Lightpanda

Open-source sandboxes and SDKs for AI agents that control desktops

Open-source computer-use infrastructure for agents that need to drive desktop environments in the background. CUA includes Cua Driver, Sandbox, Run, Bench, and Verified Data across Linux, Windows, macOS, and Android, with MCP and CLI surfaces for screenshots, accessibility trees, keyboard/mouse actions, shell commands, task evaluation, and fleet execution.

The 5MB open-source agent daemon that hides nothing

CrabTalk is a lightweight five-megabyte daemon that streams every AI agent event to your client in real time including text deltas, tool calls, and thinking steps. It provides complete transparency into agent operations with one-curl installation and bring-your-own-model support. Designed as the observable alternative to opaque agent runtimes where you cannot see what the AI is actually doing.

ACP skill definitions giving coding agents HuggingFace ML superpowers

Hugging Face Skills is the official collection of ACP skill definitions that give AI coding agents access to HuggingFace ML capabilities. The 13 skills cover LLM fine-tuning with TRL, vision model training, dataset management, model evaluation, and cloud job submission on HF infrastructure. Compatible with Claude Code, Codex, Gemini CLI, and Cursor via a single npx command.

AI agent skill that researches topics across social platforms and web

last30days-skill is an agent skill for Claude Code and other AI coding agents that researches topics by scanning social platforms, news sites, and web sources from the past 30 days. It aggregates recent discussions, launches, and community sentiment into actionable research summaries. With 17,400 GitHub stars and MIT license, it has become one of the most popular agent skills in the emerging ACP ecosystem.

Self-hosted AI platform with RAG, agents, and 40+ connectors

Onyx is an open-core, self-hostable AI knowledge platform for enterprise search, RAG chat, deep research, custom agents, and workplace connectors. It connects to 40+ apps, supports permission-aware retrieval, and offers Cloud, Docker/Kubernetes, and enterprise deployment paths for teams that need controlled internal AI search.

Open standard for portable skills across AI agents

Agent Skills is the open SKILL.md folder specification for packaging reusable instructions, scripts, references, and assets that compatible AI agents load through progressive disclosure. Originally developed by Anthropic and released as an open standard, it defines the portable format itself—not an example library, marketplace, or hosted agent product.

Heterogeneous CPU-GPU inference and SFT for large MoE models

Open-source framework for running and fine-tuning large Mixture-of-Experts models with heterogeneous CPU-GPU execution, optimized kernels, limited VRAM and SGLang or LLaMA-Factory integrations.

Official Kubernetes and Helm reference stack built on the vLLM inference engine

Official vLLM reference implementation for scaling the existing inference engine on Kubernetes with Helm, request routing, KV-cache offload, autoscaling and Prometheus/Grafana observability.

Distributed inference orchestration above vLLM, SGLang and TensorRT-LLM

Open-source, datacenter-scale orchestration layer that coordinates vLLM, SGLang and TensorRT-LLM across nodes with disaggregated serving, KV-aware routing, multi-tier cache management and automatic scaling.

Open-source GPU control plane for scalable AI model serving

Open-source GPU cluster manager that configures vLLM, SGLang, TensorRT-LLM or custom engines, serves models through compatible APIs, and provisions SSH-accessible GPU instances across on-premises, Kubernetes and cloud environments.

Disaggregated KV cache storage and transfer for LLM serving

Open-source infrastructure for disaggregated LLM serving that pools KV caches across prefill and decode workers, with high-performance transfer, distributed storage and integrations for vLLM and SGLang.