AI agent
primitive-bench
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.
- Rank
- #2309 of 2,677
- Stars
- 127★
- On radar
- since 2026-07-23
Momentum
rate of rise, not size · recomputes hourly
17.7
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
primitive-bench is an AI agent ranked #2309 of 2,677 on the Cresting momentum radar, with a score of 17.7. It has 127 GitHub stars, and has been tracked since 2026-07-23.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.283 |
| Recency boost | 0.071 |
| Signal decay | 0.994 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+0 in window · 4 latest · 2 snapshots
github · stars+0 in window · 127 latest · 2 snapshots
Related ai agents
- goutoujunshi一个先接住情绪、再分析关系并给出可执行策略的 Codex 恋爱军师，内置心理、法律、社会、人文、哲学、婚姻家庭与性学知识库，支持多元关系。#1 · 647★
- video-shotcraftAI video skill for Claude Code & Codex — cinematic product videos with Remotion: 106 shot recipe cards, 161 motion previews, a production-ready template#2 · 984★
- open-krittOrchestrate AI agents to find real vulnerabilities in code.#3 · 359★
- klaatcodeOpen-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.#5 · 268★
- img2threejsRebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.#6 · 3,014★