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
- Install dependencies:
pip install -e .[dev] - Install hooks:
pre-commit install - Start services:
docker compose up -d - Run
aurora-se initto bootstrap configs - See
docs/quickstart.mdfor 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.
1 maintainer
Metadata
1 maintainer
Release files for aurora-se 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| aurora_se-0.1.0.tar.gz | 1.6 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| aurora_se-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.7 MB
Release files / aurora_se-0.1.0.tar.gz
| Download URL | aurora_se-0.1.0.tar.gz |
|---|---|
| Size | 1.6 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7d298d690775dbafde807bda5582c818f2e668a0fbe75d8f9f3fb341c94c667f
|
|
BLAKE2b-256 checksum How to use checksums |
2d08591057270f6ad31dc771330893913f7637b3baae786e0dedc676c187f816
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.7
|
Release files / aurora_se-0.1.0-py3-none-any.whl
| Download URL | aurora_se-0.1.0-py3-none-any.whl |
|---|---|
| Size | 112.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b4821d331cf30cb08e6a7105ba207288c9d5cc1a7da56c17e959e94bc961cbc1
|
|
BLAKE2b-256 checksum How to use checksums |
f061f9540ba3dadd1fb5ac425d341ce31ec6552edb55f0392be06a54bf4588bf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.7
|
Security for aurora-se 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
