Metadata-Version: 2.4
Name: antaris-flame
Version: 2.0.0
Summary: Antaris Flame — memory, safety, and context for AI agent bots (5,000 memory tier)
Author-email: Antaris Analytics <moro@antarisanalytics.ai>
License: Apache-2.0
Project-URL: Homepage, https://antarisanalytics.ai
Project-URL: Repository, https://github.com/Antaris-Analytics-LLC/antaris-flame
Project-URL: Documentation, https://docs.antarisanalytics.ai
Keywords: ai,memory,agent,flame,llm,safety
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
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 :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: antaris-memory~=4.0
Requires-Dist: antaris-guard~=4.0
Requires-Dist: antaris-context~=4.0
Provides-Extra: semantic
Requires-Dist: sentence-transformers>=2.2.0; extra == "semantic"
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: pytest-xdist; extra == "dev"
Dynamic: license-file

# antaris-flame

**Memory, safety, and context for AI agent bots — Flame tier (5,000 memories)**

[![PyPI version](https://badge.fury.io/py/antaris-flame.svg)](https://pypi.org/project/antaris-flame/)
[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
[![Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)

antaris-flame is the mid-tier of the Antaris bot runtime — bundling persistent memory, safety screening, and context optimization in a single install. Capped at **5,000 memories** for production deployments.

## What's Included

- **antaris-memory** — BM25 + co-occurrence semantic search, audit logging, memory decay, recovery
- **antaris-guard** — Prompt injection detection, PII redaction, rate limiting, compliance templates
- **antaris-context** — Token budget management, context window optimization, compression strategies

## Tier Limits

| Tier | Memory Cap | Package |
|------|-----------|---------|
| Spark | 500 memories | `antaris-spark` |
| **Flame** | 5,000 memories | `antaris-flame` |
| Forge | 25,000 memories | `antaris-forge` |

## Quick Start

```python
from antaris_memory import MemorySystem
from antaris_guard import PromptGuard
from antaris_context import ContextManager

# Memory — capped at 5,000 entries by default
mem = MemorySystem("./workspace")
mem.load()
mem.ingest("User prefers concise answers", source="conversation")
results = mem.search("user preferences")

# Guard
guard = PromptGuard()
if not guard.is_safe(user_input):
    return  # block before reaching model

# Context
ctx = ContextManager(total_budget=8000)
ctx.set_memory_client(mem)
ctx.add_content("conversation", messages)
ctx.optimize_context()
```

## GitHub

<https://github.com/Antaris-Analytics-LLC/antaris-flame>

## License

Apache 2.0 — see [LICENSE](LICENSE)
