AI Agent2025
Composes AI agent teams from a Ghost+Shell+Model formula: each Bot pairs a prompt/MCP/Skills Ghost with a Chat, ClaudeCode, or Dify shell and a model like Claude or DeepSeek. Bots form Teams that run as traceable Tasks, wired to GitHub and DingTalk.
AI Infra2025
Extends vLLM beyond text to serve omni-modal models — Qwen3-Omni, TTS like CosyVoice3, and diffusion image/video/audio generators — in one engine, adding the non-autoregressive Diffusion Transformer support the core project never targeted.
AI Agent2025
Declares and installs agent dependencies from an apm.yml manifest—skills, prompts, agents, plugins and MCP servers—with transitive resolution, security auditing, plugin packaging, and cross-host registries so agents are reproducible across repos.
AI Infra2025
Provides an NVFP4‑optimized training and inference infrastructure for long-form video diffusion models — supports multi-shot AR training, KV-cache and NVFP4 quantized inference, sequence-parallelism and async decoding for higher FPS and longer outputs.
AI Infra2025
Provides Gymnasium-style APIs and tooling to run isolated, networked execution environments for agentic reinforcement learning. Offers async/sync EnvClients, Docker/Kubernetes container providers, a web UI and CLI for scaffolding and deploying environments (Hugging Face Spaces); experimental and evolving.
AI Infra2025
Provides a Gymnasium-style API and tooling to create, deploy, and interact with isolated execution environments for agentic RL training. Includes async/sync clients, a web interface, CLI, Docker-based deployment, and Hugging Face Spaces integration.
AI Infra2025
Orchestrates multiple AI providers to generate context-aware attack payloads, scan web targets for 45+ vulnerability types, and produce compliance-mapped reports. Supports dynamic provider failover, RAG-indexed CVE intelligence, browser automation, and AI triage; requires API keys and authorized testing.
AI Infra2025
Generates production-grade synthetic datasets from scratch or from seed data using dependency-aware samplers, LLM-backed text columns, built-in validators, previewing, and LLM-as-judge scoring.
AI Infra2025
Enforces filesystem and network limits on arbitrary processes at the OS level, no container required. Uses macOS Seatbelt, Linux bubblewrap, and the Windows Filtering Platform; built to sandbox MCP servers and AI agents under a secure-by-default model.
AI Infra2025
Runs recurring workplace tasks across 100+ tools (Slack, GitHub, Gmail, Notion, Linear) as scheduled sub-agents that triage errors, draft outreach, and compile daily briefs. Each run executes in an isolated Firecracker microVM with scoped permissions.
AI Infra2025
Defines a vendor-neutral JSON/YAML semantic model specification and tooling to exchange metrics, dimensions, lineage and other business semantics across analytics, AI and BI platforms; includes a core spec, validators, converters (dbt, GoodData, Salesforce) and example models.
AI Infra2025
Combines a vector store, Cypher-style graph queries, and on-device LLM inference in one Rust engine, with a graph neural network that reranks results and adapts to query patterns in under a millisecond. Services ship as self-contained .rvf containers.