matrx-batch

Cost-shield foundation for AI workloads in the Matrx ecosystem.

Three primitives:

OpenAI Batch API + Anthropic Message Batches — submit JSONL, poll status, fetch results. Async wrappers over the provider SDKs.
Urgency router — BatchRouter.submit(job) routes a job to live inference, to the provider's Batch API (50% discount, 24h SLA), or makes a cost-based decision automatically.
Embedding cache — content-addressable (SHA256 of model || text) reuse of embedding vectors across the org. Backed by rag.embedding_cache via a host-supplied asyncpg pool.

Dependency posture

matrx-batch sits one notch above matrx-utils in the dependency graph and is consumed by matrx-rag (embedding cache) and matrx-ai (urgency router, future). It MUST NOT import from aidream/ or from any other matrx-* sibling — every cross-boundary dependency comes in via matrx_batch.configure(...).

Usage (host-side wiring)

import matrx_batch
from openai import AsyncOpenAI
from anthropic import AsyncAnthropic

matrx_batch.configure(
    openai_client=AsyncOpenAI(api_key=settings.OPENAI_API_KEY),
    anthropic_client=AsyncAnthropic(api_key=settings.ANTHROPIC_API_KEY),
    pool_factory=lambda: get_async_pg_pool(),
    cost_check=_aidream_budget_precheck,
)

# Wire the cache into matrx-rag's embed() funnel
import matrx_rag
matrx_rag.configure(embedding_cache=matrx_batch.get_embedding_cache())

Usage (consumer)

from matrx_batch import BatchRouter, BatchableJob

router = BatchRouter()
receipt = await router.submit(
    BatchableJob(
        kind="chat",
        provider="anthropic",
        urgency="auto",
        payload={"model": "claude-haiku-4-5", "messages": [...]},
        estimated_tokens_in=8200,
    )
)

Release files for matrx-batch 0.2.98

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

Source distribution (sdist)

Source distribution for matrx-batch 0.2.98
File	Size	Uploaded
matrx_batch-0.2.98.tar.gz	82.8 kB	Sep 19, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for matrx-batch 0.2.98
File	Interpreter	ABI	Platform	Reset
matrx_batch-0.2.98-py3-none-any.whl 72.5 kB Sep 19, 2026	Python 3	none	any	Details

Total release size: 155.3 kB

Release files / matrx_batch-0.2.98.tar.gz

Download URL	matrx_batch-0.2.98.tar.gz
Size	82.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`18837712ecfe83b71f43d3a037bf4e42184a56d2f6ea35d618a3d05135a027e5`
BLAKE2b-256 checksum How to use checksums	`aa9421a8a6549b496510e428b3f0868d42eb91b9096a9e51f2d3e69f96e878f5`
Upload date	Sep 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/AI-Matrix-Engine/aidream
Publishing commit: github.com/AI-Matrix-Engine/aidream/tree/e84e1c50017678d0bad0da000af4f2d121fe5402

Workflow

Publishing configuration: github.com/AI-Matrix-Engine/aidream/blob/e84e1c50017678d0bad0da000af4f2d121fe5402/.github/workflows/publish-package.yml
Publishing logs: github.com/AI-Matrix-Engine/aidream/actions/runs/35429676728/attempts/1

Artifact

Subject: matrx_batch-0.2.98.tar.gz
SHA-256 checksum: 18837712ecfe83b71f43d3a037bf4e42184a56d2f6ea35d618a3d05135a027e5 Verifying attestations

Release files / matrx_batch-0.2.98-py3-none-any.whl

Download URL	matrx_batch-0.2.98-py3-none-any.whl
Size	72.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`f090f516379d77f94c0ace69fe21fb766f5773e5139a34bf9a06689565698853`
BLAKE2b-256 checksum How to use checksums	`aeadeb9b9696c7bf1c7e0a6f0a27cb6dc4d765315cfeca6a779c1c36ea4ffec9`
Upload date	Sep 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/AI-Matrix-Engine/aidream
Publishing commit: github.com/AI-Matrix-Engine/aidream/tree/e84e1c50017678d0bad0da000af4f2d121fe5402

Workflow

Publishing configuration: github.com/AI-Matrix-Engine/aidream/blob/e84e1c50017678d0bad0da000af4f2d121fe5402/.github/workflows/publish-package.yml
Publishing logs: github.com/AI-Matrix-Engine/aidream/actions/runs/35429676728/attempts/1

Artifact

Subject: matrx_batch-0.2.98-py3-none-any.whl
SHA-256 checksum: f090f516379d77f94c0ace69fe21fb766f5773e5139a34bf9a06689565698853 Verifying attestations