Initialize and manage specialized AI sub-agents for Claude Code in your project
A pi extension extension that brings smart Claude Code-style autonomous sub-agents to pi.
CLI tool for spawning and managing multiple Cursor sub-agents in parallel with feedback loops
Elyra extension for Laravel AI SDK -- agents, sub-agents, tools, structured output, embeddings, and more
Agent switcher, sub-agents, permissions and approval gateway
OpenCode TUI sidebar plugin that shows running background sub-agents.
A pi extension that brings Claude Code-style autonomous sub-agents to pi. Friendly fork of @tintinweb/pi-subagents.
Multi-phase security audits with specialist sub-agents, isolated context windows, capped concurrency, and resumable state — packaged as a Pi extension.
Public Pi package that adds in-process sub-agents via the SDK
Coding agent CLI with persistent memory, sub-agents, intelligent routing, and orchestration
Sub-agents extension for pi coding agent.
OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment
Un CLI interactif à la Claude Code : slash commands, skills, sub-agents, MCP — avec provider démo (pas de clé API).
TypeScript boilerplate with skills and sub-agents for Claude Code. Prevents context exhaustion through role-based task splitting.
Lightweight sub-agents for pi — spawn specialized agents with isolated sessions, tools, and models.
Multi-agent development orchestration with Claude Code + cmux. Spawn, monitor, and integrate parallel sub-agents visually in terminal panes.
Portable AI development framework — agents, sub-agents, skills and tools for AI-assisted development
Pi extension: Claude Code-style autonomous sub-agents with live widget, parallel execution, mid-run steering, and custom agent types
ClaudeHub CLI - Sync skills, workflows, and sub-agents like git
EpisCloud coding agent SDK — typed tools, permissions, streaming, sub-agents, handoffs, guardrails, structured outputs.
PI extension for spawning isolated sub-agents with live TUI spying
An AI coding agent CLI with tools, skills, sub-agents, worktree isolation, and MCP support.
c11-native multi-agent orchestration package (successor to cmux-team). Spawn, monitor, and coordinate parallel Claude Code sub-agents on Stage 11 Agentics' c11 terminal multiplexer.
Agent Orchestrator MCP Server for tmux-based sub-agents
Core agent loop, configuration, context builder, metrics, and vault for Zeph
MPM orchestration platform: AI agent harness with multi-model routing, tool execution, and subprocess delegation.
A terminal multiplexer for teams of AI coding agents
Subagent management: spawning, grants, transcripts, and lifecycle hooks for Zeph
The autonomous, self-improving AI agent. Single Rust binary. Every channel. Install with: cargo install opencrabs
Derive Toolpath provenance documents from Gemini CLI conversation logs
Transparent zstd compression for Claude Code session bundles via FUSE (Linux)
Session-based AI development assistant with conversational codebase interaction, multimodal vision support, built-in MCP tools, and multi-provider AI integration
Session-scoped subagent registry for motosan-agent-loop. Spawn, message, and wait on long-lived child agents from a parent agent's tool calls.
A minimal Rust crate that gives any application agentic capabilities.
AWS integrations for the Rust deep agents SDK.
Core traits, data models, and prompt primitives for building deep agents.
Ruby implementation of deepagents - a library for creating deep agents with planning capabilities, sub-agent spawning, and a mock file system
pikuri-subagents owns the sub-agent (delegation) feature top to bottom: the +Pikuri::SubAgent::SubAgentTool+ class (exposed to the LLM as the +agent+ tool), the +Persona+ record, the +Extension+ that wires it onto an agent, and the bundled +Pikuri::SubAgent::RESEARCHER+ persona (network-read only). Hosts that want sub-agents add this gem as a runtime dep and call +c.add_extension Pikuri::SubAgent::Extension.new(personas: [...])+ inside their +Agent.new+ block — same opt-in shape as +pikuri-skills+ / +pikuri-mcp+. Also ships +bin/pikuri-minions+ as a fan-out delegation demo.
A plugin for the Fluentd event collection agent that provides Google Cloud Pub/Sub support
Manage AI agent skills, sub-agents, and hooks across workspaces
A plugin for the Fluentd event collection agent that provides a coupling between a GuardSight SPOP and Google Cloud Pub/Sub
TurnKit provides a small Ruby runtime for AI agents with conversations, turns, tool calls, terminal tools, file-based skills, sub-agents, and optional Rails persistence.
pikuri-tasks gives a pikuri-core agent an in-memory task list it can use to plan and track multi-step work. A +Pikuri::Tasks::List+ holds the per-Agent state; four tools (+task_create+, +task_in_progress+, +task_completed+, +task_delete+) mutate it via content-as-identifier (no item IDs to hallucinate). +Pikuri::Tasks::Extension+ wires the list and tools onto an +Pikuri::Agent+ via +c.add_extension(...)+ inside the +Agent.new+ block. The list lives in process memory only — nothing is written to disk. Sub-agents do not inherit the parent's list (consistent with the "sub-agents do not inherit extensions" rule).
pikuri-core is the lean, audit-friendly foundation of the pikuri family: Pikuri::Agent (a thin wrapper around ruby_llm's chat loop) with its Configurator + Extension protocol, the strict Pikuri::Tool framework, a listener surface for rendering / budgets / sub-agents, and four bundled stateless tools (calculator, web search, web scrape, fetch). Extensions (skills, MCP, workspace, coding stack, named-agent personas) live in sibling gems so a privacy-conscious user can install just this core and audit a minimal dependency tree. For the convenience bundle that pulls in everything, see the +pikuri+ metagem.
pikuri-vectordb gives a pikuri-core agent a +vectordb_search+ tool over a local document corpus — agentic search, the agent decides when to retrieve. Ships a swappable backend (a pure-Ruby +Backend::InMemory+ for teaching, plus thin +Backend::Qdrant+ / +Backend::Chroma+ HTTP clients for persistence — Qdrant recommended), a chunker, an embedder wrapper over +RubyLLM.embed+, and an optional +Reranker::LlamaServer+ that speaks +/v1/rerank+ against a cross-encoder model. Text extraction goes through +Pikuri::FileType.read_as_text+ in pikuri-core, which handles plain text / Markdown / PDF; HTML extraction is a deferred follow-up. Hosts wire the feature via +c.add_extension Pikuri::VectorDb::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-skills+. The bundled +Pikuri::VectorDb::LIBRARIAN+ persona is the privilege-separated sub-agent counterpart for hosts that want recall to flow through a child rather than the parent's context. Three model endpoints in the full setup — chat (via ruby_llm), an embedder (via +RubyLLM.embed+), and an optional reranker (HTTP +/v1/rerank+). A single +llama-server+ in router mode serves all three by default, loading each cached GGUF on demand; see the gem's README for details.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.