DeerFlow: review, pricing, security and alternatives

What DeerFlow does

DeerFlow belongs to the deep research family: agents that search, read and cross-check dozens of sources to produce a sourced report. On our grid it ranks #1 of the 18 projects of this family listed in the directory.

You use it from: web app and API. Usable models: any OpenAI-compatible model. It can run on your own machine or server.

Who is DeerFlow for?

It targets analysts, students and teams who must cross-check many sources to produce a reasoned summary. Typical tasks people give it:

• write a sourced overview of a topic
• compare products or competitors
• prepare a technical or regulatory watch

It is a good candidate if you prefer doing everything in a browser, with no install and your data must stay on your machines.

Access and human control

According to its documentation, DeerFlow can:

• run commands in a terminal
• read and edit files
• drive a web browser
• call online services and APIs

We could not establish whether it asks for human approval before sensitive actions: test it first on an unimportant account or folder.

DeerFlow pricing

The code is free, under the MIT licence.

Getting started with DeerFlow

1. Install it: the project ships as a Python package (install with pip or uv). The exact command is in the repository README.
2. Create an API key with the model provider and put it in an environment variable, never in a shared or versioned file.
3. Give it a first playground with nothing at stake: a test folder, a secondary account or a throwaway project. Only open your real accounts once you have seen how it behaves.
4. Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.

Security: risk level

An agent's report may cite misread or invented sources: check the links before reusing a figure.

Points found for DeerFlow:

• Sensitive access: it can run commands in a terminal, with no established default human approval.
• Outside content: it reads web pages or API responses, which may contain booby-trapped instructions (prompt injection).

Three habits: least privilege (minimal rights, dedicated keys), human approval for irreversible actions, a sandbox for code execution. The AI agent security check reviews your setup in a few minutes.

Project activity and releases

Created on May 7, 2025, the bytedance/deer-flow repository has 84,377 stars, 11,803 forks and 538 open issues, with 4,439 commits in total. It received changes this month.

Over the last 52 weeks: 3,874 commits, an average of 74.5 per week.

2 releases in total; 2 in the last twelve months. Latest release: v2.1.0, on September 24, 2026.

DeerFlow vs other deep research

GitHub stars of the best-rated open-source projects in the deep research family. Stars measure attention, not quality: a heavily promoted project collects them fast, a specialised tool will have few.

DeerFlow and other deep research at a glance

The 7 best-ranked agents in the same family, 7 of them open source. The score out of 100 only applies to open-source projects; for proprietary services we show the published entry price. A dash marks information the documentation does not state.

How we rated it

Score: 87/100, computed only from public, verifiable data, with no subjective testing or partnership:

• Adoption 35/40: 84,377 stars on a log scale (40 points from about 200,000).
• Activity 27/30: last commit less than a month ago, 2 releases in six months, 3,874 commits in a year.
• Framework 25/30: licence, default human approval, self-hosting, model choice and documentation site.

The score does not say whether the agent will succeed at your tasks: it measures how solid the project is. The full grid is on the method page.