LLM

Lemonade helps users find and run local AI apps by serving language models from GPUs and NPUs.

Searchable tracks brand visibility across ChatGPT, Claude, Perplexity, and other AI search engines with analytics tools.

LiteLLM provides a way to call more than 100 language models through an OpenAI-compatible interface.

Quickly understand inscrutable LLM frameworks by intercepting API calls.

Flickboard provides an Android keyboard that uses flick gestures for text input. Its project listing identifies it as a keyboard application.

TextFX is a deprecated AI experiment from Google Creative Lab for exploring language and text.

Semantic Cache Router presents a distributed semantic cache and stateful routing system.

Petals runs large language models at home through a BitTorrent-style approach and supports text generation and fine-tuning.

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

The delightful humane design list curates resources about humane design and technology for practitioners and researchers.

Cleanlab Detect scores AI responses for trust and accuracy and flags issues such as hallucinations or missing context.

dut calculates disk usage on Linux, according to its project description.

Imagepipe reduces image file sizes and removes EXIF metadata, helping users share smaller images without embedded camera details.

Off Grid runs language models, image generation, vision, and speech tools locally on phones or Macs.

Use Bifrost as an AI gateway with load balancing, guardrails, cluster mode, and support for many models.

Gain control with LangGraph to design agents that reliably handle complex tasks.

piia-engram provides local-first AI memory that users can inspect and edit across coding tools.

LLMeBench provides a flexible framework for benchmarking large language models.

Traffic Light tracks network and data usage on Android, providing an open source view of device traffic with privacy in mind.

Cohere develops AI models and solutions for enterprise process automation, employee tools, and turning fragmented data into insights.

This Hugging Face article describes SelfCheckGPT NLI for detecting hallucinations in generated answers.

Indico benchmarks language models on extractive, classification, and predictive tasks.

This API extracts and parses text from PDF, Word, and PowerPoint files, with OCR models and options to anonymize documents and remove PII.

Slidev creates presentation slides for developers, according to its site.