OpenCode plugin providing research-oriented agents (ideator, critic, sweeper)
Unofficial alphaXiv-powered CLI and library for research agents
AI-powered security research agents for vulnerability hunting and exploit development
OpenRouter MCP server for research agents
Structured observation management for research agents
OpenRouter MCP server for research agents
Agent-native marketing playbook: 56 skills, 5 research agents, brand memory that compounds, plus a local Studio dashboard (beta). One install, then /cmo in Claude Code walks you through a 4-question setup wizard. CLI for the agent, Studio for the human.
Schema, runner, scoring engine, and agent adapters for eval-kit — the scoring cockpit for research agents.
Anthropic Sandbox Runtime (ASRT) - A general-purpose tool for wrapping security boundaries around arbitrary processes
Governance substrate for AI coding agents — adversarial PR review, drift-detected rules, immutable audit, and closed-loop outcome routing for Claude, Codex, Gemini, and OpenCode
SOTA NPM module for agentic processes using local or cloud LLMs.
Maps proxy protocols to `http.Agent` implementations
CLEO skill definitions - bundled with CLEO monorepo
Autoresearch adapter — collaborative autonomous ML research over the Decentralized Knowledge Graph
Install AI research engineering skills to your coding agents (Claude Code, OpenCode, Cursor, Gemini CLI, Hermes Agent, and more)
A kanban foundation for coding agents
the shared design system for react ui @ nous. components, hooks, utils, fonts, overlays, etc.
Tavily integration for LangChain.js
DeepSeek AI-powered CLI agent for code assistance and automation
Opinionated OpenCode agent harness — PRIME, plan, build, QA, skills, MCP wiring, hashline editing.
LangGraph
Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action
The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows.
The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows. This package contains the logic for building realtime voice agents on the server or in the browser.
SBO3L Phase 3.1: on-chain audit-chain anchoring — periodically publish audit-root digests to AnchorRegistry contracts on Ethereum / Optimism / Base / Polygon for tamper-evident verification.
SBO3L CLI binary: validate, decide, sign, audit, passport run/verify/explain, doctor.
SBO3L core: protocol types, request hashing, error model, signed receipts.
SBO3L execution: sponsor adapters (KeeperHub, Uniswap) wrapping the GuardedExecutor trait.
SBO3L identity: ENS-backed agent identity resolution (offline fixture + live RPC).
SBO3L MCP — stdio JSON-RPC server wrapping SBO3L primitives (validate_aprp, decide, run_guarded_execution, verify_capsule, audit_lookup, explain_denial).
SBO3L policy engine: YAML/JSON policy parsing + rule evaluation + persistent budget tracking.
SBO3L HTTP daemon: POST /v1/payment-requests pipeline (auth, idempotency, policy, budget, audit, signed receipt).
SBO3L storage: SQLite persistence + hash-chained audit log.
Shared DID parsing and validation logic for the L1fe ecosystem (Zer0 Runtime, Forge, Factory, CLI).
Composable agentic framework on top of atomr actors and atomr-infer.
Agent actor + per-turn pipeline + tool-call orchestration loop.
Claude Swarm enables you to run multiple Claude Code instances that communicate with each other via MCP (Model Context Protocol). Create AI development teams where each instance has specialized roles, tools, and directory contexts. Define your swarm topology in simple YAML and let Claude instances collaborate across codebases. Perfect for complex projects requiring specialized AI agents for frontend, backend, testing, DevOps, or research tasks.
A lightweight, dependency-free Ruby client for the Tavily API. The web access layer built for LLMs and AI agents. Wraps the search, extract, crawl, map, and research endpoints with typed response objects, automatic retries with backoff, streaming research, and granular error handling.
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.