primitive-bench/primitive-bench — The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive B…

Description and use

Primitive Bench provides an open verification layer that turns isolated prompts and tools into repeatable, multi‑agent workflows by offering fixed‑price, verifiable AI outcomes with automatic refunds if the result isn’t delivered. Its Python‑based SDK/API/CLI makes it easy to integrate into existing pipelines for coordinating agents, adding tool‑use pipelines, and standardizing memory, enabling a straightforward pilot adoption. With recent activity, strong ecosystem signals, and 127 GitHub stars, the project shows high production readiness for an OSS candidate, pending a final review of license, security, and maintainer activity.

Problem

primitive-bench/primitive-bench helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it, refunded if the outcome isn't delivered. This repo is the open verification layer.

Source