A previous release had provenance metadata, but this release does not. View details.
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.
Documentation • Quick Start • Features • Security
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
parlor init # Interactive setup wizard
Or create ~/.parlor/config.yaml manually:
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
parlor --version # Show version
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.
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
parlor chat --model gpt-4o "hello" # Override model
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
Metadata
Release files for parlor 0.15.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Loss of provenance
These files do not have provenance metadata, despite files in a prior release including this data.
We recommend further investigation before installing these files. View details.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| parlor-0.15.1.tar.gz | 703.4 kB | Without provenance | Details for parlor-0.15.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| parlor-0.15.1-py3-none-any.whl | Python 3 | none | any | Details for parlor-0.15.1-py3-none-any.whl |
Total release size: 1.4 MB
Release files / parlor-0.15.1.tar.gz
Loss of provenance
This file belongs to a release without provenance metadata, despite a prior release including this data.
We recommend further investigation before installing this file. View details.
| Download URL | parlor-0.15.1.tar.gz |
|---|---|
| Size | 703.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
01cd1a7f31948ee38eb3928381992bc976294dfcd67cea40202e374961255842
|
|
BLAKE2b-256 checksum How to use checksums |
18efc63237a160006030aeff71b8ce1da748d15283f6d8b9145e6474db22f6cf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / parlor-0.15.1-py3-none-any.whl
Loss of provenance
This file belongs to a release without provenance metadata, despite a prior release including this data.
We recommend further investigation before installing this file. View details.
| Download URL | parlor-0.15.1-py3-none-any.whl |
|---|---|
| Size | 746.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8d8a04c1b2b540a69bb23a3a8c54ef59177243f92ba18f5947a1d96c293409e4
|
|
BLAKE2b-256 checksum How to use checksums |
cc9065ceff06a657b8c5acab26c98c57d926488e2db55e2f99a4486196fdfaff
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Security for parlor 0.15.1
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.
Loss of provenance
A previous release of these files had provenance metadata, but this release does not.
While this could reflect a routine change by the project maintainers, it may also indicate that the release files have been compromised.
Release comparison
- Removed 0.9.1 2 files With provenance
- Added 0.15.1 2 files Without provenance
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.
To learn more about protecting yourself from malicious actors, visit our package security documentation.