AI-powered development framework with task management, 41 agents, 83 skills, and MCP tools for Cursor, Claude Code, Gemini, Codex & OpenCode. File-based memory that survives across sessions.

A lightweight framework for parallel development with multiple AI agents. Provides structured memory management, specialized agent roles, and workflow guidance to maximize development velocity. Runic enhances Large Language Models (LLMs) with Long-Term Memory (LTM) capabilities and structured knowledge retention.

a startup but not simple agent demo using google adk.

Real-time dashboard to launch and monitor multi-agent AI missions using CrewAI + Groq. Choose Swarm Research, Feasibility Sprints, or Conference Planning, watch agents collaborate live with streaming timeline, Mermaid graph, token counter, and history.

An autonomous multi-agent storytelling framework for Minecraft. Features an LLM-driven World Narrator and intelligent agent swarms capable of PvP, building, and survival using a hybrid Python (Reasoning) and Node.js (Execution) architecture.

A reference architecture demonstrating local-first LLM orchestration for SOC compliance workflows. Built on ~11GB VRAM edge hardware using Ollama, featuring a multi-agent coordination pattern with file-based handoffs, a two-lane integration model (human-initiated vs automated processing), and a HITL approval gate for resource-sensitive operations.

This project implements an innovative agent-based system for automated financial transaction classification and revenue recognition.

GPU-native agent-swarm orchestration for the NVIDIA AI stack — NeMo, NIM, Triton, DCGM, NGC, NIXL, OpenShell. Spawn GPU-pinned agent teams across DGX/HGX nodes with NVLink-aware scheduling, task DAGs, adaptive scheduling, and full observability.

15-agent orchestration skill for Claude Code CLI — 6 Opus leads, 7 Sonnet specialists, 2 utility agents with scope boundaries, position-locked cross-feed, and 4-wave execution for building, auditing, and shipping browser extensions

Autonomous marketing agency powered by Claude Code agent swarms — multi-agent pipeline for content, SEO, campaigns, and more

A self-learning, multi-agent AI for accelerating Alzheimer’s research. From data to insights—fully autonomous and open-source.

AI Agent Swarm with Autonomous Payments - Chainlink Convergence 2026 Hackathon

A LangGraph-powered multi-agent research system (MARS) that orchestrates five specialized AI agents (Planner, Researcher, Writer, Critic, Word) using Google Gemini to produce polished research reports in JSON and .docx formats, with a FastAPI interface, iterative refinement loops, and automatic model fallback for rate limits.

Self-hosted multi-agent AI coding orchestrator. Planner→Worker→Reconciler architecture on a single VPS. Inspired by Longshot (TreeHacks 2026).

An open-source framework for task-based agent swarms with dynamic parallelization, routing, and execution topology.

DeepTrace - Real-time observability layer for agentic AI systems. Intercept, trace, visualize, and secure every LLM inference and tool invocation across your agent swarm.