AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

Taz33m/codex-demo-day-arena

Product-foundry control plane for AI coding agents: validator gates, buyer scoring, compute allocation, and Demo Day-style investment decisions across startup product candidates. Next step would be in automating outreach to get real PMF validation and iterate from there.

Python MIT GitHub ↗
★ 0
stars
100
AI relevance
50
solo dev
0
tool sigs

SUMMARY AI summary by gpt-5-mini

Codex Demo Day Arena is a control-plane for evaluating AI-built product candidates like a venture portfolio. It orchestras repo-owner agents, maturity validators, synthetic buyer-usefulness judges, a compute-allocation policy, proof prioritization, and IC-style stopping rules to decide which candidates merit further compute or external validation. Who uses it: product-foundry operators, repo-owner agents, evaluators and researchers building governance for agentic product pipelines. Key features: - Validator gates enforcing structural readiness (demos, tests, artifacts). - Buyer-usefulness rubrics producing plausibility scores and recommendations. - Compute allocator that funds rounds only when DeltaInvestmentBelief > cost+risk. - Proof prioritizer that ranks “proof-now” candidates and enforces external-proof before investment. - Public control-plane artifacts: policies, prompts, scripts, sanitized examples, and a technical paper. Core result: 20 candidates assessed, 20 structurally ready, 19 buyer-compelling, 0 investment-grade proofs.

GitHub Topics

#agent-orchestration #ai-agents #codex #evals #startup #product-foundry

Language breakdown (by bytes)

TeX
23.6%
Python
75%
Mermaid
1.3%
Makefile
0.2%

Owner

Account
Taz33m
Type
User
Followers
1

a bit of everything, aptitude

Dates

Created on GitHub 2026-05-13
Last push 2026-05-13
First seen here 2026-05-13
Last fetched 2026-05-16 18:19

Similar repos (same language)

bgzhang1/sw2api

Reverse proxy for your ai quota from the SW platform.

Python 19 AI 45
dea6cat/2b-agent

This llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus

Python 1 AI 75
Zuboy/Carbon-Cost-Optimizer-Agentic-AI

An AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.

Python 1 AI 75
FuchaZ/lm-studio-vision-bridge

给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务

Python 1 AI 45
Shrutirowlo/AI-Video-Agent

AI-powered video generation agent that automates script analysis, scene planning, and video creation.

Python 1 AI 75
Shivang0/social-vision

Paste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.

Python 1 AI 70
markusbegerow/claude-fuer-oeffentliche-verwaltung

⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.

Python 1 AI 75
knowledgegut/course-distiller

把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF;最後的重組交還人腦。A Claude Code skill by 知識包小腸.

Python 1 AI 45