Sandbox
52 repos for ros · Any agent · ResearchClear
graph-robots/
open-robot-skills

Skill and tool bundles for gap (graph as policy) — Anthropic Agent Skills format, discovered by path

41

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

4.2k
YizhiSong/
FriesTrader

Robinhood Agentic Trading agent — a fully automated AI trading bot placing real orders through Robinhood's Agentic Trading MCP, under mechanical, auditable risk rules the model cannot override. Able to run unattended on Claude Pro, no metered API spend. Not financial advice.

157
rollingSirius/
equity-research-skill

Possibly the deepest AI equity-research skill: nine-chapter single-stock deep dives and earnings deep-dives, with scripted DCF/EPV/EVA and reproducible valuation. Covers US, HK and A-shares. Docs in EN and ZH.

433
keyuchen21/
agentic-engineering-handbook

The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.

187

The Unitree Go2 MCP Server is a server built on the MCP that enables users to control the Unitree Go2 robot using natural language commands interpreted by a LLM.

87

Lateral thinking skills for AI agents - 8 techniques + a router. de Bono for your coding agent.

298
fabio-rovai/
open-ontologies

AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.

492

Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available.

97
freestylefly/
wesight

Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.

918
AElfProject/
aelf-skills

Unified aelf skills hub for discovery, routing, bootstrap, and health checks across OpenClaw, Codex, Cursor, and Claude Code.

184

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

3.3k

Claude Code–style dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git-worktree isolation, cost accounting, an interactive /workflows TUI, an /ultracode standing opt-in, and deep research.

502
AgentAnycast/agentanycastFrameworks & SDKs

Connect AI agents across any network — zero config, encrypted, skill-based routing

79
mixelpixx/
Konnect

AI-assisted PCB design for KiCAD 10. Native KiCAD plugin — a single Rust binary exposing 217 schematic, layout, routing, placement, design-review, and manufacturing tools to Claude, or the LLM of your choosing

608
mikepapadim/
london-property-hunt-public

Automated London flat/room hunt powered by Claude Code + Claude in Chrome + Gmail MCP. Scrapes 4 rental platforms on a cron, deduplicates via spreadsheet, prioritises HIGH/MED/LOW, and emails ready-to-send outreach.

86
DY-2026/
GameDesignOS

Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.

385
naderelewa/
Product-to-Prod

AI product management skills and plugin for Claude Code, Cowork, Codex & other AI agents: evidence-tagged PRDs, specs, requirements, RICE prioritization, backlog and roadmap scoring, product strategy, GTM launch plans, release verification, benchmark packs, UX/UI design prompts for web + mobile apps. Every claim sourced or labelled unsourced.

42
elusznik/
mcp-server-code-execution-mode

An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.

339

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

3.3k

A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude, and local Ollama models and returns a structured synthesis, as an MCP server that needs no API keys in hosted mode.

70