Baby-SkyNet
An autonomous memory management system for Claude AI, featuring multi-provider LLM integration and a persistent memory database.
Directory
An autonomous memory management system for Claude AI, featuring multi-provider LLM integration and a persistent memory database.
Turn any OpenAPI/Swagger/Postman spec into an MCP server — give your LLM live access to any API.
A comprehensive, production-ready research server (MCP). Provide your LLM clients with real-time access to the web, data, and more.
A universal REPL session manager supporting Python, Node.js, Ruby, and more, with session management and LLM-assisted recovery.
Query Hyperliquid perp and HIP-3 market data — OHLCV, funding rates, open interest, and positioning — plus quant funding/volatility forecasts, straight from…
LLM proxy that benchmarks AI models on real prompts and finds cheaper, faster alternatives across 340+ models.
The MCP server that gives your LLM a trading account without giving it the keys to blow up your portfolio
Persistent memory for AI agents. Single SQLite file, 192 MCP tools. FTS5 search, knowledge graph, session handoffs, write gate. No server, no API keys, no LLM…
C# SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6…
A reactive AI agent framework for creating agents that use tools to perform tasks, with support for multiple LLM providers and MCP servers.
GPU infrastructure control plane + per-agent LLM FinOps. 74 tools. Deploy, scale, track cost per agent, enforce budgets. MIT license.
Cost-optimised LLM model routing for autonomous agents
Smart token compression for LLM apps. Save 70-90% on API costs with Gemma 4 local compression, multi-model cost tracking, and intelligent model routing.
Structural AI Search Readiness MCP. Audit, dry-run fixes, rescore, doctor. No LLM rankings.
Cut LLM Token Costs by Routing Code Context
Manage, version, and publish LLM prompts via PromptOT. Build structured prompts from blocks, add variables, save drafts, publish versions, and deliver via API…
MCP server that lets AI agents crop screenshots to exact pixel regions before vision LLM inference, paying 0.0005 USDC per crop on Base L2 via x402 — no API…
Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents
An MCP server for the codetoprompt library, enabling integration with LLM agents.
A lightweight, LLM-agnostic RESTful proxy that unifies multiple MCP servers under a single API.
Personalized music recommendations and playlist management for TIDAL, powered by its API and LLM filtering.
An advanced penetration testing tool for automated, LLM-driven security assessments using tools like nmap and dirb.
Compresses long files, prompt inputs, and MCP catalog descriptions into denser context for LLM agents while preserving the useful signal.
Agency OS delivering 26 specialized AI roles over MCP with a real-time retro CRT Pixel Office visualizer and multi-provider live LLM workspace.