Skip to main content

​
Moorcheh On-Edge Changelog

Track releases of the on-device Moorcheh On-Edge stack: moorcheh-edge on PyPI, the moorcheh/moorcheh-edge Docker image, REST API, moorcheh-edge CLI, and MoorchehEdge / MoorchehEdgeApiClient.
​
Version 0.1.1
Released June 1, 2026

​
CI, release pipeline, and multi-arch Docker

Patch release for Moorcheh On-Edge with automated CI and publish workflows, plus a multi-architecture Docker image. No breaking changes to the REST API, CLI, or MoorchehEdge client.

​
Install and upgrade

pip install moorcheh-edge==0.1.1
# or
pip install -U moorcheh-edge

​
What’s new

  • CI pipeline — automated tests and checks on pull requests and pushes
  • Publish pipeline — automated PyPI and Docker image releases for moorcheh-edge and moorcheh/moorcheh-edge
  • Multi-arch Docker image — moorcheh/moorcheh-edge:0.1.1 and :latest ship linux/amd64 and linux/arm64 (Intel/AMD PCs and ARM edge devices such as Arduino UNO Q). Docker selects the correct architecture automatically; no CLI changes required.

​
Upgrade notes

No code changes are required if you already use the moorcheh-edge CLI or MoorchehEdge from v0.1.0. Your existing moorcheh-edge up workflows and data under ~/.moorcheh-edge/data are unchanged.
​
Version 0.1.0
Released May 26, 2026

​
Initial release

First public release of Moorcheh On-Edge — on-device vector upload, similarity search, and delete. You provide 1024-dimensional embeddings; the server binarizes them for fast local search. No cloud API keys or Ollama required.

​
Install

pip install moorcheh-edge
moorcheh-edge up
moorcheh-edge status

​
Runtime

  • moorcheh-edge up / down / status — Start and stop the Moorcheh On-Edge API server (moorcheh/moorcheh-edge:latest) via Docker
  • Local data — Persistent store under ~/.moorcheh-edge/data (moorcheh_edge_store.json)
  • Default API — http://localhost:8080

​
REST API

  • Health — Server status, vector dimension, and per-store item quota (GET /health)
  • Upload — Upload or replace vectors by id (POST /upload)
  • Search — Similarity search with a 1024-float query vector (POST /search)
  • Delete — Remove vectors by id (DELETE /delete)

​
CLI and Python client

  • moorcheh-edge on PyPI — Installs the moorcheh-edge CLI and Python SDK in one package
  • CLI — up, down, status, upload-vectors, search, delete
  • Python — MoorchehEdge (lifecycle + API) and MoorchehEdgeApiClient (HTTP only); errors via MoorchehEdgeApiError

​
Limits

  • Vector-only — Plain text queries are not supported; generate embeddings upstream
  • 1024 dimensions — Upload and search vectors must be exactly 1024 finite floats
  • 10,000 items per store; HTTP 409 when the cap would be exceeded
  • No API keys — intended for localhost and trusted networks
Getting started: See Introduction, Prerequisites, and Quickstart.