Model releases, capabilities, pricing, and benchmarks.
293 posts
Grant the AI octopus access to a portion of your desktop
Community-driven behavioral reliability benchmark for LLMs. 231 probes across 19 modules, deterministic scoring, perplexity correlation, lay...
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents....
The first MCP server for Guesty property management. 38 tools for reservations, guests, messaging, pricing, financials, calendars, reviews,...
Visualize and diagnose OpenClaw context windows to identify token usage, file health, and available space for conversation.
Harvest RSS and HTML news sources in Node.js, deduplicate articles, and build compact digests for LLM context windows
Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.
Portable memory layer for AI agents -*pre-release
Real-time trustworthiness evaluation and safety interception for AI agents. Semantic analysis, safe alternative suggestions, multi-step atta...
The highest-scoring AI memory system ever benchmarked. Now in Rust with rich features — single-binary port from @milla-jovovich/mempalace. F...
MCP server for DeFi execution — lets AI agents swap, provide liquidity, lend, bridge, and run yield strategies across 22 chains
A comprehensive security benchmark for evaluating infrastructure-layer defenses in MCP-based AI agent systems
