🧬♻️ An AI-native, build-in-public compounding loop for aging science: falsifiable question → open data → public verifier → honest write-up → share → compound. No wet lab required.

🤖 The most comprehensive, community-driven resourcefor Automated AI Research — papers, tools, people, lbs, roadmaps. Featuring Recursive Lab, Sakana AI, DepMind & beyond.

🧪 the Evaluation Operating System — OEC (Observe → Evaluate → Control) for foundation models, agents, and business objectives

Any design intent in (text, picture) → execution-ready 3D blueprint out — construction- and 3D-print-verified. Game design · simulation · architecture (3DCP+AI) · interior · landscape.

🛠️ FM-os: the living, SLM-first map of foundation-model operations — pre-training, post-training, fine-tuning & RL. Curated repos, courses, papers & jobs, auto-refreshed weekly.

Python framework for building self-monitoring intelligent agents — idle detection, output quality verification (SMARC criteria), and audit trails. Zero external dependencies.

Control theory as an instrument for judging AI systems. A safety claim is worth exactly the weakest assumption holding it up — so the guarantee is capped at what its assumptions actually discharge.

🎬 The ranked, living map of animation tooling — learn it, hand it to your agents (machine-readable graph + llms.txt), keep it fresh. CSS → AI-authored video.

Track 1 RCA agent: rank by magnitude, date by onset. 0.073 -> 0.199 on the dev split, with the ablation that says why.

The 20% Question — a CFO's view of a GPU cluster. MantisGrid Hackathon 2026, Track 2, Team 3: Hugging-Bear.

A loop orchestrator that turns any target into a self-improving, agent-native CLI by driving generate -> judge -> refactor -> re-judge to convergence.

Open-source predictive formation intelligence for seminary and ministry training teams.

All-in interaction with the digital and physical world — one super-repo composing the -anything/-os agent family

secure-anything — the composition layer for agent security: a lean core (registry, router, gate seam, signed ledger) over a rich ecosystem of capabilities and knowledge. AgentGate ships as its firs…

The composition layer for agent security: a lean core (registry, deterministic router, gate seam, signed ledger) over a curated, evidence-tiered ecosystem of capabilities and knowledge. Code Apache…

Evidence-gated benchmark for LLM tool-use over real MCP servers — the answer must be earned through the tools

Life GPS generates for you smart plan that adapts to your ever changing life and tells you what the next best steps should be. So that you will maximally achieve your weekly goals as simple as you …

Open-source agentic portfolio — make yours free, share in one click

An AI-native family field lab where the whole family grows wiser than AI — together. Grown-ups & kids (Daniel 11, David 6) learning to think clearly, use AI well, create real value & serve real peo…

Live demo of the Super U agentic webapp (static landing page)