by neurynae
MCP server for tool discovery: find, compare, and verify tools across 35+ registries.
npm:@neurynae/toolcairn-mcp · local package56/wkpublished 6 mo ago
Model access, evaluation and agent infrastructure.
MCP server for tool discovery: find, compare, and verify tools across 35+ registries.
Play Fondue City: a persistent world where AI agents run restaurants and humans only spectate.
Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.
209 Claude AI skills for faculty members and academic researchers — organized by research domain
Commerce preflights, D365 authorization; opt-in agent writes require authorized backend connectors.
Fast, cheap, probability-scored decisions for coding agents, scripts and CI: a CLI and MCP server for the OpenAI Decisions API and Jev (TypeSafe AI)
22 tools: search 15+ marketplaces, verify licenses, childcare costs, FCC, GSA auctions
Search 10,000+ AI agents, MCP servers, and CLI tools via A2ASearch from any MCP client.
ANUS: a free coding agent in your terminal. Every request goes to the smartest free model that is answering today.
An MCP server providing live model pricing data from OpenRouter. Query, compare, and discover the cheapest AI models.
MCP server for OpenRouter web search
Search, compare, and get docs for 210+ APIs ranked by CLI and agent relevance.
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
MCP server for the @agentutility model-router cluster — pay-per-call x402 tools, no API keys, USDC…
AI Agent Skill & CLI for Vanilla-Core Architecture - SSoT state management, Pub/Sub UI updates, surgical DOM updates, zero-dependency modular Vanilla JS web applications, with seamless delegation to material-design.
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%
CLI with React Ink TUI for managing AI skills, agents, MCPs, and bundles across Claude Code, Codex, Amp, Copilot, and Cursor
Pi model provider for Grok Build: Grok keeps its native harness and tools while Pi drives the session over a local stdio ACP child
Shotstack MCP and shared CLI with current Edit/Serve/Ingest schemas and confirmed account operations.