# DeerFlow

> DeerFlow 2.0 (83.9k stars, MIT, v2.1.0 September 2026) is a web workspace that runs a lead agent with sub-agents, memory and code sandboxes (local, Docker or Kubernetes). Built-in skills cover deep research, report writing, slide decks, web pages, charts, image, video and podcast generation; it also has scheduled tasks, MCP plugins and bots for Telegram, Slack, Discord, Feishu and others. You bring model keys (it suggests Doubao, DeepSeek or Kimi; vLLM works) and a search provider such as Tavily or InfoQuest. Needs at least 4 vCPU and 8 GB RAM; Linux plus Docker is the recommended server.

- Repository: https://github.com/bytedance/deer-flow
- Official docs: https://github.com/bytedance/deer-flow#readme
- Checked: 2026-10-16

## What it replaces
- Manus: Deep research reports, File and code tasks in a sandbox, Slides generated from a prompt, Scheduled agent tasks, Connectors to your apps (partial). Covers research, sandboxed work, slides, schedules and connectors when self-hosted; no cloud browser product or hosted website publishing.
- Genspark: Slides generated from a prompt, Deep research reports, File and code tasks in a sandbox, Connectors to your apps (partial). Research, slides and sandboxed tasks, with Slack, Telegram and other chat bots; you run and configure it yourself.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Self-hosted with Docker (recommended) or a local dev setup | https://github.com/bytedance/deer-flow#deployment-sizing | 2026-10-16 |
| Code licence | Confirmed | MIT | https://github.com/bytedance/deer-flow/blob/main/LICENSE | 2026-10-16 |
| Model weights licence | Confirmed | No separate model weights; you bring model API keys or host a model yourself (vLLM supported) | https://github.com/bytedance/deer-flow#deployment-sizing | 2026-10-16 |
| Commercial use | Confirmed | Yes, MIT code; model and search provider terms apply separately | https://github.com/bytedance/deer-flow/blob/main/LICENSE | 2026-10-16 |
| Paid services needed? | Partial | Needs a model (API key or self-hosted) and a web search provider such as Tavily or InfoQuest; self-hosted fetchers exist | https://github.com/bytedance/deer-flow#configuration | 2026-10-16 |
| Hardware | Confirmed | Minimum 4 vCPU, 8 GB RAM, 20 GB free SSD for local use (more for Docker or shared servers); a local LLM is sized separately | https://github.com/bytedance/deer-flow#deployment-sizing | 2026-10-16 |
| Operating systems | Confirmed | Linux recommended for servers; macOS and Windows (Git Bash) for development or evaluation | https://github.com/bytedance/deer-flow#deployment-sizing | 2026-10-16 |
| Setup effort | Confirmed | Medium; make setup writes config, then make docker-start; needs Docker Compose v2.24+ and model and search keys | https://github.com/bytedance/deer-flow#option-1-docker-recommended | 2026-10-16 |

GitHub: 83939 stars, 11699 forks, last push 2026-10-16, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/deer-flow). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.