The-Vibe-Company/Quivr

9.4

Adjusted Score

9.4

Raw Score

100%

Time Factor

2026-08-31

Last Push

39.5K

Stars

Python

Language

20.2K

Lines of Code

177

Files

137

Pattern Hits

2026-09-02

Scan Date

0.01

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 1MEDIUM 23LOW 113

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 137 distinct pattern matches across 13 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers49 hits · 52 pts

Severity	File	Line	Snippet	Context
LOW	core/tests/test_brain.py	14	def test_brain_empty_files_no_vectordb(fake_llm, embedder):	CODE
LOW	core/tests/test_brain.py	37	async def test_brain_from_files_success(	CODE
LOW	core/tests/test_brain.py	60	async def test_brain_from_langchain_docs(embedder, fake_llm, mem_vector_store):	CODE
LOW⚡	core/tests/test_utils.py	13	def test_model_supports_function_calling():	CODE
LOW⚡	core/tests/test_utils.py	18	def test_get_prev_message_incorrect_message():	CODE
LOW⚡	core/tests/test_utils.py	27	def test_get_prev_message_str():	CODE
LOW	core/tests/test_utils.py	44	def test_parse_chunk_response_nofunc_calling():	CODE
LOW	core/tests/test_utils.py	62	def test_parse_chunk_response_func_calling(chunks_stream_answer):	CODE
LOW	core/tests/test_chat_history.py	19	def test_chat_history_constructor():	CODE
LOW	core/tests/test_chat_history.py	37	def test_chat_history_get_history(ai_message: AIMessage, human_message: HumanMessage):	CODE
LOW	core/tests/test_chat_history.py	56	def test_chat_history_iter_pairs_invalid(	CODE
LOW	core/tests/test_chat_history.py	66	def test_chat_history_iter_pais(ai_message: AIMessage, human_message: HumanMessage):	CODE
LOW	core/tests/test_llm_endpoint.py	11	def test_llm_endpoint_from_config_default():	CODE
LOW	core/tests/test_llm_endpoint.py	29	def test_llm_endpoint_from_config():	CODE
LOW	core/tests/test_llm_endpoint.py	42	def test_llm_endpoint_constructor():	CODE
LOW	core/tests/test_config.py	21	def test_default_retrievalconfig():	CODE
LOW	core/tests/test_quivr_file.py	25	def test_create_file_add_metadata():	CODE
LOW	core/tests/processor/test_registry.py	26	def test_get_default_processors_cls():	CODE
LOW	core/tests/processor/test_registry.py	38	def test_get_default_processors_cls_core():	CODE
LOW	core/tests/processor/test_registry.py	46	def test_append_proc_mapping_empty():	CODE
LOW	core/tests/processor/test_registry.py	63	def test_append_proc_mapping_priority():	CODE
LOW⚡	core/tests/processor/test_registry.py	142	def test_get_processor_cls_import_error(caplog):	CODE
LOW⚡	core/tests/processor/test_registry.py	150	def test_get_processor_cls_error():	CODE
LOW⚡	core/tests/processor/test_registry.py	156	def test_register_new_proc_noappend():	CODE
LOW⚡	core/tests/processor/test_registry.py	162	def test_register_new_proc_append(caplog):	CODE
LOW	core/tests/processor/test_registry.py	191	def test_register_non_processor():	CODE
LOW	core/tests/processor/test_registry.py	199	def test_register_override_proc():	CODE
LOW	core/tests/processor/test_registry.py	215	def test_register_override_error():	CODE
LOW	core/tests/processor/test_registry.py	233	def test_available_processors():	CODE
LOW	core/tests/processor/test_simple_txt_processor.py	11	def test_recursive_character_splitter():	CODE
LOW	core/tests/processor/test_tika_processor.py	18	async def test_send_parse_tika_exception(quivr_pdf):	CODE
LOW	…tests/processor/pdf/test_unstructured_pdf_processor.py	14	async def test_unstructured_pdf_processor():	CODE
LOW	…tests/processor/pdf/test_unstructured_pdf_processor.py	34	async def test_unstructured_pdf_processor_fail(ext):	CODE
LOW	…e/tests/processor/community/test_markdown_processor.py	30	async def test_markdown_processor_fail(quivr_txt):	CODE
LOW	core/quivr_core/llm/llm_endpoint.py	66	def _calculate_tokenizer_size(self) -> int:	CODE
LOW	…core/processor/implementations/simple_txt_processor.py	12	def recursive_character_splitter(	CODE
LOW	core/quivr_core/rag/quivr_rag_langgraph.py	198	def has_non_completable_tasks(self) -> bool:	CODE
LOW	core/quivr_core/rag/quivr_rag_langgraph.py	521	def filter_chunks_by_relevance(self, chunks: List[Document], **kwargs):	CODE
LOW	core/quivr_core/rag/quivr_rag_langgraph.py	770	async def retrieve_full_documents_context(self, state: AgentState) -> AgentState:	CODE
LOW	core/quivr_core/rag/quivr_rag_langgraph.py	1157	def _is_final_node_and_chat_model_stream(self, event: StreamEvent) -> bool:	CODE
LOW	core/quivr_core/rag/quivr_rag_langgraph.py	1175	async def ainvoke_structured_output(	CODE
LOW	core/quivr_core/rag/utils.py	26	def model_supports_function_calling(model_name: str):	CODE
LOW	core/quivr_core/rag/utils.py	32	def format_history_to_openai_mesages(	CODE
LOW	core/quivr_core/rag/utils.py	117	def get_answers_from_tool_calls(tool_calls):	CODE
LOW	core/quivr_core/rag/entities/config.py	24	def normalize_to_env_variable_name(name: str) -> str:	CODE
LOW	core/quivr_core/rag/entities/config.py	281	def get_supplier_by_model_name(cls, model: str) -> DefaultModelSuppliers \| None:	CODE
LOW	core/quivr_core/rag/entities/config.py	510	def resolve_special_edges_in_name_and_edges(self):	CODE
LOW	core/quivr_core/rag/entities/config.py	563	def check_first_node_is_start(self):	CODE
LOW	core/quivr_core/brain/brain.py	402	async def afrom_langchain_documents(	CODE

Decorative Section Separators16 hits · 41 pts

Severity	File	Line	Snippet	Context
MEDIUM	core/quivr_core/rag/prompts.py	33	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	core/quivr_core/rag/prompts.py	35	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	core/quivr_core/rag/prompts.py	57	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	core/quivr_core/rag/prompts.py	59	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	core/quivr_core/rag/prompts.py	111	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	core/quivr_core/rag/prompts.py	113	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	core/quivr_core/rag/prompts.py	119	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	core/quivr_core/rag/prompts.py	121	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	core/quivr_core/rag/prompts.py	142	# ---------------------------------------------------------------------------	STRING
MEDIUM	core/quivr_core/rag/prompts.py	144	# ---------------------------------------------------------------------------	STRING
MEDIUM	core/quivr_core/rag/prompts.py	166	# ---------------------------------------------------------------------------	STRING
MEDIUM	core/quivr_core/rag/prompts.py	168	# ---------------------------------------------------------------------------	STRING
MEDIUM	core/quivr_core/rag/prompts.py	196	# ---------------------------------------------------------------------------	STRING
MEDIUM	core/quivr_core/rag/prompts.py	198	# ---------------------------------------------------------------------------	STRING
MEDIUM	core/quivr_core/rag/prompts.py	233	# ---------------------------------------------------------------------------	STRING
MEDIUM	core/quivr_core/rag/prompts.py	235	# ---------------------------------------------------------------------------	STRING

Fake / Example Data22 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW	examples/chatbot/.chainlit/translations/mr.json	125	"placeholder": "\u0924\u0941\u092e\u091a\u093e \u092e\u0947\u0938\u0947\u091c \u0907\u0925\u0947	CODE
LOW	examples/chatbot/.chainlit/translations/bn.json	125	"placeholder": "\u098f\u0996\u09be\u09a8\u09c7 \u0986\u09aa\u09a8\u09be\u09b0 \u09ac\u09be\u09b0	CODE
LOW	examples/chatbot/.chainlit/translations/ta.json	125	"placeholder": "\u0b89\u0b99\u0bcd\u0b95\u0bb3\u0bcd \u0b9a\u0bc6\u0baf\u0bcd\u0ba4\u0bbf\u0baf\	CODE
LOW	examples/chatbot/.chainlit/translations/zh-CN.json	123	"placeholder": "\u5728\u8fd9\u91cc\u8f93\u5165\u60a8\u7684\u6d88\u606f..."	CODE
LOW	examples/chatbot/.chainlit/translations/ml.json	125	"placeholder": "\u0d28\u0d3f\u0d19\u0d4d\u0d19\u0d33\u0d41\u0d1f\u0d46 \u0d38\u0d28\u0d4d\u0d26\	CODE
LOW	examples/chatbot/.chainlit/translations/kn.json	125	"placeholder": "\u0ca8\u0cbf\u0cae\u0ccd\u0cae \u0cb8\u0c82\u0ca6\u0cc7\u0cb6\u0cb5\u0ca8\u0ccd\	CODE
LOW	examples/chatbot/.chainlit/translations/gu.json	125	"placeholder": "\u0aa4\u0aae\u0abe\u0ab0\u0acb \u0ab8\u0a82\u0aa6\u0ac7\u0ab6\u0acb \u0a85\u0ab9	CODE
LOW	examples/chatbot/.chainlit/translations/hi.json	125	"placeholder": "\u0905\u092a\u0928\u093e \u0938\u0902\u0926\u0947\u0936 \u092f\u0939\u093e\u0901	CODE
LOW	examples/chatbot/.chainlit/translations/te.json	125	"placeholder": "\u0c2e\u0c40 \u0c38\u0c02\u0c26\u0c47\u0c36\u0c3e\u0c28\u0c4d\u0c28\u0c3f \u0c07	CODE
LOW	examples/chatbot/.chainlit/translations/he-IL.json	125	"placeholder": "\u05db\u05ea\u05d5\u05d1 \u05d4\u05d5\u05d3\u05e2\u05d4 \u05db\u05d0\u05df..."	CODE
LOW	examples/chatbot/.chainlit/translations/en-US.json	123	"placeholder": "Type your message here..."	CODE
LOW	examples/chatbot_voice/.chainlit/translations/mr.json	125	"placeholder": "\u0924\u0941\u092e\u091a\u093e \u092e\u0947\u0938\u0947\u091c \u0907\u0925\u0947	CODE
LOW	examples/chatbot_voice/.chainlit/translations/bn.json	125	"placeholder": "\u098f\u0996\u09be\u09a8\u09c7 \u0986\u09aa\u09a8\u09be\u09b0 \u09ac\u09be\u09b0	CODE
LOW	examples/chatbot_voice/.chainlit/translations/ta.json	125	"placeholder": "\u0b89\u0b99\u0bcd\u0b95\u0bb3\u0bcd \u0b9a\u0bc6\u0baf\u0bcd\u0ba4\u0bbf\u0baf\	CODE
LOW	…amples/chatbot_voice/.chainlit/translations/zh-CN.json	123	"placeholder": "\u5728\u8fd9\u91cc\u8f93\u5165\u60a8\u7684\u6d88\u606f..."	CODE
LOW	examples/chatbot_voice/.chainlit/translations/ml.json	125	"placeholder": "\u0d28\u0d3f\u0d19\u0d4d\u0d19\u0d33\u0d41\u0d1f\u0d46 \u0d38\u0d28\u0d4d\u0d26\	CODE
LOW	examples/chatbot_voice/.chainlit/translations/kn.json	125	"placeholder": "\u0ca8\u0cbf\u0cae\u0ccd\u0cae \u0cb8\u0c82\u0ca6\u0cc7\u0cb6\u0cb5\u0ca8\u0ccd\	CODE
LOW	examples/chatbot_voice/.chainlit/translations/gu.json	125	"placeholder": "\u0aa4\u0aae\u0abe\u0ab0\u0acb \u0ab8\u0a82\u0aa6\u0ac7\u0ab6\u0acb \u0a85\u0ab9	CODE
LOW	examples/chatbot_voice/.chainlit/translations/hi.json	125	"placeholder": "\u0905\u092a\u0928\u093e \u0938\u0902\u0926\u0947\u0936 \u092f\u0939\u093e\u0901	CODE
LOW	examples/chatbot_voice/.chainlit/translations/te.json	125	"placeholder": "\u0c2e\u0c40 \u0c38\u0c02\u0c26\u0c47\u0c36\u0c3e\u0c28\u0c4d\u0c28\u0c3f \u0c07	CODE
LOW	…amples/chatbot_voice/.chainlit/translations/he-IL.json	125	"placeholder": "\u05db\u05ea\u05d5\u05d1 \u05d4\u05d5\u05d3\u05e2\u05d4 \u05db\u05d0\u05df..."	CODE
LOW	…amples/chatbot_voice/.chainlit/translations/en-US.json	123	"placeholder": "Type your message here..."	CODE

Modern AI Meta-Vocabulary5 hits · 16 pts

Severity	File	Line	Snippet	Context
MEDIUM	README.md	80	#### Basic RAG	COMMENT
MEDIUM⚡	core/quivr_core/rag/prompts.py	58	# Prompt for RAG	COMMENT
MEDIUM	core/quivr_core/brain/brain.py	132	# RAG dependencies:	COMMENT
MEDIUM	docs/docs/workflows/examples/basic_rag.md	1	# Basic RAG	COMMENT
MEDIUM	docs/docs/workflows/examples/rag_with_web_search.md	1	# RAG with web search	COMMENT

Redundant / Tautological Comments9 hits · 14 pts

Severity	File	Line	Snippet	Context
LOW	core/quivr_core/llm/llm_endpoint.py	101	# Check if adding this would exceed either cache limit	COMMENT
LOW	core/quivr_core/llm/llm_endpoint.py	162	# Check if the model name matches or starts with the base model name	COMMENT
LOW	core/quivr_core/rag/quivr_rag_langgraph.py	980	# Check if there is a system message in messages	COMMENT
LOW	core/quivr_core/rag/entities/config.py	28	# Check if the normalized name starts with a digit	COMMENT
LOW	core/quivr_core/rag/entities/config.py	284	# Check if the model name or a base part of the model name is in the supplier's models	COMMENT
LOW	core/quivr_core/rag/entities/config.py	353	# Check if the corresponding API key environment variable is set	COMMENT
LOW	core/quivr_core/rag/entities/config.py	458	# Check if the corresponding API key environment variable is set	COMMENT
LOW	examples/simple_question_megaparse.py	33	# Check if user wants to exit	COMMENT
LOW	examples/pdf_parsing_tika.py	30	# Check if user wants to exit	COMMENT

Deep Nesting12 hits · 12 pts

Severity	File	Line	Context
LOW	core/quivr_core/__init__.py	9	CODE
LOW	core/quivr_core/llm/llm_endpoint.py	145	CODE
LOW	core/quivr_core/llm/llm_endpoint.py	212	CODE
LOW	core/quivr_core/rag/quivr_rag_langgraph.py	393	CODE
LOW	core/quivr_core/rag/quivr_rag_langgraph.py	844	CODE
LOW	core/quivr_core/rag/quivr_rag_langgraph.py	1164	CODE
LOW	core/quivr_core/rag/utils.py	130	CODE
LOW	core/quivr_core/rag/quivr_rag.py	188	CODE
LOW	core/quivr_core/rag/entities/config.py	478	CODE
LOW	core/quivr_core/rag/entities/config.py	510	CODE
LOW	core/quivr_core/rag/entities/config.py	574	CODE
LOW	core/quivr_core/brain/brain.py	47	CODE

Unused Imports7 hits · 7 pts

Severity	File	Line	Context
LOW	core/quivr_core/__init__.py	3	CODE
LOW	core/quivr_core/__init__.py	4	CODE
LOW	core/quivr_core/llm/__init__.py	1	CODE
LOW	core/quivr_core/files/__init__.py	1	CODE
LOW	core/quivr_core/brain/__init__.py	1	CODE
LOW	examples/quivr-whisper/app.py	5	CODE
LOW	examples/quivr-whisper/app.py	8	CODE

Over-Commented Block7 hits · 7 pts

Severity	File	Line	Snippet	Context
LOW	docs/docs/vectorstores/pgvector.md	1	# PGVector	COMMENT
LOW	docs/docs/vectorstores/faiss.md	1	# Faiss	COMMENT
LOW	docs/docs/examples/index.md	1	# Examples	COMMENT
LOW	examples/chatbot/basic_rag_workflow.yaml	21	# Maximum number of previous conversation iterations	COMMENT
LOW	examples/chatbot/.chainlit/config.toml	61	# Large size content are by default collapsed for a cleaner ui	COMMENT
LOW	examples/chatbot_voice/basic_rag_workflow.yaml	21	max_history: 10	COMMENT
LOW	examples/chatbot_voice/.chainlit/config.toml	61	# Large size content are by default collapsed for a cleaner ui	COMMENT

Self-Referential Comments2 hits · 6 pts

Severity	File	Line	Snippet	Context
MEDIUM	core/scripts/run_tests_buildx.sh	19	# Create the builder if it doesn't exist	COMMENT
MEDIUM	core/quivr_core/rag/quivr_rag_langgraph.py	658	# Create a tuple of the retrieval task and task_id	COMMENT

Docstring Block Structure1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	core/quivr_core/brain/brain.py	50	Process files in storage. This function takes a StorageBase and return a list of langchain documents. Args:	STRING

Modern Structural Boilerplate4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	core/quivr_core/__init__.py	6	__all__ = ["Brain", "registry", "register_processor"]	CODE
LOW	core/quivr_core/llm/__init__.py	3	__all__ = ["LLMEndpoint"]	CODE
LOW	core/quivr_core/files/__init__.py	3	__all__ = ["QuivrFile"]	CODE
LOW	core/quivr_core/brain/__init__.py	3	__all__ = ["Brain"]	CODE

Excessive Try-Catch Wrapping2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	core/quivr_core/llm/llm_endpoint.py	185	except Exception as e:	CODE
LOW	…quivr_core/processor/implementations/tika_processor.py	62	except Exception as e:	CODE

AI Structural Patterns1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	core/quivr_core/rag/quivr_rag.py	186		CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings