# vercel-labs/durable-harness

> Experimental library that runs coding-agent harnesses (Pi, OpenCode, fx, Claude Code, Codex) as durable workflows on a Workflow SDK World: the session, in-flight turn and every model and tool call live in the run's event log, so a crash resumes from the log and unsafe tool calls are never repeated.

- Magnitude: 4.9 out of 10 — Early signal
- Stars: 153 total · +9 stars measured 2026-10-22, 00:37–04:07 UTC, ≈ 72 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: Apache-2.0 · Created: 2026-10-16 · Last push: 2026-10-19
- GitHub: https://github.com/vercel-labs/durable-harness · Homepage: https://vercel.com/docs/agent-harnesses · Page: https://gitnova.dev/en/r/vercel-labs/durable-harness

## Useful for

- Wire a durable Pi agent into a Next.js app via chatRoute and withDurableHarness
- Resume an interrupted agent turn after a crash by replaying it from the event log on another machine
- Isolate agent-run commands in a virtual workspace or a dedicated Vercel Sandbox

## Why it’s here

- Star-counter measurements on 2026-10-22 (UTC), 00:37–04:07: 144 → 153 stars (+9). This is the change over that interval.
- Estimated end-of-day forecast: about +72 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 153 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #145.
- Recent forks include notable developers: @davila7 (2,430 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 8
- Issues and pull requests: 22
- Watchers: 2
- Average over the last week: 32 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 3

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-10-16 … 2026-10-22: 0, 2, 2, 1, 65, 83, 9

## Magnitude by day, last 2 days

10-21 3.7, 10-22 4.9

## Spotted in now

- Top new repositories this week: #145

## More in this category

1. **google-research/harness2** — 7.8 · Peaking · AI agents · Python · +122 stars measured 2026-10-22, 00:37–04:07 UTC, ≈ 1,079 by evening
   A framework for recursive optimization of AI agent harnesses (prompts, tools, memory, skills) without fine-tuning model weights, with JobBench, LAB and WorkBuddy-Bench benchmarks.
   Full card: https://gitnova.dev/en/r/google-research/harness2.md
2. **ai-job-search-dev/ai-job-search** — 7.3 · Peaking · AI agents · Python · +95 stars measured 2026-10-22, 00:37–04:07 UTC, ≈ 1,273 by evening
   A job application framework built on Claude Code: evaluates postings, tailors CVs, and writes cover letters. Runs locally, focused on the Danish job market.
   Full card: https://gitnova.dev/en/r/ai-job-search-dev/ai-job-search.md
3. **Graphify-Labs/graphify** — 6.8 · Breakout · AI agents · Python · +215 stars measured 2026-10-22, 00:37–04:07 UTC, ≈ 1,239 by evening
   Turns any codebase, docs, SQL schemas, configs, and PDFs into a queryable knowledge graph. Works as a /graphify skill in Claude Code, Cursor, Codex, and Gemini CLI with local deterministic AST parsing.
   Full card: https://gitnova.dev/en/r/Graphify-Labs/graphify.md
4. **aicodeking/pandacode** — 6.1 · Early signal · AI agents · Rust · +12 stars measured 2026-10-22, 00:37–04:07 UTC, ≈ 175 by evening
   A native desktop workspace for managing and running coding agents. It unifies projects, Git, terminal, and LLM tools in one window.
   Full card: https://gitnova.dev/en/r/aicodeking/pandacode.md
5. **bowenliang123/dsh-context** — 6.1 · Breakout · AI agents · TypeScript · +68 stars measured 2026-10-22, 00:37–04:07 UTC, ≈ 378 by evening
   A DeepSeek Harness plugin that visualizes an agent's context: dashboard, browser, sidebar panel and /context command showing composition, stats and evolution of the context window.
   Full card: https://gitnova.dev/en/r/bowenliang123/dsh-context.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-22 04:18 UTC, updated every 30 minutes.