Code

Security for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.

Check generated audio, video and stills for defects. Returns a verdict, not more media.

Concurrent Builder + Breaker agents generate code and adversarial tests at once, gated in CI.

Generate complete, tested FastMCP 3.x MCP servers from one plain-English sentence.

Self-curating agent memory kept honest by survival-based selection over measured outcomes.

CUDA-Q docs, API reference, and runnable examples for AI agents, pinned to your installed version.

Test generation, mocks, coverage analysis for AI agents

Use Llama AI Chat to test Meta Llama 4 Maverick on code review, long PDFs, and screenshots.

AI-powered social media management. Create, schedule, and publish posts across Twitter/X, Instagram, LinkedIn, TikTok, Threads, Bluesky, Pinterest, Facebook, and more — over MCP or REST.

The full Prufa QA agent over MCP: audits, flows, monitors, gremlin chaos, discovery.

SWI-Prolog as a logic calculator for LLMs

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

Multi-model AI orchestration MCP server with code review, compare, and debate tools.

Local multi-channel message emulator for E2E testing, with MCP tools for LLM agents.

Multi-table synthetic data with FK integrity and exact declared aggregates. No real data.

FRC documentation MCP server for WPILib, REV, CTRE, Redux, and PhotonVision.

Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.

LLM-assisted biomedical literature screening and extraction for PubMed, GEO, and preprints.

x402 CVE triage MCP: EPSS + CISA KEV -> exploit priority, $0.01 per query.

Run JavaScript and TypeScript in sandboxed V8 isolates with policy-controlled host capabilities.