ErrorAI v2
ErrorAI is a Python-only autonomous runtime that starts on import, catches exceptions, and operates with safe-by-default watch/read/write behavior.
Quickstart
pip install ErrorAI
import errorai
That import initializes a singleton runtime, registers exception hooks, and starts background watch services when supported.
Optional setup commands
errorai init
errorai doctor
errorai install-model
init: writes default.errorai.tomldoctor: reports environment/runtime/model readiness and fallback modeinstall-model: retries local model bootstrap
Model bootstrap strategy
- Core package does not bundle large model weights.
- On import/first use, ErrorAI attempts to bootstrap a lightweight local coding model into user cache.
- If bootstrap fails (offline/network/permissions), runtime continues in
rules-onlymode with clear status.
Safety defaults
- Safe mode is enabled by default.
- Writes are restricted to the project root.
- Sensitive/common ignore patterns are blocked by default.
- Dry-run mode is on by default to preview edits before writing.
Migration notes from v1 beta
import errorainow auto-starts the runtime; explicitglobal_activate()is optional.@watchandcatch_errorsremain available for compatibility but are no longer required.
1 maintainer
Metadata
1 maintainer
Release files for ErrorAI 2.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| errorai-2.1.0.tar.gz | 19.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| errorai-2.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 40.6 kB
Release files / errorai-2.1.0.tar.gz
| Download URL | errorai-2.1.0.tar.gz |
|---|---|
| Size | 19.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
83b5df1e05d20b061fa277191f7b5f6f7934852801197a046b181bf7a19b0186
|
|
BLAKE2b-256 checksum How to use checksums |
71d8b07a960c101653778d4efd70f3ca9eed2ab96e6c029bd6998d34a47eeb9a
|
| 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 Aug 26, 2026.
Transparency logRelease files / errorai-2.1.0-py3-none-any.whl
| Download URL | errorai-2.1.0-py3-none-any.whl |
|---|---|
| Size | 21.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2b1ce1e824c44172e76319f7479da864e6a0129a5f6afb3e0070656a8603b032
|
|
BLAKE2b-256 checksum How to use checksums |
454d41a21458fe120c44f921b047e223c9f021987abd7b7b0b72c8c481c32d1d
|
| 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 Aug 26, 2026.
Transparency log
