Skip to main content

Atom Zero 49.2M — a local assistant that cites its sources

Atom Zero is a local, source-cited assistant built around a 49.2M parameter model trained from scratch. Facts live in a local RAG index, not in the model weights; the model handles wording and behavior while deterministic tools, documents, memory and citations do the rest.

This is the standalone atomzero package. The low-VRAM trainer remains in the separate streamft package.

Install

pip install atomzero==0.1.2

Optional local MiniLM reranker:

pip install "atomzero[neural]"

The model weights are not bundled. Download them from Hugging Face or ModelScope.

Quickstart

atomzero-quickstart

The first run downloads the ~197 MB checkpoint/tokenizer, seeds a demo corpus and opens the local UI. No streamft checkout is needed. Use --provider to route free-form chat to local Ollama while RAG/tools stay local.

Manual run

atomzero `
  --model checkpoints/transformer_behavior_50m_scaled `
  --tokenizer data/chat_en_bpe8k.json `
  --docs data/docs.db

Then open the local page (default http://127.0.0.1:8013).

Features

  • PDF, DOCX, HTML and Markdown ingestion with page/section citations.
  • Evidence API/panel that opens the exact local chunks behind a citation.
  • Deterministic tools: time, safe arithmetic, tasks, name/likes memory.
  • Constrained plan API (/v1/agent/plan): allowlist, three-step cap and explicit confirmation for task/research side effects.
  • Sessions: transcript restore, export/import, exact Forget.
  • Research queue: approved-only Wikipedia fetch and local teacher notes.
  • Optional local provider: Ollama/OpenAI-compatible free-form chat while RAG, tools and memory stay local.
  • No telemetry and no hosted service.

Honest limits

  • The raw 49.2M model scores 2/10 on the no-RAG knowledge probe.
  • The product scores 21/21 on the narrow authored product benchmark because RAG and tools do the work.
  • The core context is 128 tokens; it is not a general reasoning or coding model.
  • No OCR; scanned PDFs need OCR before ingestion.
  • Safety is optional and off by default.

Apache-2.0 for code and weights; data attribution in NOTICE.

Metadata

Release files for atomzero 0.1.2

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

Source distribution (sdist)

Source distribution for atomzero 0.1.2
File Size Uploaded Provenance Actions
atomzero-0.1.2.tar.gz 93.2 kB Without provenance Details for atomzero-0.1.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for atomzero 0.1.2
File Interpreter ABI Platform Actions
atomzero-0.1.2-py3-none-any.whl Python 3 none any Details for atomzero-0.1.2-py3-none-any.whl

Total release size: 191.8 kB

Release files / atomzero-0.1.2.tar.gz

Download URL atomzero-0.1.2.tar.gz
Size 93.2 kB
Tags Source
SHA-256 checksum
How to use checksums
c13a2b572dbab1a7a6646a9a41eb4de362fdba56217ef8a58d358bac86310dab
BLAKE2b-256 checksum
How to use checksums
0f62be5d8f35d4ea6c9f3f28313a010b3241ba0083fca9202049c13945bc7ef8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.9

Release files / atomzero-0.1.2-py3-none-any.whl

Download URL atomzero-0.1.2-py3-none-any.whl
Size 98.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
75fba12758fb7f2ba599b4cfcee85c10745bbb4960e03a90744eb4c31ae34a95
BLAKE2b-256 checksum
How to use checksums
a6f98873988c4513c3c20a049ce842ff4b9698d13c81769c4a5cde94630006b1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.9

Security for atomzero 0.1.2

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

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