AI Agent2026
Runs shared, self-hosted AI agents in isolated Kubernetes sandboxes accessible from Slack or an API. Provides durable workflows, reusable tool plugins, and network-edge credential injection (iron-proxy) so agents can execute real work securely and audibly for teams.
AI Infra2026
Routes LLM API traffic across providers by translating OpenAI, Anthropic, and OpenAI Responses formats, and orchestrates multi-backend routing with typed algorithms and Prometheus metrics. A Rust proxy/library offering launcher, standalone server, and embeddable routing components; experimental (pre-alpha).
AI Train2026
End-to-end Python framework for training and serving NVIDIA's Cosmos world models (Cosmos3), integrating distributed training (FSDP/TP/CP/PP), DCP/safetensors checkpoints, dataset adapters, multiple inference backends, online serving, and agent skills.
AI Agent Papers2026
Matches detection paradigms to four stratified attack-surface layers of AI agents — infrastructure, protocol/tool, agent behavior, and model — and presents AI-Infra-Guard: an open-source red-teaming framework with rule-based infra scanning, LLM-driven audits of MCP servers and skill packages, and a jailbreak/attack-operator harness.
Enables RL post-training with million-token prompts under a fixed GPU budget by evaluating shared prompt state without autograd, retaining only minimal model state, and replaying short response branches; instantiated as GRPO and demonstrated on Qwen3.6-27B and GLM-5.2 up to multi-million token execution.
AI Infra2026
Indexes chemistry literature as provenance-bearing atomic claims and provides a faceted taxonomy, evidence graph, and REST/SDK/MCP APIs so researchers and AI agents can retrieve verifiable, claim-level findings across papers; live index contains 2.4M claims from 147K papers.
Tao Feng, Fangxu Yu +10University of Illinois Urbana-Champaign, University of Maryland, College Park +3
Frames LLM routing as a sequential decision process and introduces LLMRouter plus the xRouteBench benchmark to develop, evaluate, and deploy learned routing policies across heterogeneous LLMs, optimizing response quality versus inference cost.
Enables interactive serving of large Mixture-of-Experts (MoE) models on personal machines by adapting offload and execution to measured device bandwidth and agentic workload patterns. Key features include bandwidth-adaptive execution, semantic-aware caching of recurrent state, and an elastic GPU expert cache; supports 20+ MoE models and runs models from ~35B to 753B on consumer/workstation GPUs.