NirDiamant/agents-towards-production

20.8

Adjusted Score

20.8

Raw Score

100%

Time Factor

2026-07-04

Last Push

21.0K

Stars

Jupyter Notebook

Language

5.3K

Lines of Code

Files

Pattern Hits

2026-07-14

Scan Date

0.12

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

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

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 6MEDIUM 15LOW 28

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 49 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.

Self-Referential Comments7 hits · 24 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tutorials/fastapi-agent/scripts/fastapi_agent.py	61	# Create an instance of our agent	COMMENT
MEDIUM⚡	tutorials/fastapi-agent/scripts/fastapi_agent.py	70	# Create a synchronous endpoint for the agent	COMMENT
MEDIUM⚡	tutorials/fastapi-agent/scripts/fastapi_agent.py	77	# Create a streaming endpoint for the agent	COMMENT
MEDIUM	…d-gpu-deploy/crew-ai-ollama-runpod-tutorial/handler.py	12	# Create a pseudo-research tool that returns fake information	COMMENT
MEDIUM	…d-gpu-deploy/crew-ai-ollama-runpod-tutorial/handler.py	82	# Create the task for our topic	COMMENT
MEDIUM	…d-gpu-deploy/crew-ai-ollama-runpod-tutorial/handler.py	99	# Create the crew with just our blog writer	STRING
MEDIUM	tutorials/agent-with-streamlit-ui/app.py	36	# Define a function to generate a response from the AI given a user message	COMMENT

Magic Placeholder Names3 hits · 18 pts

Severity	File	Line	Snippet	Context
HIGH	tutorials/runpod-gpu-deploy/README.md	271	--header "authorization: [YOUR_API_KEY]" \	CODE
HIGH	…od-gpu-deploy/crew-ai-ollama-runpod-tutorial/README.md	79	--header "authorization: [YOUR_API_KEY]" \	CODE
HIGH	tutorials/agent-with-streamlit-ui/app.py	17	# client = openai.OpenAI(api_key="sk-your-api-key") # (Not recommended to hard-code in real apps)	COMMENT

Cross-File Repetition3 hits · 15 pts

Severity	File	Snippet	Context
HIGH	tutorials/runpod-gpu-deploy/README.md	creates a blog post on the given topic using crewai	STRING
HIGH	…d-gpu-deploy/crew-ai-ollama-runpod-tutorial/handler.py	creates a blog post on the given topic using crewai	STRING
HIGH	…od-gpu-deploy/crew-ai-ollama-runpod-tutorial/README.md	creates a blog post on the given topic using crewai	STRING

Modern AI Meta-Vocabulary4 hits · 12 pts

Severity	File	Line	Snippet	Context
MEDIUM	README.md	375	### 🔍 RAG & Knowledge Management	COMMENT
MEDIUM	README.md	664	# Example: Multi-tool agent orchestration	COMMENT
MEDIUM	tutorials/agent-RAG-with-Contextual/requirements.txt	2	# Production-Ready RAG Agents with Contextual AI	COMMENT
MEDIUM	tutorials/agent-RAG-with-Contextual/README.md	3	# Production-Ready RAG Agents with Contextual AI	COMMENT

Excessive Try-Catch Wrapping7 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	tutorials/fastapi-agent/run_server.py	21	except Exception as e:	CODE
MEDIUM	tutorials/fastapi-agent/run_server.py	22	print(f"Error running server: {e}")	CODE
LOW	tutorials/runpod-gpu-deploy/README.md	126	except Exception as e:	CODE
LOW	…d-gpu-deploy/crew-ai-ollama-runpod-tutorial/handler.py	128	except Exception as e:	CODE
LOW	…od-gpu-deploy/crew-ai-ollama-runpod-tutorial/README.md	155	except Exception as e:	CODE
LOW	tutorials/agent-security-apex/model_testing_tools.py	73	except Exception as e:	CODE
MEDIUM	tutorials/agent-security-apex/model_testing_tools.py	74	print(f"Error loading CSV file: {e}")	CODE

Structural Annotation Overuse7 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	…torials/ai-memory-with-cognee/guido_contributions.html	40	var nodes = [{"name": "", "type": "DocumentChunk", "ontology_valid": false, "version": 1, "topological_rank"	CODE
LOW⚡	…ls/ai-memory-with-cognee/data/guido_contributions.json	194	"before_code": " if literal(expr) == LITERAL_TYPE:\n vartype = type_map[expr]\	CODE
LOW⚡	…ls/ai-memory-with-cognee/data/guido_contributions.json	195	"after_code": " if literal(expr) == LITERAL_TYPE:\n vartype = type_map[expr]\n	CODE
LOW⚡	…ls/ai-memory-with-cognee/data/guido_contributions.json	196	"diff_context": " if literal(expr) == LITERAL_TYPE:\n vartype = type_map[expr]	CODE
LOW	tutorials/kotlin-agent-with-koog/tutorial.md	160	## Step 1: Your First AI Agent	COMMENT
LOW	tutorials/kotlin-agent-with-koog/tutorial.md	230	## Step 2: Adding Tools to the Agent	COMMENT
LOW	tutorials/kotlin-agent-with-koog/tutorial.md	364	## Step 3: Structured Output	STRING

Unused Imports6 hits · 6 pts

Severity	File	Line	Context
LOW	tutorials/fastapi-agent/scripts/fastapi_agent.py	1	CODE
LOW	tutorials/fastapi-agent/scripts/fastapi_agent.py	1	CODE
LOW	tutorials/fastapi-agent/scripts/fastapi_agent.py	1	CODE
LOW	tutorials/fastapi-agent/scripts/fastapi_agent.py	6	CODE
LOW	…d-gpu-deploy/crew-ai-ollama-runpod-tutorial/handler.py	6	CODE
LOW	tutorials/agent-with-streamlit-ui/app.py	6	CODE

Decorative Section Separators2 hits · 6 pts

Severity	File	Line	Snippet	Context
MEDIUM	tutorials/kotlin-agent-with-koog/run.sh	2	# -------------------------------------------------------	COMMENT
MEDIUM	tutorials/kotlin-agent-with-koog/run.sh	5	# -------------------------------------------------------	COMMENT

Verbosity Indicators4 hits · 6 pts

Severity	File	Line	Snippet	Context
LOW	…torials/ai-memory-with-cognee/guido_contributions.html	40	var nodes = [{"name": "", "type": "DocumentChunk", "ontology_valid": false, "version": 1, "topological_rank"	CODE
LOW⚡	…ls/ai-memory-with-cognee/data/guido_contributions.json	194	"before_code": " if literal(expr) == LITERAL_TYPE:\n vartype = type_map[expr]\	CODE
LOW⚡	…ls/ai-memory-with-cognee/data/guido_contributions.json	195	"after_code": " if literal(expr) == LITERAL_TYPE:\n vartype = type_map[expr]\n	CODE
LOW⚡	…ls/ai-memory-with-cognee/data/guido_contributions.json	196	"diff_context": " if literal(expr) == LITERAL_TYPE:\n vartype = type_map[expr]	CODE

Over-Commented Block2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	tutorials/docker-intro/README.md	401	#1 transferring context: 2B done	COMMENT
LOW	tutorials/kotlin-agent-with-koog/tutorial.md	181	// "suspend fun main()" is Kotlin's way of writing an async main function.	COMMENT

Hyper-Verbose Identifiers2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	tutorials/agent-security-apex/model_testing_tools.py	16	async def generate_chatgpt_response(client: AsyncOpenAI, prompt, system_prompt):	CODE
LOW	tutorials/agent-security-apex/model_testing_tools.py	49	def check_password_in_response(response):	CODE

Redundant / Tautological Comments1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	tutorials/agent-security-apex/model_testing_tools.py	139	# Check if encoding succeeded where unencoded failed	COMMENT

Deep Nesting1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	…rials/agent-security-apex/prompt_manipulation_tools.py	1		CODE