Code

Production-proven Polymarket CLOB V2 trading and data. Fail-closed fills; keys stay local.

AI-native MCU debugging and observability through probes, symbols, RTOS, logs, and build tools.

WAF security testing: 5,500+ payloads, 25 WAF fingerprints, 21 recon checks, bypass AI

Recursive Claude spawning for autonomous project builds with self-healing test loops

Autonomous AI development system with persistent task queue and background execution

Detect when AI code changes exceed declared task scope (MCP server).

Autonomous QA MCP for web and macOS that tests like a real engineer, finds bugs, and verifies them.

JSON-first Coreutils CLI for AI agents. 114 commands with sandbox, dry-run, and MCP support.

Secure Python sandbox for data optimization and Matplotlib rendering via x402 microtransactions.

Session memory for AI coding agents. Search past sessions, extract rules, and track what works.

Architecture diagram with concurrency capacity and bottleneck estimates from any codebase.

The canonical Python stdlib oracle for AI coding agents — always free, always MIT, token-frugal.

Is this number real, or is it noise? Peek-safe A/B tests, change detection, honest forecasts.

MCP server for MigratorXpress — cross-platform database migration with parallel transfer

Static blast-radius audit for MCP servers before agent install. Manifest optional.

Open-source, self-hosted conversation QA for voice agents. MIT.

Visual tech-stack inventory of any codebase: languages, frameworks, databases, AI SDKs, infra.

Durable MCP control plane for long-running Codex Desktop tasks.

Reports which of your code's API usages break when you upgrade a dependency (Python, .NET, Java).

Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.