Experimenting in AI Founding DevRel @LiteLLM
Vancouver, Canada
Joined August 2015
- Tweets2.8K
- Following837
- Followers8.7K
- Likes5.9K
No account, no telemetry. Scans in the background while you work.
Free and open source: github.com/misbahsy/novul
Works with any agent: Claude or Codex, desktop or CLI, or any MCP client. NoVul keeps the list fresh; your agent reads the findings, upgrades, and rescans until nothing’s left.
It looks at homebrew, runtimes past end of life, global npm/pipx/cargo installs, your AI tools (Claude Code, Codex, Ollama), and keys left in plain-text files.
It never stores or shows the key. Just tells you (or your agent) what to fix.
Over 100 new CVEs land every day. You and your agents are quietly installing them without knowing.
So I built NoVul, a free open-source menu bar app:
- scans everything locally
- tells you exactly what known vulnerabilities are on your mac
- hands fixes to your agent
- runs quietly in the background
Most startups miss out big on AEO.
Open-sourcing answerrank. Take the guesswork out of AEO.
Give it a URL, and it scores your product across Al models and returns a detailed report on what to fix.
Includes two skills for Claude Code / Codex:
- answerrank: sets up the run, lets you review questions, and summarizes the report
- answerrank-browser: asks the same questions in chatgpt, claude, gemini, perplexity, and google Al Mode directly in your browser
skill: npx skills add misbahsy/answerrank
repo: github.com/misbahsy/answerra…
Built using @LiteLLM
Can I run AI models locally on my machine?
Do I actually need an NVIDIA GPU? What VRAM?
Can I route to local and cloud models with @LiteLLM ?
Quantization, MoE, Batching and more...
A visual learning journey: master-local-ai.netlify.app/
Woah! Argon is a beast! One-shotted this video.
Prompt below:
Gemini 4 Argon, @Google’s flagship reasoning model, is now supported on LiteLLM!
Launch pricing until Nov 30:
Input: $2.00 / MTok
Output: $10.00 / MTok
Cache read: $0.10 / MTok
Pricing and limits: models.litellm.ai/models/gem…
/anatomy explain how @SpaceX Raptor 3 engine works
Introducing Anatomy
Describe a machine in one line. Claude brings it to life.
- Interactive isometric wireframes you can rotate, inspect and explore
- WebGL shaders for fire, water, plasma and more
- Real 3D motion, with individual parts that rotate and move
Install it as an agent skill. Fully open source.
I’ve made and edited thousands of videos using claude/codex over the past year.
Providing high-quality reference material has been the biggest time saver.
24fps aggregates the best videos from over 2,500 creators. Feed the agent the exact recipe (easing, layout, typography), and you save a bunch of tokens and minutes.