This release is a pre-release and may not be stable for production use.
title: RACHEL (rachel-proxy) emoji: 🎲 colorFrom: red colorTo: blue sdk: docker app_port: 7860 pinned: false
RACHEL (rachel-proxy)
RACHEL (Rpg Agent CHat Evaluation Loop) is a FastAPI proxy that sits between JanitorAI (or any OpenAI-compatible client) and LLM completion providers (OpenRouter, OpenAI, Google Gemini, DeepSeek), running request payloads through a stateful LangGraph agent with a secure V8 code sandbox containing dice and contest RNG helper functions.
- Why Use RACHEL? — Core features, benefits, assumptions, and design philosophies.
- All About Sessions — How session IDs are resolved and managed via API endpoints.
- Road to Multi-Tenant — Multi-tenant cloud roadmap and architecture.
🚀 Quickstarts
RACHEL is deployed as a single-tenant desktop application.
🖥️ One-Click Desktop Launchers
Download the release zip for your operating system from Releases and launch with one click:
- Windows: Unzip and double-click
launch.bat. - macOS: Unzip and double-click
launch.command. (If blocked by Gatekeeper, runxattr -cr launch.commandin Terminal). - Linux: Unzip and double-click
launch.sh.
💻 Developer Setup
If you are cloning this repository for local development:
- Install Python dependencies:
pip install -e ".[dev]"
- Build Frontend Assets (Required):
The compiled static frontend directory (
src/rachel/static/) is git-ignored. You MUST build the frontend before launching the backend server:python scripts/build_frontend.py --target local
- Run the Server:
uvicorn rachel.proxy:app --reload --host 0.0.0.0 --port 8000
- Run Tests with Coverage:
Ensure your code changes pass all tests and maintain at least 75% coverage:
pytest --cov=src --cov-fail-under=75
Initial Setup & LLM Provider Credentials
Once the proxy starts, open the Admin Console in your browser at http://localhost:8000:
- Proxy API Key: Enter the local admin key (printed to console logs or saved in
data/proxy.key). - Provider Credentials: Configure your preferred provider (OpenRouter BYOK / PKCE, OpenAI, Google Gemini, or DeepSeek) directly in the Provider Credentials card.
- Select your Active Provider and save settings.
Release files for rachel-proxy 0.1.0b4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| rachel_proxy-0.1.0b4.tar.gz | 299.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| rachel_proxy-0.1.0b4-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 377.8 kB
Release files / rachel_proxy-0.1.0b4.tar.gz
| Download URL | rachel_proxy-0.1.0b4.tar.gz |
|---|---|
| Size | 299.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ef81a9674a601d0ab11b6ae12d89c53d3744c132503731720324b6ae99aafba6
|
|
BLAKE2b-256 checksum How to use checksums |
6df379730c3d954e29ddaeabd8e369355e7ae3f0256290224ecbc68a5220d491
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.
Transparency logRelease files / rachel_proxy-0.1.0b4-py3-none-any.whl
| Download URL | rachel_proxy-0.1.0b4-py3-none-any.whl |
|---|---|
| Size | 77.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c142b63de6b5be4b28af98a333f02ca480dc83f11b0944f5ca596079690b2590
|
|
BLAKE2b-256 checksum How to use checksums |
87a4404d34cd96d531938789927b7a4afbf8cbf7cbec13f0ccce361e06c5d7a2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.
Transparency log