astra-assistants
Astra Assistants API - drop in replacement for OpenAI Assistants, powered by AstraDB
Decision gist · record as of 2026-08-14
Yes, if you are already using OpenAI Assistants and want to add AstraDB vector storage or experiment with alternative LLM providers without rewriting integration code. The low install friction and broad provider support make it a practical bridge. However, the aging maintenance status (482 days since last release) and unclear license terms are cautions—verify license compliance and test compatibility with your current OpenAI SDK version before committing to production use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- API keys for AstraDB and at least one LLM provider must be set as environment variables.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
(unclear) — License treatment is unclear; no SPDX identifier or raw license text is published. Verify the actual license terms before using in proprietary or commercial contexts.
last release 2025-04-19 (482 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 89,593 downloads/mo, #13,647 on PyPI
Alternatives
Verify before relying
pip install astra-assistants
from openai import OpenAI
from astra_assistants import patch
client = patch(OpenAI())- Whether the aging maintenance status (482 days since last release) affects compatibility with current OpenAI SDK versions.
- Exact license terms and any restrictions on commercial use or redistribution.
- Support status for the full Assistants v2 API surface, including all recent OpenAI additions.
What it is and what it does
Astra Assistants is a Python library that patches the OpenAI SDK to act as a drop-in replacement for OpenAI's Assistants API. It extends the standard API with support for AstraDB vector stores and adds a credential abstraction layer that lets you route requests to alternative LLM providers—including Groq, Anthropic, Gemini, Perplexity, Cohere, AWS Bedrock, Vertex AI, and many others—by setting environment variables. The library wraps litellm under the hood to handle provider-specific authentication and API translation.
You install it alongside the OpenAI SDK, import the patch function, and apply it to an OpenAI client instance. From that point forward, your existing OpenAI Assistants code works unchanged, but now backed by AstraDB for vector storage and able to use any LLM provider litellm supports. It includes support for streaming and the full Assistants v2 API surface. The package carries 12 runtime dependencies covering HTTP clients, language server protocol support, code parsing, and linting.
Use it for
- Build an assistant that uses AstraDB for semantic search and retrieval without rewriting OpenAI integration code.
- Route assistant requests to multiple LLM providers (Anthropic, Groq, etc.) by changing environment variables instead of code.
- Add vector store capabilities to an existing OpenAI Assistants application with minimal refactoring.
- Prototype multi-provider LLM workflows where you can swap backends without touching business logic.
- Stream assistant responses from non-OpenAI providers using the same Assistants v2 API surface.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are already using OpenAI Assistants and want to add AstraDB vector storage or experiment with alternative LLM providers without rewriting integration code.
The low install friction and broad provider support make it a practical bridge. However, the aging maintenance status (482 days since last release) and unclear license terms are cautions—verify license compliance and test compatibility with your current OpenAI SDK version before committing to production use.
Install
astra-assistants on PyPI
Before you install
Low install friction with a pure-Python wheel. Maintenance status is aging—last release was 482 days ago—so expect slower response to issues or compatibility updates with newer OpenAI SDK versions.
Requires Python 3.10 or later. API keys for AstraDB and at least one LLM provider must be set as environment variables.
License in practice
License treatment is unclear; no SPDX identifier or raw license text is published. Verify the actual license terms before using in proprietary or commercial contexts.
Quickstart
pip install astra-assistants
from openai import OpenAI
from astra_assistants import patch
client = patch(OpenAI())Verify before relying
- Whether the aging maintenance status (482 days since last release) affects compatibility with current OpenAI SDK versions.
- Exact license terms and any restrictions on commercial use or redistribution.
- Support status for the full Assistants v2 API surface, including all recent OpenAI additions.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release <4.0,>=3.10.0 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 12 packageshttpxopenailitellmboto3aiohttppython-dotenvtree-sitter-pythonlsprotocolpython-lsp-jsonrpcrufftree-sittermcp |
| Maintenance | Aging 482 days since the last release |
| First released | |
| Downloads | 89,593 / month, #13,647 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: astra_assistants-2.5.5-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “openai assistants api wrapper”
- astra-assistantsWraps OpenAI's Assistants API as a drop-in replacement, adding…
- langchain-deepseekIntegrates DeepSeek language models into LangChain applications,…
- langchain-openaiProvides LangChain integrations for OpenAI's API, enabling language…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also litellm-enterprise · livekit-plugins-openai · any-llm-sdk · litellm-proxy-extras · unclecode-litellm · llm-openai-plugin · astrapy · openai · langchain-astradb