AIAny
AI Agent2025
Icon for item

Build with Claude

Searchable plugin marketplace and curated collections of Claude Code agents, commands, hooks, skills and plugins — lets users discover, browse, and install subagents and tooling via a web UI, plugin commands or a CLI. Indexes community plugins and MCP servers and provides curated packs.

Introduction

As Claude Code deployments multiply, the hard part is not building a single agent but discovering interoperable subagents, commands and server integrations that actually plug into your workflow. This repo centralizes curated collections and a searchable marketplace so teams can find Claude-compatible agents, slash commands, hooks and plugin bundles without hunting individual repositories.

What Sets It Apart
  • Broad, indexed surface: curated collections (117 agents, 175 commands, 28 hooks, 26 skills, ~50 plugin bundles) plus indexing of thousands of external items (20k+ community plugins, 4,500+ MCP servers, 1,100+ marketplaces). This makes it a practical first stop for discovery rather than a single-package library.
  • Multi-surface access: browse via a Web UI, add the marketplace into Claude Code with a single plugin marketplace command, or use the provided CLI (bwc-cli) to interactively discover and install items — so discovery can fit GUI, editor, or pipeline workflows.
  • Packaging and conventions: plugins are organized with consistent metadata (agent/command/hook frontmatter) and curated install commands, reducing friction when adding subagents to Claude Code environments or sharing setups across teams.
Who it's for — and tradeoffs

Great fit if you run or explore Claude Code workflows and need a consolidated place to discover interoperable subagents, tools, and MCP server listings; especially useful for teams wanting curated starter packs or quick install commands. Look elsewhere if you need a single-vendor, production-grade plugin hosting SLA (this is a community-curated GitHub marketplace repo) or if you require deep security guarantees and audits beyond community vetting. The repo speeds discovery and prototyping but relies on contributors for quality and maintenance.

Information

  • Websitegithub.com
  • AuthorsDave Poon
  • Published date2025/07/25

Categories

More Items

Adapts LLM agents online by self-distilling verified execution trajectories into persistent LoRA weights during deployment to improve success and efficiency on long‑horizon tasks. Uses a frozen stable copy as a privileged teacher to predict hindsight next‑token distributions and filters invalid-action turns so experience consolidates without external solutions or memory retrieval.

Hugging Face

Provides 5.5K+ self-contained data-analysis RL tasks: each row bundles a real tabular dataset, a question, and a deterministically-gradable gold answer. Verified from jupyter-agent notebooks; splits for training, held-out testing, and quick eval; intended for prompting, fine-tuning, and agent RL.

Hugging Face
AI Model2026

A 9B agentic multimodal SFT checkpoint distilled from Qwen3.5-9B for coding, general agent tasks, visual coding and cybersecurity. Provided by Xiaomi MiMo as a research seed (77.4B-token SFT mix) to bootstrap agentic RL and tool-use experiments.