Architecture overview of Axum Labs Studio — an autonomous AI web agency: agent swarm (intake to deploy), Rust MCP gateway behind a Universal Commerce Protocol, and four-tier shared memory (Postgres/Redis/Mem0/Neo4j). Public overview; source proprietary.
🏛️ An AI agent swarm that argues like the Roman Senate — five conflicting senators deliberate your decision in parallel, a cross-family envoy attacks their consensus, and the Legions are sent to do the work /senate for Claude Code. SPQR.
Luna Pipes: a concatenative AI shell language. 358 verbs composed via >>. AI honesty auditor (/ll-no-bluf), agent scaffolder, 21 stack-aware doctors, evidence-weighted voting swarm. Claude Code plugin. MIT. Runs locally.
Self-hosted multi-agent AI coding orchestrator. Planner→Worker→Reconciler architecture on a single VPS. Inspired by Longshot (TreeHacks 2026).
Bulk YouTube transcripts → AI agent swarm. Ask any YouTube channel a question: one AI agent reads every video transcript in parallel and answers with timestamped citations. Rust CLI + MCP server for Claude. Powered by the BulkTranscripts API.
Research-team-swarm plugin for Claude Code. Spec-driven workflows: gap-finding, novel hypothesis generation with falsification criteria, adversarial red-team critique. Bundles HF/arxiv/web/GitHub MCP tools and integrates deeply with the superpowers skill library.
ClawTeam: Agent Swarm Intelligence (One Command → Full Automation)
Deterministic, BFT-Hardened MCP Memory Server for Agent Swarms
Give a swarm of LLM agents a message board and a job that needs coordination, then watch what they do. Parallel lockstep runs on any OpenRouter model, exact replay, and a live observer UI.
Agent swarm across Claude Code and Codex: every model answers, agents argue on a shared board, an outside judge writes the verdict. Bash + jq.
Run, observe and steer many Claude Code & AGY sessions as one fleet, from a CLI and a local dashboard.
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.
Multi-agent orchestration SDK by Parallax Ventures AI — spawn, coordinate, and manage AI agent swarms across any provider
Pinchy: a desktop AI assistant and agent harness built on Claude Code. A blue lobster that lives on your screen and does real work — chat, files, computer use, scheduled agents, multi-agent swarms, Code and Work jobs, a phone app and an away server. Windows, macOS, Linux, Android. Free; runs on your own Claude plan.
Contract-governed AI orchestration layer for LawFirm OS, coordinating models, tools, approvals, run ledgers, and evidence packets without owning canonical semantic truth.
One repo for top agentic-AI skills + Python agent engineering, with a working stdlib-only swarm orchestrator and live bounty-scout pipeline
A self-learning, multi-agent AI for accelerating Alzheimer’s research. From data to insights—fully autonomous and open-source.
Multi-Agent Swarm Orchestration Platform - build, deploy, and monitor AI agent swarms at scale. Provider-agnostic (OpenAI/Anthropic/DeepSeek/Google), 5 swarm topologies, streaming handoffs, full observability.
Agent Emergency Protocol Incident Codes: a vendor-neutral runtime incident-code language for autonomous AI agents. Created by Mitthan Meena.
OmniShell uses an AI agent swarm to plan, secure, and execute complex cross-platform workflows directly on your host machine.
To associate your repository with the agent-swarm topic, visit your repo's landing page and select "manage topics."