Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
sub-agents-mcp
MCP serversDefine task-specific AI sub-agents in Markdown for any MCP-compatible tool.
git clone https://github.com/shinpr/sub-agents-mcp.git -
deepseek-as-subagent
MCP serversRun DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded Bash.
git clone https://github.com/PsChina/deepseek-as-subagent.git -
capa
MCP serversOne capabilities.yaml wires skills, tools, rules, sub-agents, MCP servers, and plugins into Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and 30+ other AI coding agents
git clone https://github.com/infragate/capa.git -
vectora
MCP serversAI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.
vectora-agent@0.1.0rc3 -
paraglide-messages-mcp
MCP serversValidated, sub-agent per-locale translation of Paraglide JS / inlang message-format projects.
paraglide-messages-mcp@0.3.0 -
luftpause
MCP serversasync/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs
ghcr.io/luftpause/runtime:v0.1.4 -
Agent Intern
MCP serversDelegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.
agent-intern@0.37.1 -
subtask
MCP serversBackground sub-agents for Claude Code, Codex, Kimi and OpenCode, over MCP, with a spend cap.
subtask-mcp@0.5.9 -
Open Computer Use
MCP serversGive any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents
-
Run Budget Guard
MCP serversHard dollar, token, call and time caps shared by every sub-agent in one agent run.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.