agent-framework-azure-cosmos
Azure Cosmos DB history provider integration for Microsoft Agent Framework.
Decision gist · record as of 2026-08-14
Yes, if you are building agent applications on the Microsoft Agent Framework and need durable storage for conversation history or workflow checkpoints. The package is actively maintained, has low install friction, carries no known vulnerabilities, and is MIT-licensed. It is still in beta (1.0.0b260730), so expect potential API changes before a stable release.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later and an active Azure Cosmos DB account with endpoint and credentials.
- Low install friction with a pure-Python wheel.
- Active maintenance—released 15 days ago with recent commits.
License · maintenance · safety
permissive license (permissive) — MIT license (permissive); you can use, modify, and distribute this package freely with minimal restrictions.
last release 2026-07-30 (15 days) · last repo commit 2026-08-14 · 12,804 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 239,547 downloads/mo, #8,920 on PyPI
Alternatives
Verify before relying
pip install agent-framework-azure-cosmos --pre
from azure.identity.aio import DefaultAzureCredential
from agent_framework_azure_cosmos import CosmosHistoryProvider
provider = CosmosHistoryProvider(
endpoint="https://.documents.azure.com:443/",
credential=DefaultAzureCredential(),
database_name="agent-framework",
container_name="chat-history",
)- Whether the package works with Python 3.14 in practice (classifier lists it but it's a future release).
- Performance characteristics and cost implications of storing large conversation histories or frequent checkpoint writes in Cosmos DB.
What it is and what it does
This package bridges the Microsoft Agent Framework and Azure Cosmos DB, offering two main storage backends: CosmosHistoryProvider for persisting multi-turn conversation history, and CosmosCheckpointStorage for durable workflow state. Both support multiple authentication modes (managed identity, account keys, environment variables) and auto-create their database and container on first use.
It is designed for developers building agent applications that need to survive process restarts or maintain long-running conversation context. The package integrates directly with the agent-framework-core runtime and relies on the azure-cosmos client library for all Cosmos DB operations.
Use it for
- Store multi-turn conversation history for chatbots or virtual agents across user sessions.
- Enable workflow pause-and-resume by checkpointing agent state to Cosmos DB between supersteps.
- Build production agent systems with managed identity authentication for secure, credential-less deployment.
- Persist agent conversation context for audit, compliance, or analytics purposes.
- Scale agent applications by offloading session state to a managed NoSQL database.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building agent applications on the Microsoft Agent Framework and need durable storage for conversation history or workflow checkpoints.
The package is actively maintained, has low install friction, carries no known vulnerabilities, and is MIT-licensed. It is still in beta (1.0.0b260730), so expect potential API changes before a stable release.
Install
agent-framework-azure-cosmos on PyPI
Before you install
Low install friction with a pure-Python wheel. Active maintenance—released 15 days ago with recent commits. Depends on agent-framework-core and azure-cosmos, both standard Azure SDK packages.
Requires Python 3.10 or later and an active Azure Cosmos DB account with endpoint and credentials.
License in practice
MIT license (permissive); you can use, modify, and distribute this package freely with minimal restrictions.
Quickstart
pip install agent-framework-azure-cosmos --pre
from azure.identity.aio import DefaultAzureCredential
from agent_framework_azure_cosmos import CosmosHistoryProvider
provider = CosmosHistoryProvider(
endpoint="https://.documents.azure.com:443/",
credential=DefaultAzureCredential(),
database_name="agent-framework",
container_name="chat-history",
)Verify before relying
- Whether the package works with Python 3.14 in practice (classifier lists it but it's a future release).
- Performance characteristics and cost implications of storing large conversation histories or frequent checkpoint writes in Cosmos DB.
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 2 packagesagent-framework-coreazure-cosmos |
| Maintenance | Actively maintained 15 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 239,547 / month, #8,920 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Typing :: Typed |
Evidence: agent_framework_azure_cosmos-1.0.0b260730-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 › “azure cosmos db agent framework”
- agent-framework-azure-cosmosProvides Azure Cosmos DB integration for the Microsoft Agent…
- azure-mgmt-cosmosdbProvides programmatic management of Azure Cosmos DB…
- azure-cosmosPython client library for Azure Cosmos DB SQL API that manages…
Give your agent the search over MCP, or paste the wish link into any chat.
More Application Frameworks packages
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.
Install it if you're developing CLI tools, dashboards, or interactive terminal applications.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.
Install it if you need to build or connect to servers.
Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.
See also agent-framework-azure-ai · agent-framework-azurefunctions · azure-cosmos · agent-framework-redis · azure-mgmt-cosmosdb · cosmos-xenna · prefect-azure · pydocumentdb · agent-framework-foundry-hosting · agent-framework-bedrock