前端工具库
LLM tool definitions and execution-plan resolver for DG-Lab Coyote control
Cisco IOS automation agent CLI with mock simulation, guardrails, and LLM tool-calling support.
A comprehensive TypeScript library providing easy retrieval of airport data based on IATA, ICAO, city codes, country codes, and continents. Includes LLM tool definitions for AI integration.
Koishi Lark/Feishu LLM tool gateway powered by self-managed lark-cli binary.
The Agent Commerce Protocol (ACP) Node SDK v2 is a ground-up rewrite of the ACP Node SDK. It replaces the callback/phase-based model with an event-driven architecture built around `AcpAgent` and `JobSession`, with first-class LLM tool integration, pluggab
Pi extension that guards against common LLM tool call mistakes: missing skill documentation injection, unknown tool bash fallback, and edit/write/read field name normalization
AI Agent framework for generating faui JSON Schema pages via LLM tool calls
On-device AI agent engine for Capacitor apps — thin WebView bridge to a native Rust agent with LLM, tool execution, cron, and MCP support
Galya REST API client + LLM tool definitions for agent integrations
Parse and validate LLM tool-call JSON payloads. Loose JSON parsing (repairs common LLM mistakes) + JSON-Schema-subset validation. Zero dependencies.
MCP server for Immich — browse and search photos, manage albums, recognize people, surface memories, resolve duplicates, manage stacks via LLM tool calls
Shared types, permissions, ledger, cache, and LLM tool-adapter emitters for @agent-sh/harness-* tools
MCP server for Workforce AI — policy management, asset visibility, and apps catalog via LLM tool calls
A recursive Lisp-style agent loop for LLM tool-calling agents
OpenCode plugin for Opik observability - traces LLM/Tool/Subagent execution to Opik platform
MCP server for the Thetanuts SDK — read-only LLM tool access for options trading on Base + Ethereum
CLI for Porchestra - Generate LLM tool handlers
Procedural knowledge management for Node.js — Git, SQLite, zero dependencies, with a built-in LLM tool facade
Codex-style multi-agent orchestration for pi — spawn, communicate with, and coordinate sub-agents via LLM tool calls
AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin.
Validate tax identification numbers (TIN, VAT, EIN, GST, ITIN, SSN) for 76+ countries. Regex, checksum, and online VIES/government verification. TypeScript-first with LLM tool definitions.
Programmatic LibGen+ search and downloader with an MCP server for LLM tool-calls.
Deterministic prompt compiler for tool-schema compression. Implements all 8 TSCG operators (SDM, TAS, DRO, CFL, CFO, CAS, SAD-F, CCP). Reduces LLM tool-definition overhead by 71.7%. Zero dependencies.
Framework-agnostic Rust tool definitions for LLM agents
Anthropic Messages API provider for the llm-cmd toolkit
A CLI tool for interacting with LLMs (OpenAI, Anthropic) via a unified interface
Core traits, types, and streaming primitives for the llm-cmd LLM toolkit
OpenAI Chat API provider for the llm-cmd toolkit
JSONL conversation log storage for the llm-cmd toolkit
Proc macros for llm-tool (#[llm_tool] attribute)
Allow Rust functions to be called by LLMs
Find markers in your files and replace them with LLM-generated content
Phase 80.1 — autoDream fork-style memory consolidation (KAIROS port)
A package manager for coding agent skills
Registry of available tools with schema for LLM agents
liter-llm is a universal LLM API client with a Rust core and native Ruby bindings via Magnus. Provides a unified interface for streaming completions, tool calling, and provider routing across 142+ LLM providers. Rust-powered.
A tool that uses LLM to automatically fix errors detected by static analysis tools (such as RuboCop).
PrReview collects PR data from GitHub (description, commits, comments, linked issues, and code changes) and formats it as XML. Paste this XML into any LLM like ChatGPT or Claude to get helpful code reviews.
Ruby-native LLM agent framework with provider adapters (Anthropic, OpenAI, Google), tool calling, streaming, and session persistence.
A Ruby gem for building AI tools for large language models using a simple domain-specific language.
Register JSON-schema tools and let an LLM handle intent, slot-filling, and tool calls safely.
Drop-in Rails engine to register JSON-schema tools, let an Llm fill missing fields, validate input, and execute handlers safely.
LLM Bench is a Ruby gem that allows you to benchmark and compare the performance of different Large Language Model providers and APIs. It supports both OpenAI and Anthropic-compatible API formats, provides parallel execution, and includes continuous tracking capabilities with CSV export.
Productivity boosting tools powered by LLMS
LLMs::Tool provides a simple DSL for defining tools that can be serialized to the correct JSON schema to be used with LLM systems
Ruby chain tools to work with LLMs
Ruby AI Agents SDK enables creating complex AI workflows with multi-agent orchestration, tool execution, safety guardrails, and provider-agnostic LLM integration.
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.