket/agentrank-base")
query_embedding = embedder.encode(["What's my Python preference?"])
# ... search vector DB → get top-50 candidates ...

# Stage 2: Accurate reranking with cross-encoder
reranker = AutoModelForSequenceClassification.from_pretrained("vrushket/agentrank-reranker")
tokenizer = AutoTokenizer.from_pretrained("vrushket/agentrank-reranker")

def rerank(query, candidates, top_k=10):
    scored = []
    for memory in candidates:
        inputs = tokenizer(query, memory, return_tensors="pt", truncation=True)
        with torch.no_grad():
            score = torch.sigmoid(reranker(**inputs).logits).item()
        scored.append((score, memory))
    return sorted(scored, reverse=True)[:top_k]

top_10 = rerank("What's my Python preference?", top_50_candidates)
```

---

## Benchmarks

| Model | MRR | Recall@1 | Recall@5 | NDCG@10 |
|-------|-----|----------|----------|---------|
| **AgentRank-Base** | **0.6496** | **0.4440** | **99.6%** | 0.6786 |
| **AgentRank-Small** | 0.6375 | 0.4460 | 97.4% | 0.6797 |
| MPNet-base-v2 | 0.5351 | 0.3660 | 79.6% | 0.6335 |
| MiniLM-L6-v2 | 0.5297 | 0.3720 | 75.2% | 0.6370 |

**+22% MRR improvement** over baseline embedding models.

| Reranker | Validation Accuracy | Val Loss |
|----------|---------------------|----------|
| **AgentRank-Reranker** | **89.11%** | 0.2554 |

---

## Key Features

### Temporal Embeddings
10 learnable time buckets encode recency:
- Today/Yesterday, This Week, This Month, Last Quarter, etc.
- Model learns what "recent" means in context

### Memory Type Embeddings
Distinguish between:
- **Episodic**: Events ("We discussed Python yesterday")
- **Semantic**: Facts/preferences ("User likes Python")
- **Procedural**: Instructions ("To deploy, run npm build")

### Architecture
- Base: ModernBERT-base / MiniLM
- Temporal + Type embeddings added (scaled by 0.1)
- Trained on 500K synthetic agent memory samples
- Hard negative mining with 7 negative types

---

## Works Great With

**[CogniHive](https://pypi.org/project/cognihive/)** — Multi-agent memory with "who knows what" routing

```bash
pip install cognihive
```

**Together:** CogniHive routes questions to the right agent, AgentRank retrieves the right memories.

---

## Links

- **GitHub**: [github.com/vmore2/AgentRank-base](https://github.com/vmore2/AgentRank-base)
- **HuggingFace**: [huggingface.co/vrushket](https://huggingface.co/vrushket)
  - [agentrank-base](https://huggingface.co/vrushket/agentrank-base)
  - [agentrank-small](https://huggingface.co/vrushket/agentrank-small)
  - [agentrank-reranker](https://huggingface.co/vrushket/agentrank-reranker)
- **CogniHive**: [pypi.org/project/cognihive](https://pypi.org/project/cognihive/)

---

## Contact

- **Author**: Vrushket More
- **Email**: vrushket2604@gmail.com
- **LinkedIn**: [linkedin.com/in/vrushket-more-07b38b25b](https://www.linkedin.com/in/vrushket-more-07b38b25b/)
- **Issues**: [GitHub Issues](https://github.com/vmore2/AgentRank-base/issues)

---

## License

Apache 2.0 — Free for commercial use.
