Skip to main content

Kairopsis

A local workspace for relative-value research.

Explore market series, compare relationships, and develop investment Ideas with charts and notes you can revisit. Kairopsis brings investigation and saved evidence together in a browser-based dashboard.

  • Investigate: levels, differences, ratios and regression residuals, with explicit reference periods and optional risk adjustment. Library and Analyses open the same editor, with automatic previews and explicit Save/Discard.
  • Explore: combine Library series and local calculations in several charts, reuse loaded data, and choose each chart's dates and observations.
  • Retain evidence: save charts, observations and notes alongside each Idea.
  • Screen and brief: retain dated screening results for an agent to review against the recorded economic rationale and turn into a concise brief.
  • Revisit and share: compare saved evidence with the latest data and export charts or spreadsheet-ready values.

A built-in demo lets you explore without market-data credentials. Your research stays in a local workspace. Live data access uses Metapyle.

For repeatable development tests, the persisted CSV demo dataset provides 74 synthetic series, including six credit assets with multiple fields, and a standard Metapyle localfile catalogue.

Guides

  • Human guide — everyday investigation, Ideas and exports.
  • Explore guide — collections, chart dates, cached data and frozen evidence.
  • Agent setup guide — Copilot runbook for an upstream source workspace, data connections and handoff.
  • Analysis configuration skill — agent guidance for economic questions, data shaping and analytical settings, with a complete combination map and worked examples.
  • Screening skill — run a screening or review retained results, investigate significant themes, and save a brief with traceable evidence.

All three guides and both self-contained skills are included in the installed Python package and the source archive. Requires Python 3.12 or later. Frontend assets are bundled; no Node.js setup is needed.

Metadata

Release files for kairopsis 0.2.0

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

Source distribution (sdist)

Source distribution for kairopsis 0.2.0
File Size Uploaded
kairopsis-0.2.0.tar.gz 3.9 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for kairopsis 0.2.0
File Interpreter ABI Platform
kairopsis-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 6.1 MB

Release files / kairopsis-0.2.0.tar.gz

Download URL kairopsis-0.2.0.tar.gz
Size 3.9 MB
Tags Source
SHA-256 checksum
How to use checksums
1406c57a8dda9bcae243197e4a7c2ff5693ce326503b76fb0effbabeab9aad5d
BLAKE2b-256 checksum
How to use checksums
eb3bb70b027e8b776d12f261164f89d8a71516c456d400ed92118ac270a868ae
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.3

Release files / kairopsis-0.2.0-py3-none-any.whl

Download URL kairopsis-0.2.0-py3-none-any.whl
Size 2.2 MB
Tags Python 3
SHA-256 checksum
How to use checksums
6ba3d3d16a2f8eb8c75140147d1864cd6bc9b6b355a0976197a303038dacbcca
BLAKE2b-256 checksum
How to use checksums
c89af8e9113c30edeefaed7d7607f93367ad1884c6a1acdd2ad6cfa5bf19e731
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.3

Release history Release notifications | RSS feed

0.2.1

2 release files

This release

0.2.0 This release

2 release files

0.1.2

2 release files

0.1.1

2 release files

0.1.0

2 release files

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