Keep coding agents' progress when they crash with a durable harness
Vercel released durable-harness, which wraps Pi, OpenCode, Codex and Claude Code so a run that is killed mid-task can pick up where it stopped instead of forgetting everything. It works locally, on Vercel or on your own infrastructure.
Source
@stretchcloud on X · 2026-10-20
Written in our own words. Credit to the original author. Link checked 2026-10-21.
What they did
Vercel released durable-harness, which wraps Pi, OpenCode, Codex and Claude Code so a run that is killed mid-task can pick up where it stopped instead of forgetting everything. It works locally, on Vercel or on your own infrastructure.
Result (as claimed)
Agent runs survive crashes and restarts instead of losing their in-progress work.
Tools they used
Cost: Claude Code: from $17/mo; OpenAI Codex: free plan, paid from $8/mo; Vercel: free plan, paid from $20/mo.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude Code, OpenAI Codex, OpenCode, Vercel. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Keep coding agents' progress when they crash with a durable harness What the original author did: Vercel released durable-harness, which wraps Pi, OpenCode, Codex and Claude Code so a run that is killed mid-task can pick up where it stopped instead of forgetting everything. It works locally, on Vercel or on your own infrastructure. Reported result (as claimed by the author): Agent runs survive crashes and restarts instead of losing their in-progress work. Source: https://x.com/stretchcloud/status/2112688061515432091 Tools they used: Claude Code, OpenAI Codex, OpenCode, Vercel Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Keep coding agents' progress when they crash with a durable harness What the original author did: Vercel released durable-harness, which wraps Pi, OpenCode, Codex and Claude Code so a run that is killed mid-task can pick up where it stopped instead of forgetting everything. It works locally, on Vercel or on your own infrastructure. Reported result (as claimed by the author): Agent runs survive crashes and restarts instead of losing their in-progress work. Source: https://x.com/stretchcloud/status/2112688061515432091 Tools they used: Claude Code, OpenAI Codex, OpenCode, Vercel Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Keep coding agents' progress when they crash with a durable harness What the original author did: Vercel released durable-harness, which wraps Pi, OpenCode, Codex and Claude Code so a run that is killed mid-task can pick up where it stopped instead of forgetting everything. It works locally, on Vercel or on your own infrastructure. Reported result (as claimed by the author): Agent runs survive crashes and restarts instead of losing their in-progress work. Source: https://x.com/stretchcloud/status/2112688061515432091 Tools they used: Claude Code, OpenAI Codex, OpenCode, Vercel Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to run multiple coding agents together · How to vibe code an app with Claude Code · How to save, share and resume coding agent sessions · How to use Claude Code and Codex together
Related use cases
Browse, back up and move your local AI coding chats between CLIs
An open-source app that shows all your locally saved AI chats across accounts for Claude Code, Codex, Cursor, Gemini CLI, OpenCode and Cline. You can view, back up, export or copy chats, or continue a chat in another CLI.
Run eight AI coding CLIs side by side in persistent rooms on your own machine
SpaceApp is a self-hosted workspace that runs AI coding CLIs side by side in persistent rooms: OpenCode, Codex, Claude Code, Gemini, Qwen, Kimi, Grok and DeepSeek, each in its own pane on your own machine.
Add computer use to any coding agent with an open-source MCP server
open-computer-use wraps computer control (clicking, typing, reading the screen) as an MCP server for macOS, Linux and Windows. Install it with npm, then use its setup commands for Codex, Claude Code, Gemini CLI or opencode; it can run single actions or whole sequences.
Give every coding agent the same structured delivery workflow
AI-DLC from AWS Labs turns AI coding assistants into a structured, verifiable software delivery workflow. One harness-neutral core runs in Claude Code, Kiro, Codex CLI, Cursor, opencode and GitHub Copilot, installed with one command.