LLM

OSS Insight analyzes GitHub activity to compare AI agent frameworks, LLM tools, and other open-source projects.

Notte provides cloud browser infrastructure and web automation for AI and coding agents.

Respan unifies LLM observability, evals, prompt optimization, and an AI gateway so teams can ship reliable AI applications.

React applications can use Mantine, a component library with customizable components, hooks, and utilities.

LabLab’s technology index links AI topic pages with tutorials, hackathons, frameworks, and starter code.

This repository curates tools and projects built with the LangChain framework.

Flaq offers one API for accessing AI image, video, 3D, music, and language models.

llamafile packages language models so they can be distributed and run as a single file.

LlamaChat runs LLaMA language models in a macOS app, with a minimum macOS version listed.

AgentScale provides business automation solutions using robotic process automation, language models, and AI agents.

AIlice provides an autonomous, general-purpose AI agent through its open-source repository.

TensorZero builds open-source tools for production-grade LLM applications: LLM gateway, observability, optimization, evaluations, and experimentation.

The Vercel AI SDK provides TypeScript tools for building AI applications and agents.

Fuzzel launches applications and finds matches on Wayland, with inspiration from rofi and dmenu.

SimpleBench evaluates everyday reasoning by comparing language models with human performance.

Mirai Labs builds uzu, a Rust LLM engine for Apple devices, with compact Qwen, LFM, and Muse-Glimmer models.

GPTZero checks text and uploaded files for signs of AI-generated writing.

EvalView regression tests AI agents by snapshotting behavior and comparing tool calls in CI.

Transformer Explainer visualizes how transformer neural networks work through an interactive tool.

Confident AI provides evaluation, observability, red-teaming, and governance tools for testing and monitoring AI systems.

Minimize LLM token complexity to save API costs and model computations.

This bilingual chat language model is described in English and Chinese on the ChatGLM2-6B repository page.

HandyAI offers developer utilities for token counting, prompt analysis, JSON tool use conversion, and cost calculation.

Featherless is a serverless AI inference platform for open-weight models with API access to tens of thousands of models.