HumanEvalHumanEval is OpenAI's open-source benchmark of 164 hand-written Python problems for evaluating large language models on code generation using functional correctness.(0)0
llama.cppRun large language models locally with llama.cpp — a high-performance, open-source C/C++ inference engine supporting CUDA, Metal, Vulkan, and GGUF quantization for 50+ model architectures.(0)0
Flagsmith AI Feature FlagFlagsmith makes it easy to create and manage feature flags across web, mobile, and server-side apps. Roll out safely with segmentation, A/B testing, and remote config—cloud or self-hosted.(0)0
BabyAGIBabyAGI is a pioneering open-source framework for self-building autonomous AI agents that plan, prioritize, and execute tasks using large language models.(0)0
NanoCallerNanoCaller is an open-source deep convolutional neural network tool for SNP and indel variant calling from long-read sequencing data, using haplotype-aware pileup analysis.(0)0
AI VerifyAI Verify is an open-source toolkit for testing AI systems against responsible AI principles. Covers fairness, explainability, robustness, and safety compl(0)0
Microsoft Accessibility InsightsAccessibility Insights is a free, open-source toolset from Microsoft for testing WCAG 2.1 AA compliance in web apps and Windows applications before they reach customers.(0)0
LiteLLM ProxyLiteLLM Proxy is an open-source LLM gateway that provides a single OpenAI-compatible API to manage authentication, load balancing, and spend tracking across 100+ LLM providers.(0)0
Windmill AI WorkflowWindmill is an open-source, self-hostable workflow orchestration platform for developers. Build internal tools, data pipelines, and automation workflows in 20+ languages with AI assistance, Git collaboration, and enterprise-grade security.(0)0
Text Generation WebUIRun large language models locally with Text Generation WebUI — supports text, vision, tool-calling, and fine-tuning. 100% offline, open source, and private.(0)0
