Maintainer of this skill?
by vercel-labs
Durable coding-agent harnesses (Claude Code, Codex, OpenCode, Pi, fx) on a Workflow SDK World
# Add to your Claude Code skills
git clone https://github.com/vercel-labs/durable-harnessGuides for using ai agents skills like durable-harness.
See how durable-harness compares with popular alternatives.
durable-harness is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by vercel-labs. Durable coding-agent harnesses (Claude Code, Codex, OpenCode, Pi, fx) on a Workflow SDK World. It has 51 GitHub stars.
durable-harness's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/vercel-labs/durable-harness" and add it to your Claude Code skills directory (see the Installation section above).
durable-harness is primarily written in TypeScript. It is open-source under vercel-labs on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh durable-harness against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
durable-harness runs coding-agent harnesses (Pi, OpenCode, libfx's fx, Claude Code and Codex) as durable agents on a Workflow SDK World. Each session is a workflow run: its conversation, the turn in flight and every model and tool call are in the run's event log, so a crash anywhere resumes the turn from the log on another machine, and a tool call that isn't safe to repeat is never run twice.
[!NOTE] durable-harness is experimental: it's on
0.0.x, and its API may change between releases.
Install it with a harness, here Pi with pi-durable, in a Next.js app:
npm install durable-harness @earendil-works/pi-durable @earendil-works/chord @earendil-works/pi-ai just-bash
Open Pi's own durable Harness on a World-backed storage. Agents are
tool-less by default; Pi's coding tools go on a virtual workspace, whose files
live in the session's log:
// lib/agent.ts
import { BACKGROUND_CONTEXT as ctx } from '@earendil-works/chord/context';
import { createRegistry, Harness, type Storage } from '@earendil-works/pi-durable';
import { CodingTools, GATEWAY_PROVIDER, gatewayModels, resumeWith, virtualEnv } from 'durable-harness/pi-durable';
const models = gatewayModels();
const registry = createRegistry();
registry.install(CodingTools);
export const agent = { model: { provider: GATEWAY_PROVIDER, modelId: 'anthropic/claude-sonnet-4.5' } };
export const open = resumeWith((storage: Storage) => Harness.open(storage, { models, registry, env: virtualEnv() }, ctx));
Serve it from a chat route, and configure the integration:
// app/api/chat/route.ts
import { chatRoute } from 'durable-harness/pi-durable';
import { agent, open } from '@/lib/agent';
export const { GET, POST } = chatRoute({ open, agent, authorize: async (request) => { /* your auth */ } });
// next.config.ts
import type { NextConfig } from 'next';
import { withDurableHarness } from 'durable-harness/next';
const nextConfig: NextConfig = {
// your existing config
};
export default withDurableHarness(nextConfig);
Choose your harness and framework in the agent harnesses docs.
durable-harness/pi-durable
(recommended: Pi's own durable Harness on a World), or durable-harness/pi.durable-harness/opencode.durable-harness/fx,
libfx's kernel tools for its own durable agents.durable-harness/claude-code and durable-harness/codex. They run only in
the session's own Vercel Sandbox, never in a shared Function
(why).Model-chosen commands and files run on a virtual workspace (virtual()) or
in the session's own Vercel Sandbox (sandbox()), never on the machine that
drives the session. See tools
and security.
Local development uses the Workflow SDK's local World with no configuration. Deploy to Vercel for managed storage, queuing and scaling, with sessions in Agent Runs. To self-host, use the Postgres World or any other World: see self-hosting.
Contributions are welcome. Use issues to collaborate with the team, and read CONTRIBUTING.md before opening a pull request.
If you find a security vulnerability in durable-harness, disclose it responsibly instead of opening a public issue.
To participate in our Open Source Software Bug Bounty program, please email responsible.disclosure@vercel.com. We will add you to the program and provide further instructions for submitting your report.