4-day longest streak
-
hyperresearch
Agent-driven research knowledge base. Agents collect, search, and synthesize web research into a persistent, searchable wiki.
Python ★ 1.4k 1d agoExplain → -
hypercheap-voiceAI
The most cost-effective, highest performance AI voice agent possible today
Python ★ 140 8mo agoExplain → -
GPT_research_assistant
No description.
Python ★ 27 2y agoExplain → -
knack-cli
Knack CLI: agent-friendly skill operations. Self-host on GitHub or use Knack Cloud.
Rust ★ 20 8d agoExplain → -
secret-hitler-bench
An LLM benchmark based on the popular social deception game, Secret Hitler. Test intelligence, long context planning, logic, and duplicitous capabilities of popular AI models.
Python ★ 9 4mo agoExplain → -
llm-kasten
No description.
Python ★ 5 5d agoExplain → -
GPT_Assistant_Grapher
No description.
Python ★ 4 2y agoExplain → -
speedread-skill
Your AI agent reads the codebase. You speedread the report. An agent skill + one-file RSVP reader for markdown reports.
HTML ★ 3 8d agoExplain → -
TAILS_GPT_Sandbox
No description.
Python ★ 1 2y agoExplain → -
winget-pkgs ⑂
The Microsoft community Windows Package Manager manifest repository
★ 0 1d agoExplain → -
obsidian-voiceMD
Voice to text to markdown, instantly.
TypeScript ★ 0 3y agoExplain → -
ember-legal
No description.
HTML ★ 0 20d agoExplain → -
hyperresearchbench
DeepResearch-Bench runner for Claude Code agents. Agent-agnostic harness for testing any Claude Code research workflow against the 100-query DRB benchmark.
Python ★ 0 2mo agoExplain → -
wordle-jordan
No description.
★ 0 5mo agoExplain →
No repos match these filters.