Open Ralph Wiggum – Autonomous Agentic Loop

Open Ralph Wiggum, a new CLI tool implementing the Ralph Wiggum technique, launches with support for multiple AI coding agents including Claude Code, OpenAI Codex, Copilot CLI, Cursor Agent, Qwen Code, and OpenCode. The tool wraps agents in an autonomous loop that repeatedly prompts the same task until completion, enabling self-correction and incremental progress without manual intervention.

Works with Claude Code, OpenAI Codex, Copilot CLI, Cursor Agent, Qwen Code, and OpenCode — switch agents with --agent . Based on the Ralph Wiggum technique https://ghuntley.com/ralph/ by Geoffrey Huntley Supported Agents supported-agents • What is Ralph? what-is-open-ralph-wiggum • Installation installation • Quick Start quick-start • Commands commands Tired of agents breaking your local environment? 🏝️ sandboxed.sh https://github.com/Th0rgal/sandboxed.sh gives each task an isolated Linux workspace. Self-hosted. Git-backed. 💬 Join the community: relens.ai/community https://relens.ai/community Open Ralph Wiggum works with multiple AI coding agents. Switch between them using the --agent flag: | Agent | Flag | Description | |---|---|---| Claude Code | --agent claude-code | Anthropic's Claude Code CLI for autonomous coding | Codex | --agent codex | OpenAI's Codex CLI for AI-powered development | Copilot CLI | --agent copilot | GitHub Copilot CLI for agentic coding | Cursor Agent | --agent cursor-agent | Cursor Agent CLI for headless AI coding | Qwen Code | --agent qwen-code | Alibaba's Qwen Code CLI for headless AI coding | OpenCode | --agent opencode | Default agent, open-source AI coding assistant | Use Claude Code ralph "Build a REST API" --agent claude-code --max-iterations 10 Use OpenAI Codex ralph "Create a CLI tool" --agent codex --max-iterations 10 Use Copilot CLI ralph "Refactor the auth module" --agent copilot --max-iterations 10 Use Cursor Agent ralph "Add unit tests" --agent cursor-agent --max-iterations 10 Use Qwen Code ralph "Add unit tests" --agent qwen-code --max-iterations 10 Use OpenCode default ralph "Fix the failing tests" --max-iterations 10 Open Ralph Wiggum implements the Ralph Wiggum technique — an autonomous agentic loop where an AI coding agent Claude Code, Codex, Copilot CLI, Cursor Agent, Qwen Code, or OpenCode receives the same prompt repeatedly until it completes a task. Each iteration, the AI sees its previous work in files and git history, enabling self-correction and incremental progress. This is a CLI tool that wraps any supported AI coding agent in a persistent development loop. No plugins required — just install and run. The essence of the Ralph loop: while true; do claude-code "Build feature X. Output <promise DONE</promise when complete." or codex, copilot, cursor-agent, qwen, opencode done Why this works: The AI doesn't talk to itself between iterations. It sees the same prompt each time, but the codebase has changed from previous iterations. This creates a powerful feedback loop where the agent iteratively improves its work until all tests pass. Switch between AI coding agents without changing your workflow: Claude Code --agent claude-code — Anthropic's powerful coding agent Codex --agent codex — OpenAI's code-specialized model Copilot CLI --agent copilot — GitHub's agentic coding tool Cursor Agent --agent cursor-agent — Cursor's headless AI coding agent Qwen Code --agent qwen-code — Alibaba's Qwen Code headless CLI agent OpenCode --agent opencode — Open-source default option Multi-Agent Support — Use Claude Code, Codex, Copilot CLI, Cursor Agent, Qwen Code, or OpenCode with the same workflow Self-Correcting Loops — Agent sees its previous work and fixes its own mistakes Autonomous Execution — Set it running and come back to finished code Task Tracking — Built-in task management with --tasks mode Live Monitoring — Check progress with --status from another terminal Mid-Loop Hints — Inject guidance with --add-context without stopping | Benefit | How it works | |---|---| Self-Correction | AI sees test failures from previous runs, fixes them | Persistence | Walk away, come back to completed work | Iteration | Complex tasks broken into incremental progress | Automation | No babysitting—loop handles retries | Observability | Monitor progress with --status , see history and struggle indicators | Mid-Loop Guidance | Inject hints with --add-context without stopping the loop | Prerequisites: Bun https://bun.sh runtime- At least one AI coding agent CLI: Claude Code https://docs.anthropic.com/en/docs/claude-code — Anthropic's Claude Code CLI Codex https://github.com/openai/codex — OpenAI's Codex CLI Copilot CLI https://github.com/github/copilot-cli — GitHub's Copilot CLI Cursor Agent https://cursor.com/cli/ — Cursor's headless Agent CLI Qwen Code https://github.com/QwenLM/qwen-code — Alibaba's Qwen Code CLI OpenCode https://opencode.ai — Open-source AI coding assistant npm install -g @th0rgal/ralph-wiggum bun add -g @th0rgal/ralph-wiggum git clone https://github.com/Th0rgal/open-ralph-wiggum cd open-ralph-wiggum ./install.sh git clone https://github.com/Th0rgal/open-ralph-wiggum cd open-ralph-wiggum .\install.ps1 This installs the ralph CLI command globally. Simple task with iteration limit ralph "Create a hello.txt file with 'Hello World'. Output <promise DONE</promise when complete." \ --max-iterations 5 Build something real ralph "Build a REST API for todos with CRUD operations and tests. \ Run tests after each change. Output <promise COMPLETE</promise when all tests pass." \ --max-iterations 20 Use Claude Code instead of OpenCode ralph "Create a small CLI and document usage. Output <promise COMPLETE</promise when done." \ --agent claude-code --model claude-sonnet-4 --max-iterations 5 Use Codex instead of OpenCode ralph "Create a small CLI and document usage. Output <promise COMPLETE</promise when done." \ --agent codex --model gpt-5-codex --max-iterations 5 Use Codex goal mode through OMX: Ralph owns cross-iteration retries, /goal owns one iteration RALPH CODEX GOAL=1 RALPH CODEX BACKEND=omx \ ralph "Complete the task described in .harness/goal.md. Output <promise COMPLETE</promise when everything passes." \ --agent codex --max-iterations 5 Use Copilot CLI ralph "Create a small CLI and document usage. Output <promise COMPLETE</promise when done." \ --agent copilot --max-iterations 5 Use Qwen Code ralph "Create a small CLI and document usage. Output <promise COMPLETE</promise when done." \ --agent qwen-code --max-iterations 5 Complex project with Tasks Mode ralph "Build a full-stack web application with user auth and database" \ --tasks --max-iterations 50 Configure agent binaries with these environment variables: | Variable | Description | Default | |---|---|---| RALPH OPENCODE BINARY | Path to OpenCode CLI | "opencode" | RALPH CLAUDE BINARY | Path to Claude Code CLI | "claude" | RALPH CODEX BINARY | Path to Codex CLI | "codex" | RALPH CODEX GOAL | Enable Codex goal mode for --agent codex 1 , true , yes , on | unset | RALPH CODEX BACKEND | Goal-mode backend: codex or omx | detected from configured codex command | RALPH CODEX GOAL NATIVE | Force native /goal attempt even when support is not pre-confirmed | unset | OMX RALPH OMX BIN | Path to OMX CLI when RALPH CODEX BACKEND=omx | "omx" | OMX RALPH REASONING | model reasoning effort passed to omx exec in goal mode | "high" | RALPH COPILOT BINARY | Path to Copilot CLI | "copilot" | RALPH CURSOR AGENT BINARY | Path to Cursor Agent CLI | "cursor-agent" | RALPH QWEN CODE BINARY | Path to Qwen Code CLI | "qwen" | Note for Windows users: Ralph automatically resolves .cmd extensions for npm-installed CLIs. If you encounter "command not found" errors, you can use these environment variables to specify the full path to the executable. ralph "<prompt " options Options: --agent AGENT AI agent to use: opencode default , claude-code, codex, copilot, cursor-agent, qwen-code --codex-goal Run Codex iterations in goal mode; final Codex/OMX prompt starts with /goal --codex-backend BACKEND Backend for --codex-goal: codex or omx default: detect --codex-goal-native Force a native /goal attempt even when backend support is unconfirmed --min-iterations N Minimum iterations before completion allowed default: 1 --max-iterations N Stop after N iterations default: unlimited --completion-promise T Text that signals completion default: COMPLETE --abort-promise TEXT Phrase that signals early abort e.g., precondition failed --tasks, -t Enable Tasks Mode for structured task tracking --task-min-iterations N Require each top-level task to receive N Ralph iterations before completion default: 1 --task-promise T Text that signals task completion default: READY FOR NEXT TASK --model MODEL Model to use agent-specific --rotation LIST Agent/model rotation for each iteration comma-separated --prompt-file, --file, -f Read prompt content from a file --prompt-template PATH Use custom prompt template see Custom Prompts --no-stream Buffer agent output and print at the end --verbose-tools Print every tool line disable compact tool summary --questions Enable interactive question handling default: enabled --no-questions Disable interactive question handling agent will loop on questions --no-plugins Disable non-auth OpenCode plugins for this run opencode only --no-commit Don't auto-commit after iterations --allow-all Auto-approve all tool permissions default: on --no-allow-all Require interactive permission prompts --config PATH Use custom agent config file --init-config PATH Write default agent config to PATH and exit --help Show help --codex-goal is an opt-in mode for --agent codex . Open Ralph still owns the outer loop: max iterations, process restarts, promise detection, .ralph/ralph-history.json , git/file-system state, and optional auto-commits. Inside each Ralph iteration, the Codex backend receives a final prompt whose first token is /goal , so Codex goal mode can own the single-session push for that iteration. ralph \ "Complete the task in .harness/goal.md. Run .harness/checks.sh. Output <promise COMPLETE</promise when everything passes." \ --agent codex \ --codex-goal \ --codex-backend omx \ --max-iterations 5 Equivalent environment form: RALPH CODEX GOAL=1 RALPH CODEX BACKEND=omx ralph \ "Complete the task in .harness/goal.md. Run .harness/checks.sh. Output <promise COMPLETE</promise when everything passes." \ --agent codex \ --max-iterations 5 Goal-mode iterations write a small durable audit ledger to .ralph/codex-goal-ledger.jsonl . This is intentionally file-system state, not Codex thread state, so later Ralph iterations can start fresh while retaining repo-native progress evidence. If native /goal cannot be pre-confirmed, Ralph prints an explicit warning; simulated fallback is used only when native Codex goal support is not available for the selected backend. Tasks Mode allows you to break complex projects into smaller, manageable tasks. Ralph works on one task at a time and tracks progress in a markdown file. Enable Tasks Mode ralph "Build a complete web application" --tasks --max-iterations 20 Custom task completion signal ralph "Multi-feature project" --tasks --task-promise "TASK DONE" Require each top-level task to receive three Ralph iterations before task/final completion ralph "Multi-feature project" --tasks --task-min-iterations 3 --max-iterations 20 List current tasks ralph --list-tasks Add a new task ralph --add-task "Implement user authentication" Remove task by index ralph --remove-task 3 Show status tasks shown automatically when tasks mode is active ralph --status Task File : Tasks are stored in .ralph/ralph-tasks.md One Task Per Iteration : Ralph focuses on a single task to reduce confusion Automatic Progression : When a task completes <promise READY FOR NEXT TASK</promise , Ralph moves to the next eligible task Task Minimum Iterations : --task-min-iterations N requires every top-level task to receive N Ralph outer-loop iterations before task or final completion is accepted. This is separate from global --min-iterations , which gates the whole run. Task Ledger Fallback : With task minimums enabled, if the selected top-level task is already x with all subtasks x after its required iterations, Ralph advances from the task ledger even if the agent forgets to emit READY FOR NEXT TASK Persistent State : Tasks survive loop restarts; per-task attempt counts are stored in .ralph/ralph-task-runs.json when task minimums are enabled Focused Context : Smaller contexts per iteration reduce costs and improve reliability Task status indicators: - Not started / - In progress x - Complete Example task file: Ralph Tasks - Set up project structure - x Initialize git repository - / Implement user authentication - Create login page - Add JWT handling - Build dashboard UI You can fully customize the prompt sent to the agent using --prompt-template . This is useful for integrating with custom workflows or tools. ralph "Build a REST API" --prompt-template ./my-template.md Available variables: | Variable | Description | |---|---| {{iteration}} | Current iteration number | {{max iterations}} | Maximum iterations or "unlimited" | {{min iterations}} | Minimum iterations | {{prompt}} | The user's task prompt | {{completion promise}} | Completion promise text e.g., "COMPLETE" | {{abort promise}} | Abort promise text if configured | {{task promise}} | Task promise text for tasks mode | {{task min iterations}} | Configured per-task minimum Ralph iterations for tasks mode | {{task id}} | Current selected top-level task id when task-min tracking is active | {{task text}} | Current selected top-level task text when task-min tracking is active | {{task attempt}} | Current selected task attempt count when task-min tracking is active | {{task min required}} | Required attempts for the current selected task | {{task can complete}} | true when the selected task has met its task minimum | {{task gate instruction}} | Ready-to-embed task-min guidance for custom templates | {{context}} | Additional context added mid-loop | {{tasks}} | Task list content for tasks mode | Example template my-template.md : Iteration {{iteration}} / {{max iterations}} Task {{prompt}} Instructions 1. Check beads for current status 2. Decide what to do next 3. When the epic in beads is complete, output: <promise {{completion promise}}</promise {{context}} Check status of active loop run from another terminal ralph --status Add context/hints for the next iteration ralph --add-context "Focus on fixing the auth module first" Clear pending context ralph --clear-context The --status command shows: Active loop info : Current iteration, elapsed time, prompt Pending context : Any hints queued for next iteration Current tasks : Automatically shown when tasks mode is active or use --tasks Iteration history : Last 5 iterations with tools used, duration Struggle indicators : Warnings if agent is stuck no progress, repeated errors ╔══════════════════════════════════════════════════════════════════╗ ║ Ralph Wiggum Status ║ ╚══════════════════════════════════════════════════════════════════╝ 🔄 ACTIVE LOOP Iteration: 3 / 10 Elapsed: 5m 23s Promise: COMPLETE Prompt: Build a REST API... 📊 HISTORY 3 iterations Total time: 5m 23s Recent iterations: 🔄 1: 2m 10s | Bash:5 Write:3 Read:2 🔄 2: 1m 45s | Edit:4 Bash:3 Read:2 🔄 3: 1m 28s | Bash:2 Edit:1 ⚠️ STRUGGLE INDICATORS: - No file changes in 3 iterations 💡 Consider using: ralph --add-context "your hint here" Guide a struggling agent without stopping the loop: In another terminal while loop is running ralph --add-context "The bug is in utils/parser.ts line 42" ralph --add-context "Try using the singleton pattern for config" Context is automatically consumed after one iteration. This package is CLI-only . If OpenCode tries to load a ralph-wiggum or open-ralph-wiggum plugin, remove it from your OpenCode plugin list opencode.json , or run: ralph "Your task" --no-plugins If you see ProviderModelNotFoundError or "Provider returned error", you need to configure a default model: For OpenCode: - Edit ~/.config/opencode/opencode.json : { "$schema": "https://opencode.ai/config.json", "model": "your-provider/model-name" } - Or use the --model flag: ralph "task" --model provider/model For other agents: Use the --model flag to specify the model explicitly. Ralph automatically tries .cmd extensions on Windows. If you still have issues: - Set the full path using environment variables: $env:RALPH OPENCODE BINARY = "C:\path\to\opencode.cmd" - Or add the CLI to your PATH Install Bun: https://bun.sh https://bun.sh ❌ Bad: Build a todo API ✅ Good: Build a REST API for todos with: - CRUD endpoints GET, POST, PUT, DELETE - Input validation - Tests for each endpoint Run tests after changes. Output <promise COMPLETE</promise when all tests pass. ❌ Bad: Make the code better ✅ Good: Refactor auth.ts to: 1. Extract validation into separate functions 2. Add error handling for network failures 3. Ensure all existing tests still pass Output <promise DONE</promise when refactored and tests pass. Safety net for runaway loops ralph "Your task" --max-iterations 20 Ralph treats prompt files as plain text, so any format works. For best results, use a concise PRD with: Goal : one sentence summary of the desired outcome Scope : what is in/out Requirements : numbered, testable items Constraints : tech stack, performance, security, compatibility Acceptance criteria : explicit success checks Completion promise : include <promise COMPLETE</promise or match your --completion-promise Example Markdown : PRD: Add Export Button Goal Let users export reports as CSV from the dashboard. Scope - In: export current report view - Out: background exports, scheduling Requirements 1. Add "Export CSV" button to dashboard header. 2. CSV includes columns: date, revenue, sessions. 3. Works for reports up to 10k rows. Constraints - Keep current UI styling. - Use existing CSV utility in utils/csv.ts. Acceptance Criteria - Clicking button downloads a valid CSV. - CSV opens cleanly in Excel/Sheets. - All existing tests pass. Completion Promise <promise COMPLETE</promise For larger projects, a structured JSON feature list works better than prose. Based on Anthropic's research on effective agent harnesses https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents , JSON format reduces the chance of agents inappropriately modifying test definitions. Create a features.json file: { "features": { "category": "functional", "description": "Export button downloads CSV with current report data", "steps": "Navigate to dashboard", "Click 'Export CSV' button", "Verify CSV file downloads", "Open CSV and verify columns: date, revenue, sessions", "Verify data matches displayed report" , "passes": false }, { "category": "functional", "description": "Export handles large reports up to 10k rows", "steps": "Load report with 10,000 rows", "Click 'Export CSV' button", "Verify export completes without timeout", "Verify all rows present in CSV" , "passes": false }, { "category": "ui", "description": "Export button matches existing dashboard styling", "steps": "Navigate to dashboard", "Verify button uses existing button component", "Verify button placement in header area" , "passes": false } } Then reference it in your prompt: Read features.json for the feature list. Work through each feature one at a time. After verifying a feature works end-to-end, update its "passes" field to true. Do NOT modify the description or steps - only change the passes boolean. Output <promise COMPLETE</promise when all features pass. Why JSON? Agents are less likely to inappropriately modify JSON test definitions compared to Markdown. The structured format keeps agents focused on implementation rather than redefining success criteria. Good for: - Tasks with automatic verification tests, linters, type checking - Well-defined tasks with clear completion criteria - Greenfield projects where you can walk away - Iterative refinement getting tests to pass Not good for: - Tasks requiring human judgment - One-shot operations - Unclear success criteria - Production debugging ┌─────────────────────────────────────────────────────────────┐ │ │ │ ┌──────────┐ same prompt ┌──────────┐ │ │ │ │ ───────────────▶ │ │ │ │ │ ralph │ │ AI Agent │ │ │ │ CLI │ ◀─────────────── │ │ │ │ │ │ output + files │ │ │ │ └──────────┘ └──────────┘ │ │ │ │ │ │ │ check for │ modify │ │ │ <promise │ files │ │ ▼ ▼ │ │ ┌──────────┐ ┌──────────┐ │ │ │ Complete │ │ Git │ │ │ │ or │ │ Repo │ │ │ │ Retry │ │ state │ │ │ └──────────┘ └──────────┘ │ │ │ └─────────────────────────────────────────────────────────────┘ - Ralph sends your prompt to the selected agent - The agent works on the task, modifies files - Ralph checks output for completion promise - If not found, repeat with same prompt - AI sees previous work in files - Loop until success or max iterations ralph-wiggum/ ├── bin/ralph.js CLI entrypoint npm wrapper ├── ralph.ts Main loop implementation ├── package.json Package config ├── install.sh / install.ps1 Installation scripts └── uninstall.sh / uninstall.ps1 Uninstallation scripts During operation, Ralph stores state in .ralph/ : ralph-loop.state.json - Active loop state ralph-history.json - Iteration history and metrics ralph-context.md - Pending context for next iteration ralph-tasks.md - Task list for Tasks Mode created when --tasks is used ralph-questions.json - Pending user answers to agent questions npm uninstall -g @th0rgal/ralph-wiggum npm uninstall -g @th0rgal/ralph-wiggum Claude Code https://docs.anthropic.com/en/docs/claude-code is Anthropic's official CLI for Claude. Use it with Open Ralph Wiggum for powerful autonomous coding: ralph "Refactor the auth module and ensure tests pass" \ --agent claude-code \ --model claude-sonnet-4 \ --max-iterations 15 Codex https://github.com/openai/codex is OpenAI's code-specialized agent. Perfect for code generation and refactoring tasks: ralph "Generate unit tests for all utility functions" \ --agent codex \ --model gpt-5-codex \ --max-iterations 10 OpenCode https://opencode.ai is an open-source AI coding assistant. It's the default agent: ralph "Fix all TypeScript errors" --max-iterations 10 Copilot CLI https://github.com/github/copilot-cli is GitHub's agentic coding tool public preview . It requires a GitHub Copilot subscription and authentication via GH TOKEN , GITHUB TOKEN , or prior copilot /login . Install: npm install -g @github/copilot or brew install copilot-cli Usage: ralph "Refactor the auth module and add tests" \ --agent copilot \ --max-iterations 15 With a specific model ralph "Build a REST API" \ --agent copilot \ --model claude-opus-4.6 \ --max-iterations 10 Notes: - Default model is Claude Sonnet 4.5; override with --model --allow-all default maps to --allow-all + --no-ask-user in Copilot CLI --no-plugins has no effect with Copilot CLI- Authentication: set GH TOKEN / GITHUB TOKEN env var, or run copilot /login first Qwen Code https://github.com/QwenLM/qwen-code is Alibaba's headless AI coding CLI agent based on the Qwen model family. It uses the same stream-JSON output format as Claude Code. Install: npm install -g @qwen-code/qwen-code Usage: ralph "Refactor the database layer" \ --agent qwen-code \ --max-iterations 10 With a specific model ralph "Add integration tests for the API" \ --agent qwen-code \ --model qwen-coder-plus \ --max-iterations 15 Notes: - The CLI binary is qwen ; override path with RALPH QWEN CODE BINARY env var --allow-all default maps to --yolo in Qwen Code CLI auto-approves all actions --no-plugins has no effect with Qwen Code- Headless mode uses --output-format stream-json --include-partial-messages - See headless docs https://qwenlm.github.io/qwen-code-docs/en/users/features/headless/ for details Cursor Agent https://cursor.com/cli/ is Cursor's headless CLI agent. It works with any model available through your Cursor subscription. Install: curl https://cursor.com/install -fsSL | bash Usage: ralph "Add integration tests for the API" \ --agent cursor-agent \ --max-iterations 10 With a specific model ralph "Refactor the database layer" \ --agent cursor-agent \ --model sonnet-4 \ --max-iterations 15 Notes: --allow-all default maps to --force in Cursor Agent CLI --no-plugins has no effect with Cursor Agent- For headless environments no Cursor window , set the CURSOR API KEY environment variable - The binary is cursor-agent ; override with RALPH CURSOR AGENT BINARY env var Agent rotation lets you cycle through different agent/model combinations across iterations. This is useful for leveraging the strengths of different models or comparing their performance on a task. Each rotation entry uses the agent:model format: --rotation "agent1:model1,agent2:model2,agent3:model3" Valid agents: opencode , claude-code , codex , copilot , cursor-agent , qwen-code Alternate between OpenCode and Claude Code ralph "Build a REST API" \ --rotation "opencode:claude-sonnet-4,claude-code:claude-sonnet-4" \ --max-iterations 10 Cycle through three different configurations ralph "Refactor the auth module" \ --rotation "opencode:claude-sonnet-4,claude-code:claude-sonnet-4,codex:gpt-5-codex" \ --max-iterations 15 Include Copilot in the rotation ralph "Build a REST API" \ --rotation "opencode:claude-sonnet-4,copilot:claude-sonnet-4" \ --max-iterations 10 When --rotation is used, the --agent and --model flags are ignored . The rotation list takes precedence for agent/model selection. The rotation cycles back to the first entry after reaching the end: - Iteration 1 → Entry 1 - Iteration 2 → Entry 2 - Iteration 3 → Entry 1 wraps around for a 2-entry rotation - ...and so on Invalid rotation entries produce clear error messages: Invalid agent name: Error: Invalid agent 'invalid' in rotation entry 'invalid:model'. Valid agents: opencode, claude-code, codex, copilot, cursor-agent, qwen-code Malformed entry missing colon : Error: Invalid rotation entry 'opencode-model'. Expected format: agent:model Empty values: Error: Invalid rotation entry 'opencode:'. Both agent and model are required. When using --status with an active rotation, the output shows all rotation entries and marks the current one: 🔄 ACTIVE LOOP Iteration: 3 / 10 Prompt: Build a REST API... Rotation position 1/2 : 1. opencode:claude-sonnet-4 ACTIVE 2. claude-code:claude-sonnet-4 The --status command shows which agent and model was used for each iteration: 📊 HISTORY 3 iterations Total time: 5m 23s Recent iterations: 1 2m 10s opencode / claude-sonnet-4 Bash 5 Write 3 Read 2 2 1m 45s claude-code / claude-sonnet-4 Edit 4 Bash 3 Read 2 3 1m 28s opencode / claude-sonnet-4 Bash 2 Edit 1 Check out 🏝️ sandboxed.sh https://github.com/Th0rgal/sandboxed.sh — a dashboard for orchestrating AI agents with workspace management, real-time monitoring, and multi-agent workflows. MIT