This release is a pre-release and may not be stable for production use.
MAICA-幻象引擎
中文 | English
本页面是MAICA的指引页面, 当前位置是MAICA后端仓库.
MAICA项目的详细介绍页是https://maica.monika.love/.
要快速开始或了解授权, 请参阅https://maica.monika.love/tos.
MAICA的后端仓库地址是https://github.com/Mon1-innovation/MAICA.
MAICA的后端compact分支地址是https://github.com/Mon1-innovation/MAICA_Server_Submod
MAICA的子模组前端仓库地址是https://github.com/Mon1-innovation/MAICA_ChatSubmod.
MAICA LIA分支的模型地址是https://huggingface.co/edgeinfinity/MAICAv0-LIA-72B.
MAICA LOA分支的模型地址是https://huggingface.co/edgeinfinity/MAICAv0-LOA-7B.
MAICA-MTTS的子模组前端仓库地址是https://github.com/Mon1-innovation/MAICA_MttsSubmod.
MAICA-MTTS的仓库地址是https://github.com/Mon1-innovation/MAICA_MTTS.
MAICA-MTTS模型地址是https://huggingface.co/edgeinfinity/MTTSv0-VoiceClone.
MAICA的基本数据集仓库位于https://huggingface.co/datasets/edgeinfinity/MAICA_ds_basis.
MAICA的相关文档存储于https://github.com/Mon1-innovation/MAICA/tree/main/document.
Anything below this point is written by AI.
快速开始
MAICA 后端需要 Python 3.12 或更高版本，并支持 Windows 与 Linux。核心模型与 MFocus 模型使用 OpenAI-compatible Responses API，需要另行部署；数据库可使用 MySQL/MariaDB，单机测试也可使用 SQLite。
python -m pip install -e .
maica -t create
# 编辑 .env：至少设置 MAICA_IS_REAL_ENV、数据库以及 MCORE/MFOCUS 连接
maica -e .env
默认监听 WebSocket :5000 与 HTTP :6000，可通过 MAICA_WS_HOST/PORT 和 MAICA_HTTP_HOST/PORT 修改。完整配置项及说明见 maica/env_basis；部署步骤见 document/Backend Deployment.md，接口协议见 document/API Documents.md。
开发与验证
python -m pip install -e ".[dev]"
python -m pytest -q
python -m ruff check maica tests examples
examples/ 中的脚本是需要真实模型或 Milvus 的手工连通性检查，不属于离线测试。维护者应同时阅读 document/MAINTENANCE.md。
部署安全
公开实例应在反向代理上启用 TLS；HTTP 鉴权优先使用 Authorization: Bearer <access_token>，避免把令牌写入 URL。请保管 maica/keys/prv.key，为 NVWatcher 配置 SSH host key，并通过 MAICA_VISION_HOST_ALLOWLIST 限制可发送给视觉模型的图片域名。
1 maintainer
Metadata
1 maintainer
Release files for mi-maica 1.3.0rc1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| mi_maica-1.3.0rc1.tar.gz | 58.3 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mi_maica-1.3.0rc1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 117.1 MB
Release files / mi_maica-1.3.0rc1.tar.gz
| Download URL | mi_maica-1.3.0rc1.tar.gz |
|---|---|
| Size | 58.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
28c1491a5f86be2590e9524e733edf6fb8dfaec3f7a04b4addbc1458740262fd
|
|
BLAKE2b-256 checksum How to use checksums |
d5734a2890b327af5c3ee03bc9325d377376e36b7a59c6d17c146cf9dfae6e68
|
| 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 Jul 30, 2026.
Transparency logRelease files / mi_maica-1.3.0rc1-py3-none-any.whl
| Download URL | mi_maica-1.3.0rc1-py3-none-any.whl |
|---|---|
| Size | 58.8 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8ff22faaf9ce5ee02579780c1e4d98664e83024f532c16b113e0713333f7830d
|
|
BLAKE2b-256 checksum How to use checksums |
14ec288b01876b4d78540b3eefa19ded6ac7296c48c02861d0d80b9a0f4d7b4a
|
| 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 Jul 30, 2026.
Transparency log
