Skip to main content

Private local control plane for AI-assisted research operations

Project description

Kansei

Kansei is a private local control plane for AI-assisted research operations. It keeps project registries, provider configuration, dashboards, knowledge, and MCP access in one local instance while leaving each target project in its own repository or remote environment.

uv run kansei init .tmp/kansei-demo --git --with-codex --with-mcp
uv run kansei version

The CLI is the source of truth for local state changes. MCP tools and Codex instructions are an interface over that state, with read and plan operations kept separate from apply operations.

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

kansei-0.1.0.tar.gz (116.4 kB view details)

Uploaded Source

Built Distribution

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

kansei-0.1.0-py3-none-any.whl (51.8 kB view details)

Uploaded Python 3

File details

Details for the file kansei-0.1.0.tar.gz.

File metadata

  • Download URL: kansei-0.1.0.tar.gz
  • Upload date:
  • Size: 116.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for kansei-0.1.0.tar.gz
Algorithm Hash digest
SHA256 3c95dd77223ec246cba1071c1f50a1e3943f49c01c13575a01d2b4f705150f81
MD5 6bd178db24e08ad4534af92fdbbafff6
BLAKE2b-256 645e7c96a8de2ae2455dc0459f3f9996346591a6d8828bf56683231743dc1f87

See more details on using hashes here.

Provenance

The following attestation bundles were made for kansei-0.1.0.tar.gz:

Publisher: publish-pypi.yml on Nkzono99/kansei

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file kansei-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: kansei-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 51.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for kansei-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c589d2111cab8bf511e19855db16cf824abdf5caa18d4c9cf74bdbef2e92e178
MD5 05fbf30de8d4dddad4e6d1f75be33eec
BLAKE2b-256 20c223115b747c73e06e289b72ba4f07c6ba482cac10380121fd35ab0bd94124

See more details on using hashes here.

Provenance

The following attestation bundles were made for kansei-0.1.0-py3-none-any.whl:

Publisher: publish-pypi.yml on Nkzono99/kansei

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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