#Python

browser-use

browser-harness

★ 17,569

Browser Harness | Self-healing harness that enables LLMs to complete any task.

caronc

apprise

★ 17,322

Apprise - Push Notifications that work with just about every platform!

NVIDIA

SkillSpector

★ 17,309

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

bradautomates

claude-video

★ 17,228

Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.

RyanCodrai

turbovec

★ 17,181

A vector index built on TurboQuant, written in Rust with Python bindings.

microsoft

SkillOpt

★ 17,121

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Robbyant

lingbot-map

★ 17,052

A feed-forward 3D foundation model for reconstructing scenes from streaming data.

AgriciDaniel

claude-seo

★ 16,971

Universal SEO skill for Claude Code. 25 sub-skills + 18 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, backlinks, local SEO, maps intelligence, semantic clustering, e-commerce SEO, international SEO, Google APIs, and PDF/Excel reporting. Optional DataForSEO, Firecrawl, and Banana extensions.

cft0808

edict

★ 16,894

三省六部制 · OpenClaw Multi-Agent Orchestration System, 9 specialized AI agents with real-time dashboard, model config, and full audit trails.

suitenumerique

docs

★ 16,820

Docs is an open-source text editor: web-native, made for real-time collaboration, cleanly structured documents and sub-documents with full ownership of your data. Built to scale with Django and React.

xbtlin

ai-berkshire

★ 16,341

AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.

wanshuiyin

Auto-claude-code-research-in-sleep

★ 16,160

ARIS (Auto-Research-In-Sleep), Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in, works with Claude Code, Codex, OpenClaw, or any LLM agent.

img2threejs

img2threejs

★ 15,983

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

treeverse

dvc

★ 15,870

Data Versioning and ML Experiments. When you make changes, only run the steps impacted by those changes.

opensandbox-group

OpenSandbox

★ 15,273

Secure, Fast, and Extensible Sandbox runtime for AI agents. Sandbox Runtime: Built-in lifecycle management supporting Docker and high-performance Kubernetes runtime, enabling both local runs and large-scale distributed scheduling.

scipy

scipy

★ 15,014

SciPy library main repository. NumPy and SciPy are easy to use, but powerful enough to be depended upon by some of the world's leading scientists and engineers.

AgriciDaniel

claude-obsidian

★ 14,933

Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.

kyegomez

OpenMythos

★ 14,895

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

alexta69

metube

★ 14,745

Self-hosted video downloader for YouTube and other sites (web UI for yt-dlp).

aiming-lab

AutoResearchClaw

★ 14,430

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper.