1-day current streak·29-day longest streak
-
fog-agents ★ PINNED
Portable AI agents for early-stage founders. Market signal, first users, SEO, landing page, cold outreach. Works with Claude Code, Cursor, Codex CLI, Gemini CLI.
Python ★ 3 1mo agoExplain → -
llm-finance-framework ★ PINNED
Empirical framework for evaluating Large Language Models in financial decision-making. Compare AI agents against traditional quantitative trading strategies with rigorous statistical validation, memory adaptation analysis, and behavioral pattern detection.
Python ★ 0 24d agoExplain → -
counterpoint ★ PINNED
A producer-critic loop inside Claude Code: Claude Opus and OpenAI Codex cross-check each other before a turn ships.
Shell ★ 1 20d agoExplain → -
swanclip ★ PINNED
Simple AI skills to turn one long video into short-form clips and carousels for X, Instagram Reels, TikTok, LinkedIn, and YouTube Shorts. Offline, CPU-only, on your own brand.
Python ★ 3 1mo agoExplain → -
cli-skills ★ PINNED ⑂
No description.
★ 0 4mo agoExplain → -
constraint-coherence
Benchmark for evaluating LLM reasoning failures on implicit physical constraints, with six cognitive scaffolds designed to recover correct reasoning.
Python ★ 0 3mo agoExplain → -
typeform-cli ⑂
No description.
★ 0 4mo agoExplain → -
agent-evals
Test suite framework for non-coding AI agents. Code has tests. Your agents had nothing — until now.
Python ★ 0 4mo agoExplain →
No repos match these filters.