bytedance/deer-flow

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

Python★ 81,925+195 that day#6 on trending

Analyzed September 8, 2026 at 23bd760 (main) with jscpd 5.4.0 in 15.8s.

1.86%duplicated code · 4,647 of 250,044 lines

387clones in code

1,062code files of 2,543 scanned

6.02%duplicated over all files · 3,181 clones

The code number leaves out tests, fixtures, docs, examples, data files, styles, translations and vendored code, and 1 generated file: backend/packages/harness/deerflow/tools/types.py.

Largest clones in the code

11 lines in 3 placespython121 tokens

backend/packages/harness/deerflow/community/exa/tools.py:56–66backend/packages/harness/deerflow/community/infoquest/tools.py:58–68backend/packages/harness/deerflow/community/tavily/tools.py:48–58

56@tool("web_fetch", parse_docstring=True)
57def web_fetch_tool(url: str) -> str:
58    """Fetch the contents of a web page at a given URL.
59    Only fetch EXACT URLs that have been provided directly by the user or have been returned in results from the web_search and web_fetch tools.
60    This tool can NOT access content that requires authentication, such as private Google Docs or pages behind login walls.
61    Do NOT add www. to URLs that do NOT have them.
62    URLs must include the schema: https://example.com is a valid URL while example.com is an invalid URL.
63
64    Args:
65        url: The URL to fetch the contents of.

First 10 of 11 lines.

25 lines in 2 placespython225 tokens

backend/scripts/benchmark/checkpoint/summarize_channels.py:138–162backend/scripts/benchmark/checkpoint/summarize_production.py:141–165

138        summaries.append(summary)
139    return summaries
140
141
142def _columns(rows: list[dict[str, Any]]) -> list[str]:
143    preferred = [*_GROUP_FIELDS, "paired_repetitions", "failed_rows"]
144    extras = sorted({key for row in rows for key in row if key not in preferred})
145    return [field for field in preferred if any(field in row for row in rows)] + extras
146
147

First 10 of 25 lines.

31 lines in 2 placespython222 tokens

backend/packages/harness/deerflow/community/fastcrw/tools.py:63–93backend/packages/harness/deerflow/community/firecrawl/tools.py:30–60

63client = _get_fastcrw_client("web_search")
64result = client.search(query, limit=max_results)
65
66# result.web contains list of SearchResultWeb objects
67web_results = result.web or []
68normalized_results = [
69    {
70        "title": getattr(item, "title", "") or "",
71        "url": getattr(item, "url", "") or "",
72        "snippet": getattr(item, "description", "") or "",

First 10 of 31 lines.

7 more

10 lines in 5 placespython55 tokens
backend/app/gateway/routers/mcp.py:1492–1501 backend/app/gateway/routers/mcp.py:1516–1524 backend/app/gateway/routers/mcp.py:1542–1550 backend/app/gateway/routers/mcp.py:1564–1572 backend/app/gateway/routers/mcp.py:1586–1594
9 lines in 5 placespython54 tokens
backend/packages/harness/deerflow/agents/memory/backends/deermem/deer_mem.py:326–334 backend/packages/harness/deerflow/agents/memory/backends/honcho/honcho_manager.py:216–224 backend/packages/harness/deerflow/agents/memory/backends/honcho/honcho_manager.py:296–304 backend/packages/harness/deerflow/agents/memory/backends/mem0/mem0_manager.py:258–266 backend/packages/harness/deerflow/agents/memory/backends/noop/noop_manager.py:128–136
33 lines in 2 placespython212 tokens
backend/packages/harness/deerflow/community/brave/tools.py:102–134 backend/packages/harness/deerflow/community/serper/tools.py:94–126
12 lines in 4 placespython67 tokens
backend/packages/harness/deerflow/agents/memory/backends/deermem/deermem/core/updater.py:1475–1486 backend/packages/harness/deerflow/agents/memory/backends/deermem/deermem/core/updater.py:1505–1516 backend/packages/harness/deerflow/agents/memory/backends/deermem/deermem/core/updater.py:1600–1611 backend/packages/harness/deerflow/agents/memory/backends/deermem/deermem/core/updater.py:1779–1790
7 lines in 4 placespython67 tokens
backend/packages/harness/deerflow/persistence/agents/model.py:36–42 backend/packages/harness/deerflow/persistence/managed_subagents/model.py:18–24 backend/packages/harness/deerflow/persistence/mcp_tasks/model.py:61–67 backend/packages/harness/deerflow/persistence/scheduled_tasks/model.py:33–39
19 lines in 4 placestypescript64 tokens
frontend/src/core/integrations/lark/api.ts:75–93 frontend/src/core/integrations/lark/api.ts:97–115 frontend/src/core/integrations/lark/api.ts:119–137 frontend/src/core/integrations/lark/api.ts:141–159
11 lines in 3 placespython86 tokens
backend/app/gateway/routers/integrations.py:320–330 backend/app/gateway/routers/integrations.py:368–378 backend/app/gateway/routers/integrations.py:393–403

Largest clones over all files, tests and data included

410 lines in 2 placesmarkdowndocs and examples8,943 tokens

CHANGELOG.md:1613–2022CHANGELOG_zh.md:1092–1501

1613  label thrash. ([#3455])
1614
1615[2.0.0]: https://github.com/bytedance/deer-flow/releases/tag/v2.0.0
1616
1617[#2329]: https://github.com/bytedance/deer-flow/pull/2329
1618[#2556]: https://github.com/bytedance/deer-flow/pull/2556
1619[#2582]: https://github.com/bytedance/deer-flow/pull/2582
1620[#2583]: https://github.com/bytedance/deer-flow/pull/2583
1621[#2584]: https://github.com/bytedance/deer-flow/pull/2584
1622[#2585]: https://github.com/bytedance/deer-flow/pull/2585

First 10 of 410 lines.

94 lines in 2 placesmarkdowndocs and examples2,068 tokens

CHANGELOG.md:2023–2116CHANGELOG_zh.md:1501–1594

2023[#4181]: https://github.com/bytedance/deer-flow/pull/4181
2024[#4187]: https://github.com/bytedance/deer-flow/pull/4187
2025[#4188]: https://github.com/bytedance/deer-flow/pull/4188
2026[#4190]: https://github.com/bytedance/deer-flow/pull/4190
2027[#4192]: https://github.com/bytedance/deer-flow/issues/4192
2028[#4193]: https://github.com/bytedance/deer-flow/pull/4193
2029[#4197]: https://github.com/bytedance/deer-flow/pull/4197
2030[#4199]: https://github.com/bytedance/deer-flow/pull/4199
2031[#4202]: https://github.com/bytedance/deer-flow/pull/4202
2032[#4203]: https://github.com/bytedance/deer-flow/pull/4203

First 10 of 94 lines.

91 lines in 2 placesmarkdowndocs and examples1,982 tokens

CHANGELOG.md:2293–2383CHANGELOG_zh.md:1772–1862

2293[#4852]: https://github.com/bytedance/deer-flow/pull/4852
2294[#4853]: https://github.com/bytedance/deer-flow/pull/4853
2295[#4860]: https://github.com/bytedance/deer-flow/pull/4860
2296[#4861]: https://github.com/bytedance/deer-flow/pull/4861
2297[#4863]: https://github.com/bytedance/deer-flow/pull/4863
2298[#4865]: https://github.com/bytedance/deer-flow/pull/4865
2299[#4868]: https://github.com/bytedance/deer-flow/pull/4868
2300[#4877]: https://github.com/bytedance/deer-flow/pull/4877
2301[#4882]: https://github.com/bytedance/deer-flow/pull/4882
2302[#4887]: https://github.com/bytedance/deer-flow/pull/4887

First 10 of 91 lines.

18 lines in 37 placesjsondocs and examples53 tokens
frontend/public/demo/threads/3823e443-4e2b-4679-b496-a9506eae462b/thread.json:804–821 frontend/public/demo/threads/3823e443-4e2b-4679-b496-a9506eae462b/thread.json:902–919 frontend/public/demo/threads/4f3e55ee-f853-43db-bfb3-7d1a411f03cb/thread.json:371–388 frontend/public/demo/threads/4f3e55ee-f853-43db-bfb3-7d1a411f03cb/thread.json:509–526 frontend/public/demo/threads/4f3e55ee-f853-43db-bfb3-7d1a411f03cb/thread.json:607–624and 32 more
187 lines in 2 placestxtdocs and examples1,758 tokens
frontend/src/components/workspace/channels/buzz-provider-icon.LICENSE.txt:1–187 skills/public/skill-creator/LICENSE.txt:2–188

By format, code only

Format	Files	Lines	Clones	Duplicated lines	Duplication
python	639	183,868	321	3,624	1.97%
tsx	199	39,244	35	597	1.52%
typescript	175	20,740	26	357	1.72%
bash	39	4,805	5	69	1.44%
javascript	8	852	0	0	0%
jsx	1	361	0	0	0%
perl	1	174	0	0	0%

By format, all files

Format	Files	Lines	Clones	Duplicated lines	Duplication
python	1,363	485,052	2,573	31,356	6.46%
typescript	366	59,114	250	3,513	5.94%
json	55	16,501	154	3,309	20.05%
markdown	215	56,704	67	1,580	2.79%
tsx	226	42,183	38	649	1.54%
yaml	105	9,029	32	446	4.94%
bash	89	6,792	21	245	3.61%
text	61	1,684	18	91	5.4%
css	6	4,640	13	117	2.52%
markup	13	6,788	11	123	1.81%

Trending appearances

Day	Rank	Stars	Files	Lines	Clones	All files	Code	Health	Commit
Sep 8, 2026	#6	81,925 (+195)	2,543	695,216	3,181	6.02%	1.86%	—	`23bd760`

Want this for your own project? Install jscpd and run jscpd ., or measure it the way the baselines were measured.