TauricResearch/TradingAgents

TradingAgents: Multi-Agents LLM Financial Trading Framework

Python★ 106,305+745 that day#9 on trending

Analyzed September 15, 2026 at be952b8 (main) with jscpd 5.4.0 in 0.1s. Code duplication stayed at 1.34% across 2 appearances since Sep 10.

1.34%duplicated code · 156 of 11,674 lines

10clones in code

86code files of 157 scanned

1.19%duplicated over all files · 20 clones

The code number leaves out tests, fixtures, docs, examples, data files, styles, translations and vendored code.

Largest clones in the code

38 lines in 2 placespython141 tokens

tradingagents/agents/analysts/market_analyst.py:54–91tradingagents/agents/analysts/news_analyst.py:29–65

54    + """ Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read."""
55    + get_language_instruction()
56)
57
58prompt = ChatPromptTemplate.from_messages(
59    [
60        (
61            "system",
62            "You are a helpful AI assistant, collaborating with other assistants."
63            " Use the provided tools to progress towards answering the question."

First 10 of 38 lines.

36 lines in 2 placespython133 tokens

tradingagents/agents/analysts/fundamentals_analyst.py:30–65tradingagents/agents/analysts/market_analyst.py:56–91

30)
31
32prompt = ChatPromptTemplate.from_messages(
33    [
34        (
35            "system",
36            "You are a helpful AI assistant, collaborating with other assistants."
37            " Use the provided tools to progress towards answering the question."
38            " If you are unable to fully answer, that's OK; another assistant with different tools"
39            " will help where you left off. Execute what you can to make progress."

First 10 of 36 lines.

15 lines in 2 placespython67 tokens

tradingagents/agents/researchers/bear_researcher.py:16–30tradingagents/agents/researchers/bull_researcher.py:16–30

16)
17market_research_report = state["market_report"]
18sentiment_report = state["sentiment_report"]
19news_report = state["news_report"]
20fundamentals_report = state["fundamentals_report"]
21instrument_context = get_instrument_context_from_state(state)
22asset_type = state.get("asset_type", "stock")
23target_label = "stock" if asset_type == "stock" else "asset"
24fundamentals_label = (
25    "Company fundamentals report"

First 10 of 15 lines.

7 more

8 lines in 2 placespython66 tokens
tradingagents/agents/risk_mgmt/conservative_debator.py:33–40 tradingagents/agents/risk_mgmt/neutral_debator.py:33–40
8 lines in 2 placespython66 tokens
tradingagents/agents/utils/fundamental_data_tools.py:51–58 tradingagents/agents/utils/fundamental_data_tools.py:70–77
8 lines in 2 placespython65 tokens
tradingagents/agents/utils/fundamental_data_tools.py:32–39 tradingagents/agents/utils/fundamental_data_tools.py:51–58
14 lines in 2 placespython59 tokens
cli/main.py:339–352 cli/main.py:356–369
14 lines in 2 placespython56 tokens
tradingagents/agents/risk_mgmt/aggressive_debator.py:16–29 tradingagents/agents/risk_mgmt/conservative_debator.py:16–29
6 lines in 2 placespython56 tokens
tradingagents/llm_clients/openai_client.py:99–104 tradingagents/llm_clients/openai_client.py:149–154
9 lines in 2 placespython51 tokens
tradingagents/llm_clients/anthropic_client.py:45–53 tradingagents/llm_clients/google_client.py:12–20

Largest clones over all files, tests and data included

38 lines in 2 placespython141 tokens

tradingagents/agents/analysts/market_analyst.py:54–91tradingagents/agents/analysts/news_analyst.py:29–65

54    + """ Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read."""
55    + get_language_instruction()
56)
57
58prompt = ChatPromptTemplate.from_messages(
59    [
60        (
61            "system",
62            "You are a helpful AI assistant, collaborating with other assistants."
63            " Use the provided tools to progress towards answering the question."

First 10 of 38 lines.

11 lines in 2 placespythontests138 tokens

tests/test_cli_env_skip.py:52–62tests/test_cli_env_skip.py:125–135

52})
53
54with mock.patch.dict(os.environ, env, clear=False), \
55     mock.patch.object(m, "DEFAULT_CONFIG", fake_cfg), \
56     mock.patch.object(m, "fetch_announcements", return_value=None), \
57     mock.patch.object(m, "display_announcements"), \
58     mock.patch.object(m, "get_ticker", return_value="AAPL"), \
59     mock.patch.object(m, "get_analysis_date", return_value="2026-05-29"), \
60     mock.patch.object(m, "select_analysts", return_value=[]), \
61     mock.patch.object(m, "select_research_depth", return_value=1), \

First 10 of 11 lines.

36 lines in 2 placespython133 tokens

tradingagents/agents/analysts/fundamentals_analyst.py:30–65tradingagents/agents/analysts/market_analyst.py:56–91

30)
31
32prompt = ChatPromptTemplate.from_messages(
33    [
34        (
35            "system",
36            "You are a helpful AI assistant, collaborating with other assistants."
37            " Use the provided tools to progress towards answering the question."
38            " If you are unable to fully answer, that's OK; another assistant with different tools"
39            " will help where you left off. Execute what you can to make progress."

First 10 of 36 lines.

10 lines in 2 placespythontests121 tokens
tests/test_cli_env_skip.py:52–61 tests/test_cli_env_skip.py:95–104
7 lines in 2 placespythontests91 tokens
tests/test_cli_env_skip.py:104–110 tests/test_cli_env_skip.py:134–140

By format, code only

Format	Files	Lines	Clones	Duplicated lines	Duplication
python	76	10,856	10	156	1.44%
bash	9	644	0	0	0%
perl	1	174	0	0	0%

By format, all files

Format	Files	Lines	Clones	Duplicated lines	Duplication
python	139	18,501	20	243	1.31%
markdown	2	803	0	0	0%
bash	10	670	0	0	0%
perl	1	174	0	0	0%
yaml	2	97	0	0	0%
toml	1	88	0	0	0%
text	1	9	0	0	0%
txt	1	7	0	0	0%

Trending appearances

Day	Rank	Stars	Files	Lines	Clones	All files	Code	Health	Commit
Sep 15, 2026	#9	106,305 (+745)	157	20,349	20	1.19%	1.34%	—	`be952b8`
Sep 10, 2026	#6	104,143 (+367)	157	20,349	20	1.19%	1.34%	—	`be952b8`

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