This release is a pre-release and may not be stable for production use.
베타: 자동 품질 검사가 review_required(종료 코드 3) 경고를 낼 수 있습니다. 결과를 사람이 검토하세요.
hyperresearch-codex
hyperresearch-codex turns one research question into a sourced, adversarially reviewed brief. Python controls the pipeline, Codex model calls run in a read-only sandbox, and deterministic gates check citations and bounded edits.
Safe first run
pip install hyperresearch-codex
hpr demo
hpr demo is local and synthetic: it does not require a Codex login, access the network, or use model tokens.
Before real research, log in to the Codex CLI and inspect the plan:
hpr doctor
hpr run "your question" --dry-run
hpr run "your question"
Real runs consume the configured Codex allowance. Input-token thresholds can stop before a later call, but an in-flight call can exceed them and they are not billing caps.
Full documentation, measured cost boundaries, examples, security notes and contribution instructions are in the GitHub repository.
MIT licensed. Inspired by jordan-gibbs/hyperresearch; this is an independent implementation and shares no code or prompts with it.
1 maintainer
Metadata
1 maintainer
Release files for hyperresearch-codex 0.5.0b1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| hyperresearch_codex-0.5.0b1.tar.gz | 2.2 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| hyperresearch_codex-0.5.0b1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.4 MB
Release files / hyperresearch_codex-0.5.0b1.tar.gz
| Download URL | hyperresearch_codex-0.5.0b1.tar.gz |
|---|---|
| Size | 2.2 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
779e46848bb59eb2179fc597a14041e1c62f4f2740429a61a8bd77c569d4a366
|
|
BLAKE2b-256 checksum How to use checksums |
a7dda95dc2fbac9bc76a5704ef824bf942fcecaac245c1fe0fa873eaf7e5fa8d
|
| Upload date | |
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 11, 2026.
Transparency logRelease files / hyperresearch_codex-0.5.0b1-py3-none-any.whl
| Download URL | hyperresearch_codex-0.5.0b1-py3-none-any.whl |
|---|---|
| Size | 224.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
96fa63ca0a3f30adf3a51676248a3ff7d247c8c29336044d591e0b579345bb36
|
|
BLAKE2b-256 checksum How to use checksums |
537caf803c03838317e0034b26e646fd560fb7e587c384b2dbc4fb87b3310402
|
| Upload date | |
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 11, 2026.
Transparency log
