Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.
-
Updated
Mar 7, 2026 - TypeScript
Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.
The World's First Agentic IDE. Visual dashboard: live sessions, task management, code editor, terminal. Epic Swarm parallel workflows. Auto-proceed rules. Automation patterns. Beads + Agent Mail + 50 bash tools. Supervise 20+ agents from one UI.
Open-source, self-improving autonomous agent swarm🐇
TUI for easily running parallel coding agents
List of agent orchestrators
Experimental agent swarm extension for Pi. Inspired by Claude agent teams.
Multi-agent orchestration for OllamaJS. Includes TTS synthesis and speech recognition for simplified testing. Connected to telegram bot which support multiple chat 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 visualization dashboard for Claude Code agents, teams & swarms — isometric pixel world + monitoring dashboard
A specialized CLI tool for atomically claiming "ready" issues from Beads, designed specifically for multi-agent local swarms to prevent race conditions and duplicate work.
VegaMCP v7.0 - Full Spectrum Testing Edition. AI Agent Swarm Platform with 65+ tools, 15 unified capability clusters, A2A protocol, zero-trust identity, MCP gateway, async tasks, agent graphs, multimodal embeddings.
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 virtual team in your terminal: multiple AI agents discuss and converge, so you don't have to iterate alone.
This project implements an innovative agent-based system for automated financial transaction classification and revenue recognition.
🐝 Autonomous AI Agent Swarm — 11 GitHub Copilot agents that research, develop, audit, and deploy improvements to production apps 24/7. Self-healing, version-verified, event-driven pipeline. 780+ ideas/day.
Pre-built AI agent personas for Claude Code. 15 production agents, 6 fun modes, 3 swarm templates. Drop them in, they work.
Multi-agent orchestration for OllamaJS. Includes TTS synthesis and speech recognition for simplified testing and interaction.
Real-time blockchain fraud detection using autonomous multi-agent AI swarms. Detect fraud in <2s with 150x faster vector search (HNSW), 84.8% accuracy, and 73% cost reduction. Features ERC-1155 trust scores, MCP integration, and reflexion learning.
Multi-agent harness for AI coding tools. Crash-safe state, parallel execution, one CLI.
Add a description, image, and links to the agent-swarm topic page so that developers can more easily learn about it.
To associate your repository with the agent-swarm topic, visit your repo's landing page and select "manage topics."