An AI agent framework for building LLM-powered applications
Project description
lumis
An AI agent framework for building LLM-powered applications with multi-provider LLM support, graph-based workflows, vector storage, and NLP pipelines.
Features
- Multi-provider LLMs — Unified interface across OpenAI, Gemini, Ollama, and Perplexity with middleware support and automatic token counting
- Agents — ReAct, research, and graph-based agent architectures with event-driven lifecycle hooks
- Graph Workflows — Composable, stateful DAG execution with sync and async node support
- Embeddings — OpenAI and HuggingFace embedding backends
- Vector Storage — Chroma and FAISS vector database integrations
- NLP — Named entity recognition, summarization, semantic parsing, and coreference resolution
- Search & Tools — Web scraping, arXiv, Wikipedia, Yahoo Finance, Google Trends, and Tavily integrations
- Memory — Pluggable memory backends for stateful agent conversations
Installation
pip install lumis-ai
Optional extras
Some integrations are opt-in to keep the base install lighter:
| Extra | What it adds | Install |
|---|---|---|
spacy |
NER, fact extraction, coreference resolution | pip install lumis-ai[spacy] |
search |
arXiv, Google Trends, Yahoo Finance | pip install lumis-ai[search] |
django |
Django ORM memory backend | pip install lumis-ai[django] |
The spacy extra requires language models. After installing, download them:
python -m spacy download en_core_web_lg
python -m spacy download en_core_web_trf
License
MIT — see LICENSE for details.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file lumis_ai-0.1.1a7.tar.gz.
File metadata
- Download URL: lumis_ai-0.1.1a7.tar.gz
- Upload date:
- Size: 374.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.27 {"installer":{"name":"uv","version":"0.9.27","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6b7406c423e47c65d8ba4b8d82dbc6d92e853fe88456c8e2b46a72bbfa198840
|
|
| MD5 |
31960915bc9b5a14f03763941d4e99a8
|
|
| BLAKE2b-256 |
6272345bef46229e9e907582c557cf812f2caeb7358dd774e43683c82fdb70fc
|
File details
Details for the file lumis_ai-0.1.1a7-py3-none-any.whl.
File metadata
- Download URL: lumis_ai-0.1.1a7-py3-none-any.whl
- Upload date:
- Size: 120.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.27 {"installer":{"name":"uv","version":"0.9.27","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6b29b685db4d685ebd210704c6d8294fe1ffa39f524de8bb9848369e906d5f74
|
|
| MD5 |
5ff23953cdb10f48d18797ac45f66605
|
|
| BLAKE2b-256 |
c1261d93ebee806ffeecff4d68618c6ba72c9105f878cd66da860603803bdf23
|
