Skip to main content

Parlor - a private parlor for AI conversation

Project description

PyPI Version Python 3.10+ Coverage License

Parlor Logo

Parlor

The secure digital speakeasy for AI conversation.

Self-hosted ChatGPT-style web UI and agentic CLI that connects to any OpenAI-compatible API.
Install with pip. Run locally. Own your data.

DocumentationQuick StartFeaturesSecurity

Parlor - Midnight Theme


Why Parlor?

Step inside. Parlor connects to any OpenAI-compatible endpoint --- your company's internal API, OpenAI, Azure, Ollama, LM Studio, or anything else that speaks the OpenAI protocol. Built to OWASP ASVS L1 standards because your conversations deserve real security, not security theater.

One command. No cloud. No telemetry. No compromise.


Quick Start

pip install parlor

Create ~/.parlor/config.yaml:

ai:
  base_url: "https://your-ai-endpoint/v1"
  api_key: "your-api-key"
  model: "gpt-4"
parlor --test       # Verify connection
parlor              # Web UI at http://127.0.0.1:8080
parlor chat         # Terminal CLI

Features

Web UI

Full-featured ChatGPT-style interface with conversations, projects, folders, tags, file attachments, MCP tool integration, prompt queuing, command palette, and four built-in themes.

Midnight Theme Dawn Theme

CLI Chat

An agentic terminal REPL with built-in tools (read/write/edit files, bash, glob, grep), MCP integration, skills system, and Rich markdown rendering. Type while the AI works --- messages queue automatically.

parlor chat                     # Interactive REPL
parlor chat "explain main.py"   # One-shot mode
parlor chat -c                  # Continue last conversation

Shared Core

Both interfaces share the same agent loop, storage layer, and SQLite database. Conversations created in the CLI show up in the web UI, and vice versa.


Security

Layer Implementation
Auth Session tokens, HttpOnly cookies, HMAC-SHA256
CSRF Per-session double-submit tokens
Headers CSP, X-Frame-Options, HSTS, Referrer-Policy
Database Parameterized queries, column allowlists, path validation
Input DOMPurify, UUID validation, filename sanitization
Rate Limiting 120 req/min per IP
CLI Safety Destructive command confirmation, path blocking
MCP Safety SSRF protection, shell metacharacter rejection

Full details in SECURITY.md.


Documentation

For complete documentation including configuration, CLI commands, API reference, themes, MCP setup, skills, and development guides, visit parlor.readthedocs.io.


Development

git clone https://github.com/troylar/parlor.git
cd parlor
pip install -e ".[dev]"
pytest tests/ -v
Backend Python 3.10+, FastAPI, Uvicorn
Frontend Vanilla JS, marked.js, highlight.js, KaTeX
CLI Rich, prompt-toolkit, tiktoken
Database SQLite with FTS5, WAL journaling
AI OpenAI Python SDK (async streaming)
MCP Model Context Protocol SDK (stdio + SSE)

MIT License
Built for people who care about their conversations.
parlor.readthedocs.io

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

parlor-0.14.0.tar.gz (701.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

parlor-0.14.0-py3-none-any.whl (743.3 kB view details)

Uploaded Python 3

File details

Details for the file parlor-0.14.0.tar.gz.

File metadata

  • Download URL: parlor-0.14.0.tar.gz
  • Upload date:
  • Size: 701.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for parlor-0.14.0.tar.gz
Algorithm Hash digest
SHA256 9a3d68036e849a140893e91d694e5d2528a4587aebce98a773806347978b5e10
MD5 b4e6d13012bb5b2f920c95154d8ef983
BLAKE2b-256 8203011a6ecff4bf6beb8cd8d5af1e19564fbce0ff44b5a4e8889c58e973d6fb

See more details on using hashes here.

File details

Details for the file parlor-0.14.0-py3-none-any.whl.

File metadata

  • Download URL: parlor-0.14.0-py3-none-any.whl
  • Upload date:
  • Size: 743.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for parlor-0.14.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b8744201c186097b8b8ebe4bbff256d68679a782725371a7a8246be8a0a4a2ad
MD5 869ae14261fd89330b8712607a00de69
BLAKE2b-256 4bef7b27fd789d255260e0fdbc721eb92adaec042b744cdc1b0b81cd5c345e80

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page