58,136 visible repositories in the index
625–648 of 1,006 · Most stars
The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
Portfolio optimization with deep learning.
TranslatedEvoOntology: A Self-Evolving Ontology Layer for Data Agents ⚙️ The EvoOntology plugin builds and evolves an ontology layer for Claude Code/Codex
Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)
Malcom - Malware Communications Analyzer
IntelMQ is a solution for IT security teams for collecting and processing security feeds using a message queuing protocol.
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
TranslatedImage-driven 3D scene generation system. Users provide a reference image and prompt words, and the system generates previewable, replayable, and traceable scene results according to the camera trajectory; official 3D demonstration assets allow direct viewing of color/depth animations and Gaussian point clouds in the browser. Image-driven 3D scene generation system
Cython implementation of Toolz: High performance functional utilities
OpenAI Gym environments for an open-source quadruped robot (SpotMicro)
Teaching tool and debugging aid in context of references, mutable data types, and shallow and deep copy.
Dataflow compiler for QNN inference on FPGAs
Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.
pickleDB is an in memory key-value store using Python's orjson module for persistence. It can also use SQLite instead of orjson if needed.
Python Performance Benchmark Suite
"Security Incidents In A Box!" A modular, menu-driven, cross-platform tool for building customized, time-delayed, distributed security events. Easily create custom event chains for Blue- & Red Team drills and sensor / alert mapping. Red Teams can create decoy incidents, distractions, and lures to support and scale their operations. Build event sequences ("narratives") to simulate realistic scenarios and generate corresponding network and filesystem artifacts.
Idol: a single image to 3D Gaussians. Inference SDK and demo.
EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluation code.
Scalable, event-driven, deep-learning-friendly backtesting library
[CONTRIBUTORS WELCOME] Generalized Additive Models in Python
Python package for graph statistics
Bitcart is a free and open-source self-hosted payment processor for BTC, LTC, BCH, XMR, ETH, TRX, USDT and more
Source-linked Claude 5.5 video workflows: Opus and Sonnet demos, separately labeled next-Fable testing reports, prompts, tools and production evidence.
High level network definitions with pre-trained weights in TensorFlow