Skip to main content

manyminds

Status: pre-alpha. This release only claims the package name. The manyminds command prints its version and a short notice; the application is not built yet. See PLAN.md for what is coming.

What it will be

A Python app that helps you check claims you find on the web. It runs on your own machine with your own OpenRouter API key, and its only interface is a local browser app.

You paste a piece of text. The app proposes leads: specific threads that could be researched to see whether the text is supported by evidence. You edit that list, and one research agent per lead runs in parallel and writes a focused report of quoted, linked evidence. You can read finished reports while others are still running, then chat about the evidence and start more research.

manyminds gathers evidence for you to judge. It does not issue verdicts on what is true.

Where your text goes

Orchestration is local; inference is not. Text you paste is sent to OpenRouter, to the model providers you choose, and to the web search engine used for research. Your API key is kept in your operating system's keychain. The app listens on localhost only.

Install

uvx manyminds

or

uv tool install manyminds

Development

Everything runs through uv:

uv sync
uv run pytest
uv run ruff check
uv run ruff format --check
uv run mypy

Development follows strict test-driven development; the rules are in CLAUDE.md.

Licence

MIT. See LICENSE.

Metadata

Release files for manyminds 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for manyminds 0.0.1
File Size Uploaded Provenance Actions
manyminds-0.0.1.tar.gz 3.8 kB Without provenance Details for manyminds-0.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for manyminds 0.0.1
File Interpreter ABI Platform Actions
manyminds-0.0.1-py3-none-any.whl Python 3 none any Details for manyminds-0.0.1-py3-none-any.whl

Total release size: 8.4 kB

Release files / manyminds-0.0.1.tar.gz

Download URL manyminds-0.0.1.tar.gz
Size 3.8 kB
Tags Source
SHA-256 checksum
How to use checksums
82b5b6a5ff4fd453574cb6c4d153f97a42829b3853d0289b7e5d9ee674a4fe04
BLAKE2b-256 checksum
How to use checksums
ead81f1fee424d7d71edd71284a64cc84e4c937cea045f8ae0a0fa6f508c2032
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / manyminds-0.0.1-py3-none-any.whl

Download URL manyminds-0.0.1-py3-none-any.whl
Size 4.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c6660329980fd4260d8b0a66aaacbe37c05cc7c2742425d6d5be1382c38f5b3d
BLAKE2b-256 checksum
How to use checksums
da046d0263b503994420a8fe6e72cfd46e9bcf53f6f7f263712b71d741722c52
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for manyminds 0.0.1

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.

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.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page