Metadata-Version: 2.4
Name: aurora-se
Version: 0.1.0
Summary: Autonomous Unified Repo Orchestrator for Reasoning & Adaptation — Self-Editing
Author: AURORA-SE Team
License: Apache-2.0
Keywords: autonomous,ci,devops,pdca,self-editing,swe-bench
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Python: >=3.10
Requires-Dist: docker>=7.1
Requires-Dist: httpx>=0.27
Requires-Dist: matplotlib>=3.9
Requires-Dist: neo4j>=5.17
Requires-Dist: networkx>=3.3
Requires-Dist: opentelemetry-exporter-otlp>=1.25
Requires-Dist: opentelemetry-sdk>=1.25
Requires-Dist: pandas>=2.2
Requires-Dist: pgvector>=0.2.5
Requires-Dist: plotly>=5.24
Requires-Dist: prometheus-client>=0.20
Requires-Dist: psycopg[binary]>=3.2
Requires-Dist: pydantic>=2.8
Requires-Dist: pyyaml>=6.0
Requires-Dist: rich>=13.7
Requires-Dist: semver>=3.0
Requires-Dist: sqlalchemy>=2.0
Requires-Dist: tenacity>=8.3
Requires-Dist: tree-sitter-languages==1.5.0
Requires-Dist: tree-sitter==0.20.4
Requires-Dist: typer[all]>=0.12.3
Provides-Extra: dev
Requires-Dist: mypy>=1.10; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
Requires-Dist: pytest-cov>=5.0; extra == 'dev'
Requires-Dist: pytest>=8.2; extra == 'dev'
Requires-Dist: ruff>=0.6; extra == 'dev'
Requires-Dist: tomli>=2.0; extra == 'dev'
Provides-Extra: learn
Requires-Dist: accelerate>=0.33; extra == 'learn'
Requires-Dist: datasets>=2.19; extra == 'learn'
Requires-Dist: evaluate>=0.4; extra == 'learn'
Requires-Dist: peft>=0.11; extra == 'learn'
Requires-Dist: transformers>=4.45; extra == 'learn'
Description-Content-Type: text/markdown

# AURORA-SE

Autonomous Unified Repo Orchestrator for Reasoning & Adaptation — Self-Editing.

## Overview

AURORA-SE is a self-adapting engineering system that plans, applies, verifies, and learns from code changes across large-scale monorepos. It orchestrates a PDCA loop backed by observability, governance, and compliance controls.

### Tech Stack Highlights
- Planner: DeepSeek-R1 via Ollama with optional GPT-4o-mini/Gemini critic stack
- Repo Intelligence: tree-sitter, pgvector, optional Milvus, Neo4j adapter
- Execution: Docker/Firecracker sandbox, CI profiles (fast/balanced/thorough)
- Observability: OpenTelemetry, Prometheus, Grafana dashboards
- Security: Syft, Grype, TruffleHog, license/policy engine
- Learning: Filtered-SFT with LoRA/PEFT adapters, federated sync
- Evaluation: SWE-Bench Lite/Live nightly/weekly suites

### Getting Started
1. Install dependencies: `pip install -e .[dev]`
2. Install hooks: `pre-commit install`
3. Start services: `docker compose up -d`
4. Run `aurora-se init` to bootstrap configs
5. See `docs/quickstart.md` for workflow details


### Packaging & Release
- Build artifacts: scripts/build_package.sh
- Generate checksums: python scripts/generate_checksums.py dist
- Preview docs locally: mkdocs serve
- See docs/launch/release_checklist.md for full launch steps.
