idun-sdk

A thin, dependency-free Python client + CLI for Azure AI Foundry agents (Idun / NatureLM) and any OpenAI-compatible endpoint. Tenant-agnostic by default: bring your own Foundry resource, no hardcoded tenant coordinates.

Install

pip install idun-sdk
# with optional PDF ingest:
pip install "idun-sdk[pdf]"   # pulls PyPDF2

Quick start (SDK)

from idun import IdunClient

client = IdunClient()                 # reads ~/.idun/config.toml
out = client.complete("Summarize the quarterly risk report.")
print(out["text"])

Two CLIs — two setup wizards

This package ships two command-line tools with distinct purposes, and each has its own first-run setup wizard:

idun — the Azure AI Foundry client. Agent completions, trajectory export, document matrix (idun matrix), prompt packs (idun packs / idun run), and Hugging Face Hub operations (idun hf). Azure-specific.
- idun wizard configures the Azure Foundry client (endpoint / project / agent) in ~/.idun/config.toml.
idun-multi — the multi-provider LLM console. Talks to any of the 17 registered providers (OpenAI, Anthropic, Groq, OpenRouter, HF, …) plus race, cost, models, doctor, support. Provider-agnostic.
- idun-multi wizard configures the default LLM provider (picks one of the 17 registered providers) in ~/.idun/config.toml.

Both wizards write only to ~/.idun/config.toml (never ~/.idunrc, which is no longer used). Credentials live in per-provider ~/.idun/<id>.token files (0600).

idun-multi providers        # list providers + credential status
idun-multi -p openrouter ask "hello"   # -p goes BEFORE the subcommand
idun-multi race "explain quantum"      # compare providers on one prompt
idun-multi doctor            # environment + credential audit (also checks scripts)
idun-multi wizard            # pick the default LLM provider
idun wizard                  # configure the Azure Foundry client

Async

import asyncio
from idun import AsyncIdunClient

async def main():
    c = AsyncIdunClient()
    out = await c.acomplete("What changed vs last quarter?")
    print(out["text"])

asyncio.run(main())

CLI

idun chat "your prompt"                    # one-shot completion
idun chat --async "your prompt"           # async path
idun run <pack> <key>                     # run a bundled prompt pack
idun packs                                # list bundled prompt packs
idun login                               # device-code login to your Foundry
idun status                              # show token / config state
idun wizard                              # configure the Azure Foundry client
idun welcome                             # ASCII banner
idun matrix  --docs DIR  --questions FILE   # Doc x Question pivot (IDEA α)
idun diff-docs --doc-a A --doc-b B --topics T  # clause-drift compare (IDEA γ)

Supported providers

The idun CLI / IdunClient speak to any OpenAI-compatible endpoint plus the native Azure AI Foundry transport. Registered providers (3 transports):

OpenAI-compatible: openai, groq, together, perplexity, fireworks, novita, xai, deepseek, mistral, openrouter, gemini, hf
Anthropic: anthropic (Claude)
Azure: azure (Azure AI Foundry / Idun agent)
Local: ollama, local (bring your own endpoint)

Tested vs untested (as of 2026-08-21). After a full audit only a subset of these providers has actually been exercised against a live endpoint. The rest are registered and code-complete but NOT verified — they may work, but nobody has confirmed it.

Status Providers

✅ tested against a live endpoint openrouter (live OK), openai (token valid, account has no credit → HTTP 429), hf (migrated to router.huggingface.co; see note), ollama / local (correctly unreachable in CI)

⚠️ untested anthropic, groq, together, deepseek, mistral, gemini, xai, nous, perplexity, fireworks, novita

ℹ️ needs tenant azure

See AUDIT-BEFEHLE.md for the full command audit and BEFUNDE.md / ROADMAP-FIX.md for the bug log. A live test harness for idun race is planned to exercise all providers before the next release.

Status	Providers
✅ tested against a live endpoint	`openrouter` (live OK), `openai` (token valid, account has no credit → HTTP 429), `hf` (migrated to `router.huggingface.co`; see note), `ollama` / `local` (correctly unreachable in CI)
⚠️ untested	`anthropic`, `groq`, `together`, `deepseek`, `mistral`, `gemini`, `xai`, `nous`, `perplexity`, `fireworks`, `novita`
ℹ️ needs tenant	`azure`

Hugging Face (hf): migrated to the OpenAI-compatible router https://router.huggingface.co/v1 (the old api-inference.huggingface.co host was retired and no longer resolves). Requires an HF token (HF_TOKEN).

Any OpenAI-compatible base URL works with zero code changes — set it in the config and the provider switches automatically. See SUPPORT_MATRIX.md for per-provider capability details.

Configuration (tenant-agnostic)

~/.idun/config.toml (neutral defaults — supply your own resource). Secrets go to per-provider ~/.idun/<id>.token files (mode 0600), not in this file:

[defaults]
provider = "openrouter"   # selected by `idun-wizard`

[openrouter]
model = "deepseek/deepseek-chat"

No tenant coordinates are baked into the shipped code. The CLI reads the config via idun.config; environment variables (IDUN_PROVIDER, OPENAI_API_KEY, …) always win over the file.

Additional features

These build on the core SDK and live in idun.matrix / the playground repo.

Idun Matrix — Doc × Question pivot (IDEA α)

Build an N × M answer matrix over documents × questions. Each cell carries the answer, the source citation, and a status (GREEN = answered+cited, RED = contradiction, GRAY = no info).

idun matrix --docs ./contracts --questions ./questions.txt

Clause Drift compare (IDEA γ)

Compare two documents across topics and flag deviations:

idun diff-docs --doc-a contract_a.txt --doc-b contract_b.txt --topics topics.txt

PocketPal-style Bridge (IDEA β)

A tenant-agnostic mobile web UI that runs idun matrix against your Foundry resource: https://qapdex-maker.github.io/idun-playground/matrix_app.html

Development

pip install -e ".[dev]"
pytest        # offline; no network/API keys required
ruff check .  # lint (pinned ruff==0.15.10 in CI)

License

MIT.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

idun_sdk-1.0.24.tar.gz (127.8 kB view details)

Uploaded Aug 21, 2026 Source

Built Distribution

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

idun_sdk-1.0.24-py3-none-any.whl (91.5 kB view details)

Uploaded Aug 21, 2026 Python 3

File details

Details for the file idun_sdk-1.0.24.tar.gz.

File metadata

Download URL: idun_sdk-1.0.24.tar.gz
Upload date: Aug 21, 2026
Size: 127.8 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/7.0.0 CPython/3.14.6

File hashes

Hashes for idun_sdk-1.0.24.tar.gz
Algorithm	Hash digest
SHA256	`a13e782c14108adf90d8daf205f1ecbde25a05f5f22eb019db17248eb9b70624`
MD5	`ea3a672a2b8e03a6dfcc9fa74a1a5364`
BLAKE2b-256	`1ade7707c8c50da2f434cf37ddf91037f61cb59e357f313dfe008e3a752ab235`

See more details on using hashes here.

File details

Details for the file idun_sdk-1.0.24-py3-none-any.whl.

File metadata

Download URL: idun_sdk-1.0.24-py3-none-any.whl
Upload date: Aug 21, 2026
Size: 91.5 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/7.0.0 CPython/3.14.6

File hashes

Hashes for idun_sdk-1.0.24-py3-none-any.whl
Algorithm	Hash digest
SHA256	`43bdaa3a13e335ec6fa3cb8ac94ffdb5ff1d4a3307b40da083696ea92be6b183`
MD5	`c526f815a4ea7f336a8496cc1549838e`
BLAKE2b-256	`c051be14acb1fb05862b2aaa5eb8918f1ec7e3e5d140e79e267abac267ff5af1`