Skip to content
View sergestack's full-sized avatar
💯
💯
1 follower · 0 following

Block or report sergestack

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sergestack/README.md

Sergey Kryuchkov · SergeStack

I stress-test AI coding agents and build tools to run them better. Real benchmarks, what breaks, and the tooling that came out of it.

📣 Findings posted on X: @SergeStack

🛠️ Tools

Tool What it does
aiusage One terminal dashboard for usage and limits across Claude Code, OpenAI Codex (multi-account) and Grok
More coming Agent orchestration and memory tooling from my own setup

aiusage

🧪 What I work on

  • Multi-agent orchestration on self-hosted Linux
  • Local LLMs vs API: cost, speed, and where each fails
  • Agent memory (Qdrant + Postgres)
  • Token efficiency and cost control for coding agents

🏢 Company

Founder of GLINVEN, a New York software and automation company.

📬 glinven.corp@gmail.com

Pinned Loading

  1. aiusage aiusage Public

    One terminal dashboard for the usage / limits of Claude Code, OpenAI Codex (multi-account) and Grok

    Python

  2. carryforward carryforward Public

    Keep coding when your AI agent hits its limit — automatic Codex account failover with session handoff

    JavaScript