Custom tls.connect options for https.Agent
fetch wrapper with support for automatic HTTP proxy, timeout and accessible agent options
An HTTP(s) proxy `http.Agent` implementation for HTTP
the http/https agent used by the npm cli
Turn a function into an `http.Agent` instance
Missing keepalive http.Agent
A light-weight module that brings Fetch API to node.js
The open agent skills ecosystem
SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.
Send parameterized requests to GitHub's APIs with sensible defaults in browsers and Node
XMLHttpRequest for Node
[](https://www.npmjs.com/package/@google/genai) [](https://www.npmjs.com/package/@google/genai)
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/
TypeScript definitions for tunnel
Maps proxy protocols to `http.Agent` implementations
An HTTP(s) proxy `http.Agent` implementation for HTTPS
[](https://www.npmjs.com/package/@aws-sdk/middleware-user-agent) [](https://www.npmjs.c
Datadog API Node.JS Client
Agent to integrate Playwright with ReportPortal.
Get a user agent string across all JavaScript Runtime Environments
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-browser) [](https://www.n
AWS SDK for JavaScript Bedrock Agent Runtime Client for Node.js, Browser and React Native
A SOCKS proxy `http.Agent` implementation for HTTP and HTTPS
Test runner for Storybook stories
A production-grade decision agent that provides deterministic rule evaluation, conflict resolution, and full audit replay capabilities. Framework-agnostic and AI-optional.
A Rails engine providing comprehensive observability for LLM-powered applications. Features include session tracking, trace analysis, prompt management, cost monitoring, and optional chat/agent testing UI (with RubyLLM integration).
a Rails gem that allows you to validate a URL entered in a form. It validates if the URL exists by hitting it with a HEAD request. The improved version includes retries for common patterns when the head request is refused before giving a failure notice. It also looks up a SITE_URL constant to the user agent in the headers. Also has the option to also check that the URL returns content of a specified type.
llm.rb is Ruby's most capable AI runtime. It runs on Ruby's standard library by default. loads optional pieces only when needed, and offers a single runtime for providers, agents, tools, skills, MCP, A2A (Agent2Agent), RAG (vector stores & embeddings), streaming, files, and persisted state. As a bonus, llm.rb is also available for mruby. It supports OpenAI, OpenAI-compatible endpoints, Anthropic, Google Gemini, DeepSeek, xAI, Z.ai, AWS Bedrock, Ollama, and llama.cpp. It also includes built-in ActiveRecord and Sequel support, plus concurrent tool execution through threads, tasks (via async gem), fibers, ractors, and fork (via xchan.rb gem).
Kernai is an AI agent kernel based on a universal XML block protocol, enabling simple, dynamic, observable and fully controlled orchestration without external runtime dependencies. Ships with reference provider adapters for Anthropic, OpenAI and Ollama, native multimodal support, a workflow DAG scheduler, pluggable recorder sinks and an optional MCP (Model Context Protocol) bridge.
airb is an open-source CLI programming agent that helps developers build software using modern LLMs (OpenAI, Anthropic, Gemini). Built on a clean, composable architecture inspired by Stafford Beer's Viable System Model, it features streaming responses, structured tool calling, built-in file operations, and optional web-based observability. Designed for hackability with small objects, clear seams, and UNIXy ergonomics.
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.
RailsLLM integrates the llm.rb runtime and its features into Rails. RailsLLM extends the builtin ActiveRecord support available to the llm.rb runtime with a Rails integration that includes generators for getting set up quickly, and an engine for a stream-capable chat interface that can be extended with your own tools. The llm.rb runtime runs on Ruby's standard library by default. loads optional pieces only when needed, and offers a single runtime for providers, agents, tools, skills, MCP, A2A (Agent2Agent), RAG (vector stores & embeddings), streaming, files, and persisted state.
pikuri-code adds the shell-and-dev-loop layer on top of pikuri-workspace's filesystem tools: a +Pikuri::Code::Bash+ that runs commands via the +Pikuri::Subprocess+ chokepoint with +Confirmer+ gating (optionally wrapped in a +Pikuri::Code::Bash::Sandbox::Bubblewrap+ filesystem sandbox), plus the demo +bin/pikuri-code+ binary that wires file + shell + web tools into an interactive coding agent rooted at the current working directory. The +Pikuri.prompt+ search path picks up this gem's +prompts/coding-system-prompt.txt+ automatically on require.
pikuri-workspace adds "operate on a directory tree" to pikuri-core agents: the +Pikuri::Workspace::Filesystem+ class that scopes filesystem access to an anchor + explicit readable / writable prefix lists (with optional ephemeral temp playground), the +Pikuri::Workspace::Confirmer+ seam (+AUTO_APPROVE+ + +TERMINAL+) for user-state mutations, and five tools wired to those seams: +Pikuri::Workspace::Read+, +Pikuri::Workspace::Write+, +Pikuri::Workspace::Edit+, +Pikuri::Workspace::Grep+, and +Pikuri::Workspace::Glob+. Self-contained — no shell execution; +Pikuri::Code::Bash+ ships in pikuri-code on top of these.
# FaradayError [](https://badge.fury.io/rb/faraday_error) A [Faraday](https://github.com/lostisland/faraday) middleware for adding request parameters to your exception tracker. ### Supports - [Honeybadger](https://www.honeybadger.io/) - [NewRelic](http://newrelic.com/) - Your favorite thing, as soon as you make a pull request! ## Installation Add this line to your application's Gemfile: ```ruby gem 'faraday_error' ``` And then execute: $ bundle Or install it yourself as: $ gem install faraday_error ## Usage Configure your Faraday connection to use this middleware. You can optionally specify a name; defaults to `faraday`. It is expected that you also use `Faraday::Response::RaiseError` somewhere in your stack. ```ruby connection = Faraday.new(url: 'http://localhost:4567') do |faraday| faraday.use FaradayError::Middleware, name: "example_request" faraday.use Faraday::Response::RaiseError faraday.adapter Faraday.default_adapter end ``` And that's it. Make a request as you normally would. ```ruby connection.post do |req| req.url '/503' req.headers['Content-Type'] = 'application/json' req.body = JSON.generate(abc: "xyz") end ``` If any request fails, Honeybadger's "context" for this error will include your request parameters. If sending JSON or `application/x-www-form-urlencoded`, these will be included in parsed form. ```json { "example_request": { "method": "post", "url": "http://localhost:4567/503", "request_headers": { "User-Agent": "Faraday v0.9.2", "Content-Type": "application/json" }, "body_length": 13, "body": { "abc": "xyz" } } } ``` ## Development After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment. To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org). The included [RestReflector](../master/spec/rest_reflector.rb) Sinatra app is suitable for making requests that are guaranteed to fail in particlar ways. ## Contributing Bug reports and pull requests are welcome on GitHub at https://github.com/jelder/faraday_error. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct. ## License The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
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.