Awesome AI AgentsVirtual Assistants

datastax/astra-assistants-api

⭐ 205 Python added to this list on 2025-05-02 repository created 2023-11-15

Astra Assistants API is an open-source project that provides a drop-in replacement for the OpenAI Assistants API v2. It is designed to support a wide range of features including streaming, persistent threads, file handling, vector stores, assistants, retrieval, and function calling. The service leverages AstraDB, a database-as-a-service offering powered by Apache Cassandra and jvector, to manage data storage and vector search capabilities. Astra Assistants API supports integration with dozens of third-party large language model (LLM) providers as well as local models for both completion and embeddings, facilitated by LiteLLM. Users can either use the hosted Astra Assistants service or deploy the open-source API server themselves. The project provides a Python client library called astra-assistants, which can be installed via package managers like Poetry. It allows developers to easily create and manage assistants with customizable instructions and models. The API supports various LLM providers including OpenAI, Groq, Anthropic, Gemini, Perplexity, Cohere, AWS Bedrock, and Google Vertex AI, among others. Environment variables are used to configure API keys for these services. Astra Assistants API offers extensive documentation and examples to help users get started quickly. It supports Docker for containerized deployment and can be run locally using Poetry. Additionally, it provides integration with Ollama for GPU or CPU-based model hosting via Docker Compose. The project encourages community contributions and provides channels for feedback and support through GitHub issues and Discord. Overall, Astra Assistants API aims to be a versatile, open-source alternative to the OpenAI Assistants API, enabling developers to build AI assistant applications with flexibility in model choice and deployment options.

https://github.com/datastax/astra-assistants-api

ai-assistantapache-cassandraapi-serverassistantsassistants-apiastra-assistants-apiastradbclaudecoherecommunity-contributionscompletiondeploymentdockerembeddingsfilesfunction-callinggeminigpt-4groqjvectorlitellmllama3-1local-modelsollamaopen-sourceopenai-assistantsopenai-assistants-apipersistent-threadspython-clientretrievalstreamingthird-party-llm-providersvectorvector-stores

Also in Virtual Assistants

mem0ai/mem0

Mem0 is an open-source memory layer that enhances AI agents and assistants with personalized, adaptive memory capabilities for improved context-aware interactions across various applications.

CherryHQ/cherry-studio

Cherry Studio is a cross-platform desktop client that supports multiple large language model providers, offering extensive AI assistant features, document processing, and practical productivity tools in an open-source environment.

tinyhumansai/openhuman

Local-first personal AI harness combining a persistent memory brain, multi-agent orchestration, and autonomous web and data research.

khoj-ai/khoj

Khoj is a self-hostable personal AI platform that transforms any local or online large language model into a customizable, autonomous AI assistant for research, automation, and document retrieval.

kortix-ai/suna

Suna is an open-source generalist AI assistant that automates real-world tasks through natural conversation, combining browser automation, file management, web crawling, and API integrations in a secure, modular architecture.

gptme/gptme

gptme is a versatile personal AI assistant that operates in your terminal, equipped with tools for coding, file editing, web browsing, and vision, providing a powerful local alternative to popular AI agents for diverse knowledge work.

CherryHQ/cherry-studio-app

Cherry Studio App is the official mobile application that enables powerful AI Large Language Models interaction on iOS and Android devices, supporting multiple LLM providers and offering tools for conversation management and data migration.

cosmicstack-labs/mercury-agent

Personal AI agent in TypeScript that runs continuously from CLI, Telegram or web with permission-gated tools, SQLite-backed long-term memory, token budgets and installable skills.