Library to be able to test LLM base UseCase
Hardware accelerated language model chats on browsers
Resolve a URI relative to an optional base URI
Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js
Basic layout model and some utilities for Cytoscape.js layout extensions
Core module for compound spring embedder based layout styles
BlockRun SDK - Pay-per-request AI (LLM, Image, Video, Music, Voice) via x402 on Base and Solana
Hex string formatters for 4/8/16/24/32/48/64bit words, hexdump formatting of binary data
Arbitrary base-n conversions w/ presets for base8/16/32/36/58/62/64/83/85, support for bigints and encoding/decoding of byte arrays
Typescript bindings for langchain
Display language model outputs in your React project.
LLM-enhanced SAST analysis built on circle-ir
Framework for rapidly creating high quality, server-side node.js applications, using plugins like building blocks
Evaluation library for the MongoDB Assistant API.
LLM eval & testing toolkit
Local proxy that hard-caps AI coding-agent token spend per project. Point your agent's LLM base-URL at localhost; spendguard forwards to your real upstream, enforces a per-project budget, and returns an over-budget error instead of forwarding when the lim
abstract base class for hash-streams
abstract base class for crypto-streams
[llm-ui](https://llm-ui.com) markdown block.
A collection of React utility functions for Base UI.
Turn a function into an `http.Agent` instance
[llm-ui](https://llm-ui.com) code block.
An arbitrary length integer library for Javascript
The set of Unicode symbols that can serve as a base for emoji modifiers, i.e. those with the `Emoji_Modifier_Base` property set to `Yes`.
The base for `llm`; provides common structure for model implementations. Not intended for use by end-users.
Core portable library for GraphRAG - works on native and WASM
Intelligent multi-model router for self-hosted LLMs
A statically typed async framework for building LLM-based applications.
Super YARA — extends YARA-compatible rules with semantic, classifier, and LLM-based matching
Heuristic and LLM-based memory relevance scoring
LLM-based behavioral analysis for the semver-analyzer
FURNACE - AI-powered code generation and analysis MCP server with knowledge graph and tiered search
NER, coreference resolution, relation extraction, PII detection, and zero-shot entity types
NER, coreference resolution, relation extraction, PII detection, and zero-shot entity types
Pure Rust library for local embeddings, reranking, and text generation with MoE-optimized inference and aggressive performance tuning
Git-inspired context management for LLM agents -- COMMIT, BRANCH, MERGE, and CONTEXT over versioned memory (arXiv:2508.00031)
Extends ace-llm with CLI-based LLM providers like Claude Code, Codex, Gemini CLI, OpenCode, and pi-agent
Brakeman detects security vulnerabilities in Ruby on Rails applications via static analysis.
Provides LLM-as-judge and code-based evaluators for scoring LLM outputs, with built-in templates for hallucination, relevance, and toxicity detection.
RAG-based knowledge assistant using Apollo and LLM for LegionIO
LLM Memory is a Ruby gem designed to provide large language models (LLMs) like ChatGPT with memory using in-context learning. This enables better integration with systems such as Rails and web services while providing a more user-friendly and abstract interface based on brain terms.
A flexible Ruby gem for building LLM-based classifiers. Define categories, system prompts, and domain knowledge using a clean DSL. Supports multiple LLM backends (ruby_llm, OpenAI, Anthropic) and integrates seamlessly with Rails.
LLM Chain is a powerful Ruby framework that provides tools for building sophisticated LLM-powered applications. It includes support for prompt management, conversation chains, memory systems, vector storage integration, and seamless LLM provider connections. Key features: • Chain-based conversation flows • Memory management with Redis • Vector storage with Weaviate • Multiple LLM provider support • Prompt templating and management • Easy integration with existing Ruby applications
Schedule AI-driven tasks to run at specified times, process results through LLMs, and take conditional actions based on the output. Designed to be lightweight and self-hostable.
This gem simplifies the commit process by automatically generating descriptive commit messages based on the files that have been added to the Git staging area. It leverages LLM to analyze the changes and create meaningful commit messages, helping you maintain a clean and organized commit history.
Automatically intercept and log LLM requests from Ruby applications. Supports OpenAI, official Anthropic gem, ruby-anthropic gem, and other Faraday-based libraries. Features dual interceptor architecture, streaming support, thread-safe operation, and automatic duplicate request prevention.
Connects Legion to Arize AX via REST v2 and GraphQL APIs with AMQP-based LLM audit forwarding
Ragents is a pure Ruby, Ractor-based AI agent framework designed for concurrent, isolated agent execution. It provides message-passing architecture, tool-based actions, and provider-agnostic LLM integration without Rails dependencies.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.