This document specifies the integration of Jido.Thread with the ReAct strategy, implementing the key insight from JIDO_THREAD.md: Thread is the canonical history; LLM context is a derived projection.
The Machine's conversation list becomes ephemeral—generated fresh each LLM call from Thread via a ContextPolicy projector. This enables token budgeting, windowing, summarization, and provider-agnostic storage while keeping the full interaction history intact.
OpenClaw is a multi-channel message routing layer wrapped around an embedded "coding agent" runtime (pi-agent-core). It enables AI agents to operate across messaging platforms (Telegram, Discord, Slack, Signal, iMessage, WhatsApp, etc.) with unified tool access, session management, and extensibility.
┌─────────────────────────────────────────────────────────────────┐
| #!/usr/bin/env elixir | |
| Mix.install([ | |
| {:req_llm, path: ".."} | |
| ]) | |
| Logger.configure(level: :warning) | |
| defmodule SimpleAgent.V1 do | |
| use GenServer |
| defmodule PetalPro.FileUploads.Tigris do | |
| @moduledoc """ | |
| Tigris.dev S3-compatible storage provider using ExAws. | |
| ## Setup | |
| 1. Add ExAws dependencies to mix.exs: | |
| ```elixir | |
| {:ex_aws, "~> 2.0"}, | |
| {:ex_aws_s3, "~> 2.0"}, |
| defmodule CalculatorAgent do | |
| @moduledoc """ | |
| A simple calculator agent for performing arithmetic operations. | |
| CalculatorAgent provides a clean, minimal API for mathematical calculations | |
| while leveraging the full power of Jido.Agent.Server under the hood. | |
| ## Examples | |
| # Start a calculator agent |
A comprehensive quality checklist for high-quality open source Elixir modules. Use this checklist to evaluate and ensure your Elixir packages meet professional standards.
mix format --check-formatted)
| defmodule Jido.Actions.ParallelArithmetic do | |
| @moduledoc """ | |
| Runs arithmetic operations in parallel and combines their results. | |
| """ | |
| use Jido.Action, | |
| name: "parallel_arithmetic", | |
| description: "Performs multiple arithmetic operations in parallel", | |
| category: "examples", | |
| vsn: "1.0.0", |
| # Project Instructions (Phoenix Project) | |
| This document serves as a comprehensive, award-winning set of guidelines for a Phoenix-based Elixir web application. By following these instructions, you will ensure that your application is secure, maintainable, scalable, and pleasant to work with. These guidelines represent the gold standard for Phoenix development. | |
| --- | |
| ## Overview | |
| This project is a Mix-based Phoenix application, offering a web interface and API endpoints backed by a robust Elixir application. It uses the Phoenix framework’s conventions, Ecto for database interactions, and follows functional programming principles. |
| defmodule JidoWorkbench.AgentJido do | |
| use Jido.Agent, | |
| name: "AgentJido", | |
| description: "Agent Jido", | |
| actions: [JidoWorkbench.Actions.GenerateChatResponse] | |
| @chat_input %{ | |
| prompt: """ | |
| You are Agent Jido—an elite AI engineer stationed in a neon-lit orbital metropolis, where quantum cores hum beneath sleek alloy plating and encrypted data streams flicker across panoramic holo-displays. You're known for your razor-sharp, punctual insights into software engineering, artificial intelligence, and systems programming. Your words are concise and direct, often laced with a dry, ironic humor that underscores your mastery of code and computation. Remember: you build next-generation LLM tooling with a no-nonsense approach that cuts straight to the heart of any technical challenge. When you respond, speak as the efficient, world-weary hacker who's seen it all and still meets each request with crisp expertise and a subtle, knowing smirk. | |
| """, |
| name: "Deploy Server Prod" | |
| on: | |
| workflow_dispatch: | |
| env: | |
| FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }} | |
| jobs: | |
| deploy: | |
| name: Deploy Server to Production |