GitHub Trending on November 15, 2026
Repositories that trended on GitHub that day, ranked by stars gained that day.
- 1
Inject curated modern web platform guidance into coding agents through a local CLI skill.
- 2▲6dream-num/univer+1,041
An embeddable office SDK that lets teams put spreadsheets, docs and slides inside their own product or agent pipeline.
- 3▲9
A local browser review surface where you annotate coding agent plans and diffs, then send notes back to the agent.
- 4▲7
Real-time GPU video player and capture enhancer for Windows with super resolution, denoising, HDR and frame generation.
- 5▼1
Lets coding agents drive a live Chrome instance to record traces, inspect network traffic and debug web apps.
- 6▲1
Claude Skills toolkit that structures market review, trade planning, risk checks, and journaling for time-constrained retail investors.
- 7▼5
A code-review CLI that mixes deterministic pipeline steps with an LLM agent to post precise line-level findings.
- 8▼3we-promise/sure+520
Self-hostable personal finance and wealth management app for tracking net worth, cashflow, spending, and investments.
- 9▲8
Self-hosted platform that orchestrates CodeBuddy, Codex and Claude Code through sandboxed SOP workflows with human approval gates.
- 10▲9
An open event-based protocol for connecting AI agent backends to frontend applications.
- 11▼1
A self-hosted uptime monitor for people who want to watch their own services without paying for a hosted uptime service.
- 12▲2
A GUI tool for Linux that audits nearby WiFi networks: capture traffic, run deauth attacks, grab handshakes and crack passwords.
- 13NEW
Agent skills that let coding assistants drive Google Stitch to turn frontend code into designs, and designs back into React.
- 14▲1
Cuts token spend in coding agent sessions by shortening replies and compressing what the agent reads, without touching your prompts.
- 15NEW
A Claude Code skill bundle that loads bug-hunting and external red-team methodology by topic, with per-vulnerability-class patterns, validation gates and reporting.
- 16NEW
A three-tier framework for validating, deduplicating, and live-testing AI agent skills before you ship them.
- 17▼1
A terminal AI coding agent that can read, edit, run and review code, with editor, desktop, web and chat interfaces.
- 18NEW
A dependency-free C/C++ tensor library with quantized kernels and CPU/GPU/NPU backends, for running or building machine-learning inference.
- 19▼1
Serve quantized LLMs natively on Apple Silicon and NVIDIA GPUs with an OpenAI-compatible API and no Python.
Latest reads
Static Recompilation and Console Game PC Ports on GitHub: Where 70+ Projects Came FromRising right now
By stars gained in the last hour
- dream-num/univerAn embeddable office SDK that lets teams put spreadsheets, docs and slides inside their own product or agent pipeline.+97/hr
- elementalsouls/Claude-BugHunterA Claude Code skill bundle that loads bug-hunting and external red-team methodology by topic, with per-vulnerability-class patterns, validation gates and reporting.+52/hr
- alibaba/open-code-reviewA code-review CLI that mixes deterministic pipeline steps with an LLM agent to post precise line-level findings.+45/hr
- NVIDIA/SkillEvaluatorA three-tier framework for validating, deduplicating, and live-testing AI agent skills before you ship them.+44/hr
- GoogleChrome/modern-web-guidance-srcInject curated modern web platform guidance into coding agents through a local CLI skill.+43/hr