Skip to main content

The knowledge layer between your codebase and every AI that works on it.

Project description

LoomState

Git versions your code. LoomState versions your project's knowledge.

LoomState is the knowledge layer between your codebase and every AI that works on it.

Instead of every AI coding assistant rebuilding its own understanding of your project from scratch, LoomState stores trusted project knowledge in a shared, version-aware workspace. It separates verifiable project facts, AI-generated understanding, and human reasoning while tracking the provenance and freshness of every piece of information.

The result is a single source of truth that any AI tool can use to start with accurate, explainable project context instead of guessing.

Install

pip install loomstate

Usage

loom init       # initialize the workspace (requires a git repo)
loom sync       # scan the repository and update Project State
loom note "..." # add a session note
loom artifact architecture   # generate the architecture summary
loom status     # check artifact freshness
loom export agents           # export to AGENTS.md

An MCP server is also available via loom-mcp, exposing get_project_state, get_architecture_summary, get_session_notes, and write_session_note to any MCP-compatible client.

Why LoomState?

Without LoomState:

Repository
    ↓
Claude analyzes it

Repository
    ↓
Cursor analyzes it

Repository
    ↓
ChatGPT analyzes it

Every AI rebuilds the same understanding independently.

With LoomState:

Repository
    ↓
LoomState
    ↓
Claude • Cursor • ChatGPT • Codex

One shared, version-aware source of project knowledge.

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

loomstate-0.1.0.tar.gz (11.9 kB view details)

Uploaded Source

Built Distribution

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

loomstate-0.1.0-py3-none-any.whl (14.4 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: loomstate-0.1.0.tar.gz
  • Upload date:
  • Size: 11.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.4

File hashes

Hashes for loomstate-0.1.0.tar.gz
Algorithm Hash digest
SHA256 986212c505adaa3037e1ba9d3e727d864826dffc1972ac53b2ec0c6bea9d3ccf
MD5 17e0e88a25396c53bd646011e657c704
BLAKE2b-256 e88d8e9bc58a6dd76c5299da36182da1b3fa8374020d13320ae738fbc64acde2

See more details on using hashes here.

File details

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

File metadata

  • Download URL: loomstate-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 14.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.4

File hashes

Hashes for loomstate-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 70bf120d7845884da80e9f20775a9c023418a18945a4f67930686009783cca08
MD5 5a13b9da418a1b0f48918b6d1842f415
BLAKE2b-256 82fd52387a9e1f551ef80b6bc16b3e7d1903f647047e7e60d6f2a9ff6c76f5f8

See more details on using hashes here.

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