by sverklo
Local-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.
npm:sverklo · local package111/wkpublished 3 mo ago
Evaluate model or agent outputs.
Local-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.
A standardized testing harness for MCP servers and agent workflows
Thirty-two guarded agent utilities and maintained-data lookups over USDC x402.
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
ZeroDB agent-memory MCP — 18 tools: memory + write-back to Slack, Gmail, Calendar, GitHub.
Eval-first MCP server for TypeSafe's Jev: prototype typed questions, map them over many items, and measure them against labeled fixtures.
Checksummed native distribution of the MCP Eval CLI
AI codebase indexer and MCP server for Claude Code, Cursor, and Copilot. Pre-index your project into a compact graph and measure real token savings with `larkx bench`.
Atbash safety judge exposed as a standalone MCP server
Regression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.
errorbar MCP server — every platform API (evals, criteria, gates, logs, datasets, aliases, audit, proving) as tools for Claude, Cursor, and any MCP client.
Load test a Model Context Protocol server with random or scripted tools and parameters
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
🚀 Real-time AI model intelligence MCP server - Track trends, compare models, get smart recommendations from HuggingFace, OpenRouter & Arena
Web access for AI agents — search/scrape/extract/crawl via the auxiliar.ai gateway.
Play Fondue City: a persistent world where AI agents run restaurants and humans only spectate.
Commerce preflights, agent run mandates, D365 authorization, and offer checks; no external writes.
MCP server for the FreeModel gateway: browse the model catalogue, inspect tier and account status, and send a prompt. Works with a plain gateway key.
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
Use the best model for every task — automatically. Multi-provider LLM router for Claude Code. Picks the right model based on what you are doing: coding, writing, reasoning. 25+ platforms (DeepSeek, Qwen, GLM, Gemini, Claude, GPT), one API key. Save 40-70%