# OpenTrade OpenTrade is an open-source trading harness for Claude Code and Codex agents. It provides a repository-based app, agent templates, and scheduling-oriented run management for automated trading workflows. - Findings24: - Website: - Pricing: Freemium - Categories: AI Agent Infrastructure, AI Workflow Automation ## What is OpenTrade? OpenTrade is an open-source trading harness for Claude Code and Codex agents. Hosted in a public GitHub repository, it organizes trading-oriented agent work through an application, agent templates, and supporting hooks and resources. The available project material points to scheduled runs, wake outcomes, monitoring history, runtime limits, and operational logging, while leaving broker support, instrument coverage, setup requirements, and live-trading behavior to the repository documentation and code. ## What can OpenTrade do? ### Claude Code and Codex agent target The project is explicitly positioned as a harness for Claude Code and Codex agents, giving those agent environments a trading-focused repository and workflow context. ### Agent templates and hooks The repository includes \`templates/agents\` and \`resources/hooks\`, providing project-managed locations for agent instructions and supporting run behavior. ### Scheduled wake and run tracking Project history references scheduled tasks, wake outcomes, and Monitor-tab history rows, supporting workflows that need to record and revisit agent runs over time. ### Runtime and stop controls The application includes a maximum run-time path and a shared handling path for user stops and timeout kills; timed-out wakes are represented as failed with a specific timeout reason. ### Headless-run sleep guard For unattended runs, the project can hold an idle-sleep prevention assertion and release it when the run ends. Failures are reported, and lid-close and low-battery sleep are not blocked. ### Local operational records The project history describes local logging for repeated host or broker failures, with deduplication and recovery reporting rather than writing an identical persistent error on every poll. ## Use Cases ### Scheduled agent workflows Use the harness when an agent task needs to run at a future time and its wake result should remain visible in later monitoring history. ### Unattended or headless runs Run an agent workflow without keeping the application in active use, while applying a maximum runtime and reporting timeout or other run failures. ### Iterating on trading agents Use the repository’s agent-template and hook structure to organize repeatable trading-agent instructions and supporting execution behavior. ### Investigating run failures Review recorded wake status, timeout reasons, and local operational logs when a scheduled task or broker-related poll does not complete normally. ## Frequently Asked Questions ### Which agent environments does OpenTrade target? The project description explicitly names Claude Code and Codex agents. The available source does not establish compatibility with other agent runtimes. ### Is OpenTrade open source? Yes. OpenTrade is presented as an open-source project in a public GitHub repository and includes a repository license file. ### Does the source confirm which brokers or instruments are supported? No complete broker or instrument list is available in the supplied product evidence. The repository should be checked for its current supported-instrument and integration documentation. ### Can runs be stopped or timed out? The project history describes a maximum run time and a shared path for user stops and timeout kills. A wake that reaches the run limit is recorded as failed with a timed-out reason. ### Does the sleep guard prevent every kind of system sleep? No. The documented behavior covers idle sleep during headless runs; lid-close and low-battery sleep can still occur. ## Quick Facts - **Category**: Developer Tool - **Source**: Public GitHub repository - **Primary users**: Users building trading workflows with Claude Code or Codex agents - **Project type**: Open-source trading harness - **Repository components**: Application, agent templates, resources, and hooks - **Run model**: Scheduled and headless-oriented agent runs with monitoring history