DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
- benchmark
- calibration
- decision-making
- evaluation
Repository Index
47,133 repositories indexed
169–192 of 218 · Most stars
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
- agent-framework
- agentic-workflow
- aiforscience
- llm-agents
🔫 Python package for interacting with CS:GO Game Coordinator
- steam
- valve
- game-coordinator
- csgo
A Macau food recommendation Agent built on Thompson Sampling + StackedPareto weight fusion, with a full evaluation pipeline (5-fold CV, bootstrap CIs, stress tests) on 5,000 simulated users and 100k interactions. Competition entry for the QwenPaw AI Developer Challenge.
The repository host gives no description.
NitroFE is a Python feature engineering engine which provides a variety of modules designed to internally save past dependent values for providing continuous calculation.
- feature-engineering
- machine-learning
- feature
- features
Auto-optimizing a neural net (and its architecture) on the CIFAR-100 dataset. Could be easily transferred to another dataset or another classification task.
- hyperopt
- hyperparameter-optimization
- hyperparameter-tuning
- hyperparameters-optimization
Transformer-SRU LiDAR navigation for Unitree G1: Isaac Lab training, MuJoCo validation, and ROS 2 deployment.
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
GLM 5.3 Uncensored — 35 jailbreak prompt files, model guide and API access. One RouterHub key also covers GPT, Claude, DeepSeek, Qwen and Grok.
- abliterated-models
- ai-api
- ai-jailbreaks
- anthropic-compatible
A tool in Python to fix invalid GeoJSON objects and files
- geojson
- validation
- fix
- python
trycast parses JSON-like values whose shape is defined by TypedDicts and other standard Python type hints.
- parsing
- python
- typechecking
- runtime-typechecking
Pyramid addon for OpenAPI3 validation of requests and responses.
- pyramid-framework
- pyramid
- python
- openapi3
A Multilingual Latent Dirichlet Allocation (LDA) Pipeline with Stop Words Removal, n-gram features, and Inverse Stemming, in Python.
- lda
- multilingual
- machine-learning
- latent-dirichlet-allocation
🧙 meiga is a Python µframework that provides a simple, fully typed, monad-based result type ➡️ Result[Value, Error].
- monads
- result-type
- typing
- python
Data validator agains Splunk Common Information Model (CIM)
AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.
- ai-agents
- document-processing
- dspy
- entity-extraction
Convenient tools for using Swagger to define and validate your interfaces in a Pyramid webapp.
Lightweight DataFrame validation decorators for Pandas, Polars, Modin, and PyArrow. No custom types required.
A simple utility for the calculation and analysis of IP subnet values, designed to simplify network configuration tasks.
🗺️ List of GeoJSON invalid geometry issues with example files
flake8 plugin to validate annotations complexity
- flake8
- flake8-plugin
- complexity
Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous simulations. Evaluate with LLM judges.
- bland
- dspy
- livekit
- llm
Multi-stage Riemannian flow matching for physically valid molecular docking, with GNINA scoring, PoseBusters filtering, CLI inference, and benchmarks.
- alphafold3
- docking
- drug-design
- drug-discovery