Skip to content
View alvabillwu's full-sized avatar
  • Joined Jun 29, 2026

Block or report alvabillwu

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.

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

Popular repositories Loading

  1. tokencost tokencost Public

    🔢 LLM Token Cost Calculator — count tokens, estimate costs, compare models across OpenAI, Anthropic, Google, Meta & more from the CLI

    Python

  2. mcp-probe mcp-probe Public

    🔌 Probe and inspect any MCP (Model Context Protocol) server from the CLI — zero-dependency, discover tools/resources/prompts, invoke tools

    Python

  3. promptdrift promptdrift Public

    🔄 Detect drift between LLM prompt versions — line + variable diffs, breaking-drift detection, severity scoring for CI. Zero dependencies.

    Python

  4. ai-supply-guard ai-supply-guard Public

    🛡️ Audit npm dependencies for AI-specific supply-chain attacks — postinstall hooks targeting ~/.claude/settings.json, MCP injection, prompt-injection payloads, env exfil. Risk-scored, CI-ready.

    TypeScript

  5. ragbench ragbench Public

    📊 Lightweight RAG pipeline benchmarking — synthetic datasets, deterministic retrieval+generation metrics, reproducible scorecards. Framework-agnostic, zero core deps.

    Python

  6. agentlog agentlog Public

    📝 Structured logging and replay for AI agent runs — trace every LLM call, tool use, and step as JSONL; replay, summarize, and audit what the agent did. Zero deps.

    Python