Official TypeScript SDK for interacting with the AgentSearch API
n8n community node for Browserbase agent, search, and fetch workflows
Agent search plugin (OpenClaw-first): multi-backend search with RAGFlow KB, fallback/concurrent modes, Jina Reader read URL, and DeepRoute mirror support.
Sprigr MCP server — local AI agent search with WASM-powered full-text search and hybrid semantic search. Also exports a Workers-compatible runtime for in-process search inside Cloudflare Workers / bundled environments.
Minimal Secure Evidence Gateway for Pi Coding Agent — search, web_search, web_fetch, research_search. Intent-based provider routing, quota fallback, dual-LLM research, 4-layer abuse prevention.
MCP server for eSIM Agent — search eSIM plans, compare providers, check device compatibility, and find deals through AI assistants
Web search and content extraction skill for pi-coding-agent. Search the web and fetch pages via a real headless browser (CDP). Works on Linux, macOS, and Windows.
Possess your AI agent — search, summon, and possess SOUL.md personality files from the OpenSOUL.md registry
npm/npx wrapper for AI-agent search infrastructure: MCP, LLM context, browsing, and claim verification.
Agent Search Optimization (ASO) CLI — make products, APIs, and tools discoverable, evaluable, and callable by autonomous AI agents.
Azure AI Agents client library.
Azure AI Projects client library.
MCP server that lets an agent search and scrape the web and pay for it itself — per request in USDC on Base via x402. No API keys.
Aether MCP Server — financial-vertical agent search engine. Hybrid SEC filings (10-K/10-Q/8-K) + earnings transcripts retrieval over 1.4M+ chunks, plus a two-sided marketplace for third-party data. Tools: financial_search, transcript_search, list_partners
VSCode public API plugged on the monaco editor - common package (base, chat, extension-gallery, interactive, localization, mcp, notebook, remote-agent, search, terminal, walkthrough)
Autonomous grocery shopping via Instacart. Let your AI agent search products, manage shopping lists, apply discounts, and complete orders. Persistent session management for recurring grocery runs. Production-ready MCP server for personal agents.
Turn a function into an `http.Agent` instance
The official CLI for Lark/Feishu open platform
An HTTP(s) proxy `http.Agent` implementation for HTTPS
Restaurant discovery and autonomous reservations via OpenTable. Let your AI agent search dining options, check real-time availability, and book tables. Persistent session management for travel agents and personal AI assistants. Production-ready MCP server
Maps proxy protocols to `http.Agent` implementations
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/
No description provided.
Autonomous food ordering via DoorDash. Let your AI agent search restaurants, build orders, and complete checkout. Supports persistent session management, real-time tracking, and full order lifecycle automation. Production-ready MCP server for personal age
Unified multi-provider search CLI for AI agents — 12 providers, 13 modes, email verification, one binary
A complete library to interact with Dialogflow (protocol v2)
A complete library to interact with Dialogflow (protocol v2beta1)
Unified TUI search over local coding agent histories
Is this Web request from a real search engine or from an impersonating agent?
pikuri-vectordb gives a pikuri-core agent a +vectordb_search+ tool over a local document corpus — agentic search, the agent decides when to retrieve. Ships a swappable backend (a pure-Ruby +Backend::InMemory+ for teaching, plus thin +Backend::Qdrant+ / +Backend::Chroma+ HTTP clients for persistence — Qdrant recommended), a chunker, an embedder wrapper over +RubyLLM.embed+, and an optional +Reranker::LlamaServer+ that speaks +/v1/rerank+ against a cross-encoder model. Text extraction goes through +Pikuri::FileType.read_as_text+ in pikuri-core, which handles plain text / Markdown / PDF; HTML extraction is a deferred follow-up. Hosts wire the feature via +c.add_extension Pikuri::VectorDb::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-skills+. The bundled +Pikuri::VectorDb::LIBRARIAN+ persona is the privilege-separated sub-agent counterpart for hosts that want recall to flow through a child rather than the parent's context. Three model endpoints in the full setup — chat (via ruby_llm), an embedder (via +RubyLLM.embed+), and an optional reranker (HTTP +/v1/rerank+). A single +llama-server+ in router mode serves all three by default, loading each cached GGUF on demand; see the gem's README for details.
Hierarchical persistent memory with semantic search for SwarmSDK AI agents
A type-safe Ruby client for the Firecrawl v2 API. Supports scraping, crawling, batch scraping, URL mapping, web search, and AI agent operations.
A bundled spur that adds web search capabilities to Spurline agents using the Brave Search API.
A terminal interface to interactively search, select, and bundle markdown notes for AI agent context.
Official Ruby SDK for Supermemory. Add persistent memory to AI applications with document management, semantic search, user profiling, and integrations with ruby-openai, graph-agent, and langchainrb.
RCrewAI is a powerful Ruby framework for creating autonomous AI agent crews that collaborate to solve complex tasks. Build intelligent workflows with reasoning agents, tool usage, memory systems, and human oversight. Key Features: • Multi-Agent Orchestration: Create crews of specialized AI agents that work together • Multi-LLM Support: OpenAI GPT-4, Anthropic Claude, Google Gemini, Azure OpenAI, Ollama • Rich Tool Ecosystem: Web search, file operations, SQL databases, email, code execution, PDF processing • Agent Memory: Short-term and long-term memory for learning from past executions • Human-in-the-Loop: Interactive approval workflows and collaborative decision making • Advanced Task Management: Dependencies, retries, async execution, and context sharing • Hierarchical Teams: Manager agents that coordinate and delegate to specialist agents • Production Ready: Security controls, error handling, comprehensive logging, and monitoring • Ruby-First Design: Built specifically for Ruby developers with idiomatic patterns • CLI Tools: Command-line interface for creating and managing AI crews
Production-grade Ruby client for Parse Server. Map Parse classes to Ruby models with typed properties, associations, and validations; build queries with a chainable DataMapper-style DSL; handle auth, sessions, MFA, cloud code webhooks, and push; introspect and migrate schemas; manage role hierarchies; scope access with per-agent ACL/CLP; generate GraphQL types; run Atlas Search and vector search; and bypass REST for high-throughput reads via the MongoDB-direct pipeline.
pikuri-core is the lean, audit-friendly foundation of the pikuri family: Pikuri::Agent (a thin wrapper around ruby_llm's chat loop) with its Configurator + Extension protocol, the strict Pikuri::Tool framework, a listener surface for rendering / budgets / sub-agents, and four bundled stateless tools (calculator, web search, web scrape, fetch). Extensions (skills, MCP, workspace, coding stack, named-agent personas) live in sibling gems so a privacy-conscious user can install just this core and audit a minimal dependency tree. For the convenience bundle that pulls in everything, see the +pikuri+ metagem.
RcrewAI Rails is a comprehensive Rails engine that brings AI agent orchestration to your Rails applications. Build intelligent AI crews that collaborate to solve complex tasks with full database persistence, background job integration, and a beautiful web dashboard for monitoring and management. Features: • ActiveRecord models for crews, agents, tasks, and executions with full persistence • Rails generators for scaffolding AI crews and agents • ActiveJob integration for asynchronous crew execution (works with any Rails background job adapter) • Web dashboard with real-time monitoring and management interface • Multi-LLM support: OpenAI GPT, Anthropic Claude, Google Gemini, Azure OpenAI, Ollama • Production-ready with logging, error handling, and security controls • Human-in-the-loop workflows with approval mechanisms • Tool ecosystem: web search, file operations, SQL, email, code execution
Provides RobotLab::DocumentStore — a thread-safe, in-memory semantic search store backed by fastembed (BAAI/bge-small-en-v1.5). Store text documents by key and retrieve the closest matches to a natural-language query using cosine similarity. Works standalone or as a drop-in extension for robot_lab agents and networks.
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.