deer-flow
An open-source long-horizon SuperAgent that handles complex tasks over minutes to hours.
GraphCanon updated 4d · GitHub synced 4d · 28 views this month
Decision brief
Deer-flow is an advanced SuperAgent platform for handling complex tasks over extended periods with a comprehensive set of functionalities such as sandboxes and memories.
Good fit when
- When you need to manage lengthy workflows over minutes to hours that require constant supervision or adaptation by the AI agent, deer-flow's long-horizon capabilities make it suitable.
- If your project involves deep research tasks, leveraging skills through subagents or integrating complex toolsets for extended processes, choosing this platform can streamline operations with its fine
Avoid when
- For short, straightforward tasks that do not require extensive workflows (under a minute), deer-flow might be overkill due to its advanced functionalities and setup complexity.
- If your team is primarily working with technologies like Node.js or TypeScript rather than Python, other tools might offer better integration and support.
Observed Jul 11, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of 4d
- Provenance
- Not a fork · Organization account
- As of 4d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Backing
Company context for ByteDance. Display-only - separate from trust and ranking.
- Company
- Bytedance Inc.·GitHub org profile·1mo
- Commercial model
- Pure OSS·GitHub org profile (public repos)·1mo
Install
pip install deer-flowHow it fits your stack(12)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Depends on
Related
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
bytedance/deer-flow is an advanced AI Agents platform developed in Python. It enables research, coding, and creation through an extensive set of functionalities including sandboxes, memories, tools, skills, subagents, and message gateways for managing lengthy workflows.
Capability facts
- Languages
- python
Source: github.language · Aug 16, 2026
Categories
Graph entities
Tags
README
Coding Plan from ByteDance Volcengine
- We strongly recommend using Doubao-Seed-2.0-Code, DeepSeek v3.2 and Kimi 2.5 to run DeerFlow
- Learn more
- 中国大陆地区的开发者请点击这里
PyPI — pin a version for a reproducible deployment
make extension-install SOURCE="deerflow-extension-acme==1.2.3"
Improper Deployment May Introduce Security Risks
DeerFlow has key high-privilege capabilities including system command execution, resource operations, and business logic invocation, and is designed by default to be deployed in a local trusted environment (accessible only via the 127.0.0.1 loopback interface). If you deploy the agent in untrusted environments — such as LAN networks, public cloud servers, or other multi-endpoint accessible environments — without strict security measures, it may introduce security risks, including:
- Unauthorized illegal invocation: Agent functionality could be discovered by unauthorized third parties or malicious internet scanners, triggering bulk unauthorized requests that execute high-risk operations such as system commands and file read/write, potentially causing serious security consequences.
- Compliance and legal risks: If the agent is illegally invoked to conduct cyberattacks, data theft, or other illegal activities, it may result in legal liability and compliance risks.
Deployment Defaults
The Docker stack publishes its entry port on 127.0.0.1 only, matching the
local-trusted-environment model described above. To reach it from another
machine, set BIND_HOST in .env (e.g. BIND_HOST=0.0.0.0) — and only after
putting the security measures below in place.
Complete first-run setup before the host becomes reachable. A fresh
instance has no accounts yet, so create the admin account through /setup
immediately after starting any deployment that is not loopback-only.
License
This project is open source and available under the MIT License.
For agents
This page has a .md twin and JSON over the API.