Provider-agnostic autonomous agent loop for JavaScript. Built on the [Vercel AI SDK](https://sdk.vercel.ai/), it drives any `LanguageModel` through a tool-use loop until the task is complete.
Stop juggling dashboards. Let your agent do it. Analytics your AI agent can actually use — track, analyze, experiment, optimize.
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/
The read side — project the Lodestar event log into the epistemic chain and render a 'why did the agent do this?' report. Part of Lodestar, the trust layer for AI agents.
Loads environment variables from .env file
An ACP-compatible coding agent powered by the Claude Agent SDK (TypeScript)
Turn a function into an `http.Agent` instance
An HTTP(s) proxy `http.Agent` implementation for HTTPS
Maps proxy protocols to `http.Agent` implementations
NodeJS http(s) agent implementation for VS Code
Commands to interact with Salesforce agents
[](https://www.npmjs.com/package/@aws-sdk/middleware-user-agent) [](https://www.npmjs.c
Skillflag producer CLI reference implementation.
Get a user agent string across all JavaScript Runtime Environments
The official Elastic APM agent for Node.js
A module for generating metrics from V8.
An HTTP(s) proxy `http.Agent` implementation for HTTP
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-browser) [](https://www.n
A SOCKS proxy `http.Agent` implementation for HTTP and HTTPS
HTTP proxy tunneling agent. Formerly part of mikeal/request, now a standalone module.
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.
the http/https agent used by the npm cli
A PAC file proxy `http.Agent` implementation for HTTP
Global HTTP/HTTPS proxy configurable using environment variables.
Interactive document sessions with AI agents
Pure document data layer for agent-doc (component parsing, frontmatter, template, CRDT, pending, diff classification, model tier)
CLI crate for nils-agent-docs in the nils-cli workspace.
Agent-doc/session observability for tsift — cost, digest, review, guardrails, and log parsing
CodeDeploy Agent is responsible for doing the actual work of deploying software on an individual EC2 instance.
If you want an easy way to monitor services without the need of installing agents let a monkey do the job by polling status information via transport protocols.
A command-line application to generate random user agent strings. Acting as a command-line interface to the user-agent-randomizer gem without the need to do any ruby programming.
require 'mail' require 'mail-store-agent' Mail.defaults do delivery_method :test end Mail::TestMailer.deliveries = MailStoreAgent.new # send some mail to someone@someplace.com, and then ... Mail::TestMailer.deliveries.get('someone@someplace.com').is_a? Mail::Message # or nil
Causal inference engine for brain-modeled agentic AI — do-calculus and causal graphs
pikuri-tasks gives a pikuri-core agent an in-memory task list it can use to plan and track multi-step work. A +Pikuri::Tasks::List+ holds the per-Agent state; four tools (+task_create+, +task_in_progress+, +task_completed+, +task_delete+) mutate it via content-as-identifier (no item IDs to hallucinate). +Pikuri::Tasks::Extension+ wires the list and tools onto an +Pikuri::Agent+ via +c.add_extension(...)+ inside the +Agent.new+ block. The list lives in process memory only — nothing is written to disk. Sub-agents do not inherit the parent's list (consistent with the "sub-agents do not inherit extensions" rule).
MandateClaw-DSL is a Ruby DSL for defining programmatic, signed, and auditable contracts that govern what an AI agent is and isn't allowed to do on behalf of a human or organisation.
MandateClaw-DSL is a Ruby DSL for defining programmatic, signed, and auditable contracts that govern what an AI agent is and isn't allowed to do on behalf of a human or organisation.
If you're building a game, you need your game agents and characters to move on their own. A standard way of doing this is with 'steering behaviors'. The seminal paper by Craig Reynolds established a core set of steering behaviors that could be utilized for a variety of common movement tasks and natural behaviors. This Ruby library can accomplish many/most of those tasks for your Ruby / JRuby game. The basic behaviors can be layered for more complicated and advanced behaviors, such as flocking and crowd movement.
`nvim-context` extracts live context from running Neovim instances via Unix socket connections, providing AI coding tools with cursor position, current file, visual selections, and diagnostics as JSON. It enables context-aware assistance by giving agents awareness of your current Neovim editor state, supporting questions like "What does this line do?" or analysis of selected code.
# 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.
No description provided.