Source: https://seerepo.com/compare/apache/airflow/vs/microsoft/agent-framework
Markdown source: https://seerepo.com/compare/apache/airflow/vs/microsoft/agent-framework.md
Description: airflow and agent-framework share 20 technologies: FastAPI, azure-cosmos, azure-search-documents, pgvector, psycopg, pymongo, Redis, oracledb, DuckDB, AIOHTTP, uvicorn, Vite, React, Pydantic, jsonschema, msgspec, OpenTelemetry, boto3, psutil, and next-themes. Both are written in Python.

# airflow vs agent-framework

airflow and agent-framework share 20 technologies: FastAPI, azure-cosmos, azure-search-documents, pgvector, psycopg, pymongo, Redis, oracledb, DuckDB, AIOHTTP, uvicorn, Vite, React, Pydantic, jsonschema, msgspec, OpenTelemetry, boto3, psutil, and next-themes. Both are written in Python.

- [apache/airflow](https://seerepo.com/r/apache/airflow): Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
- [microsoft/agent-framework](https://seerepo.com/r/microsoft/agent-framework): A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

## What they share and what sets them apart

- In common: FastAPI, azure-cosmos, azure-search-documents, pgvector, psycopg, pymongo, Redis, oracledb, DuckDB, AIOHTTP, uvicorn, Vite, React, Pydantic, jsonschema, msgspec, OpenTelemetry, boto3, psutil, next-themes
- Only in airflow: Flask, aiosqlite, apache-airflow-providers-common-compat, apache-airflow-providers-common-sql, apache-airflow-providers-postgres, azure-datalake-store, azure-kusto-data, azure-mgmt-cosmosdb, azure-mgmt-datalake-store, azure-mgmt-storage, azure-servicebus, azure-storage-blob, azure-storage-file-datalake, azure-storage-file-share, azure-synapse-artifacts, azure-synapse-spark, cassandra-driver, confluent-kafka, gremlinpython, ibm-db, ibm-db-sa, impyla, influxdb3-python, presto-python-client, psycopg2-binary, pyodps, pyspark-client, python-arango, pyvespa, snowflake-sqlalchemy, sqlalchemy-drill, teradatasqlalchemy, weaviate-client, pyarrow, Celery, pyiceberg, fastavro, hdfs, kylinpy, pinecone, pymssql, Trino, ydb, adbc-driver-manager, adlfs, clickhouse-connect, gcloud-aio-bigquery, gcloud-aio-storage, gcsfs, hmsclient, ibmcloudant, jaydebeapi, Neo4j, pinotdb, pydruid, pyexasol, pyhive, pymysql, pyodbc, SQLite, teradatasql, vertica-python, yandex-query-client, ydb-dbapi, Google, apache-airflow-core, flask-appbuilder, asgiref, cadwyn, werkzeug, a2wsgi, Apache, react-router-dom, Rich, rich-click, flask-sqlalchemy, SQLAlchemy, alembic, sqlglot, azure-identity, azure-keyvault-secrets, flask-session, google-auth, microsoft-kiota-authentication-azure, msal-extensions, pyspnego, python-keycloak, spnego, pyjwt, cryptography, flask-login, gcloud-aio-auth, hvac, keyring, google-auth-httplib2, google-auth-oauthlib, azure-ai-projects, pydantic-ai-slim, cohere, nbconvert, jinja2, aiosmtplib, beautifulsoup4, icalendar, sendgrid, flask-wtf, wtforms, marshmallow, airflow-sdk-jul, airflow-sdk-log4j2, airflow-sdk-slf4j, apache-airflow-providers-cncf-kubernetes, apache-airflow-providers-ssh, apache-airflow-providers-standard, azure-batch, azure-mgmt-compute, azure-mgmt-containerinstance, azure-mgmt-containerregistry, azure-mgmt-datafactory, azure-mgmt-resource, Flower, org.apache.airflow:airflow-sdk, python-jenkins, structlog, kubernetes, kubernetes-asyncio, python-on-whales, Datadog, docker, Alibaba Cloud, colorlog, org.apache.logging.log4j:log4j-api, org.apache.logging.log4j:log4j-core, org.slf4j:slf4j-api, Chakra UI, React Hook Form, yaml
- Only in agent-framework: ASP.NET Core, Microsoft.Extensions.VectorData.Abstractions, Microsoft.Azure.Cosmos, Microsoft.Extensions.Caching.Memory, MongoDB, Azure.Storage.Blobs, Postgres, mssql-python, OpenAI, MCP, Anthropic, Mistral AI, Qdrant, Microsoft.Extensions.Hosting, Azure.Identity, Microsoft.Agents.CopilotStudio.Client, msal, a2a-sdk, agent-framework-core, azure-ai-inference, github-copilot-sdk, mem0ai, Microsoft.Extensions.AI.Abstractions, Microsoft.Extensions.AI.OpenAI, ModelContextProtocol, Azure.AI.Projects, agent-framework-openai, Microsoft.Extensions.AI, AGUI.Abstractions, Ollama, typesafe-sdk, AGUI.Server, Microsoft.ML.Tokenizers, filetype, Aspire, azure-core, System.Diagnostics.DiagnosticSource, Microsoft.Extensions.Logging, Microsoft.Extensions.Logging.Abstractions, botocore, Tailwind CSS, class-variance-authority, tailwind-merge, Radix UI, xyflow, Lucide

## Side by side

| | airflow | agent-framework |
|---|---|---|
| Size | 2,186,846 lines written, 4,688 code files | 1,111,813 lines written, 1,483 code files |
| Who writes it | 0.8% of its commits signed by AI. With Claude Code, GitHub Copilot, Cursor, and Devin | 27.7% of its commits signed by AI. With GitHub Copilot, Claude Code, Cursor, and Codex |
| Activity | Last push November 10, 2026, 41,951 commits, 47,436 stars | Last push November 8, 2026, 3,881 commits, 14,594 stars |
| Tests | 4,994 test files. 52.8% of its code files have a test that imports them | 1,113 test files. 68.2% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, airflow or agent-framework?

airflow, with 2,186,846 lines written; agent-framework has 1,111,813.

The proof: [apache/airflow's code at commit 2b59699](https://github.com/apache/airflow/tree/2b59699b0fe9683c418806a334b47077513bde5a)

### Which has more GitHub stars, airflow or agent-framework?

airflow, with 47,436 stars; agent-framework has 14,594.

The proof: [apache/airflow on GitHub](https://github.com/apache/airflow)

### Which has more tests, airflow or agent-framework?

airflow, with 4,994 test files; agent-framework has 1,113.

The proof: [apache/airflow's code at commit 2b59699](https://github.com/apache/airflow/tree/2b59699b0fe9683c418806a334b47077513bde5a)

### Which was updated more recently, airflow or agent-framework?

airflow: its last push was on November 10, 2026, and agent-framework's on November 8, 2026.

The proof: [apache/airflow's commits on GitHub](https://github.com/apache/airflow/commits)

### Which has more commits signed by AI, airflow or agent-framework?

agent-framework: an AI signed 27.7% of its commits, with GitHub Copilot, Claude Code, Cursor, and Codex; in airflow, 0.8%.

The proof: [the commits each tool signed in microsoft/agent-framework](https://seerepo.com/r/microsoft/agent-framework/ai)

## Sources

- apache/airflow: Read on November 10, 2026, at commit 2b59699 (https://github.com/apache/airflow/tree/2b59699b0fe9683c418806a334b47077513bde5a)
- microsoft/agent-framework: Read on November 9, 2026, at commit 924a6e5 (https://github.com/microsoft/agent-framework/tree/924a6e50ec0336f3c965ee8b1151c54085888b6e)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.