The Architect — A Claude Code meta-agent that designs complete software blueprints. Describe what you want to build, get a self-contained .md file that Claude Code can build autonomously.
Open Agent OS for Claude Code, Codex, and Cursor: meta-agent builder, A2A Hub routing, local ontology, memory and security gates.
Convoke extends BMAD Method AI agents with two types of installable modules: Teams bring new agents for a domain, Skills add new capabilities to existing agents. Install them independently or combine them.
The purpose of the "Meta Agent with More Agents" project is to dynamically solve complex queries by breaking them down into smaller tasks and assigning each to specialized AI agents. The Meta Agent coordinates the process, leveraging a ReAct Agent for tool-based tasks and a Chain of Thought Agent for reasoning-based tasks. The system's flexibility.
Save context for what matters. The last agent you'll ever need.
Open-source meta-agent orchestrator for VS Code: one sidebar for Copilot, Claude, Cursor, Devin, and Kiro.
An open framework for building self-improving AI agent teams. Includes a meta-agent architecture with independent auditing, git-backed evolution, and structured feedback loops. Ships with a complete marketing team, a reusable team-builder skill, and a portable prompt that works with any LLM.
An Agent that propagates improvements into other agents — mines session history + audits freshness, then PRs fixes.
Meta-agent system for Claude Code that creates specialized AI agents through deep domain research and 7-lens quality review
Think in Higher Dimension
Co-processor CLI for delegating deterministic coding tasks to Pi agent. Safety-first design with YOLO firewall, stall detection, parallel burst mode, and YAML pipelines. TypeScript.
Hierarchical agent orchestration system with JSON-RPC 2.0 unified architecture
A self-optimizing ML experiment advisor: meta-agent that gets better at advising ML hyperparameter tuning by learning from its own failures. 80% → 100% across 21 iterations. $26 total. Part 2 of the autoresearch series.
An AI agent that automatically improves its own prompt based on output quality scores — runs a task, evaluates the result, rewrites the prompt, and tries again until it hits the target score.
A meta-agent that generates, tests, and iterates on AI agent harnesses from plain-English descriptions. No Docker, no benchmarks required.
Meta-agent for Claude Code that convenes 3-5 specialist subagents on cross-functional decisions, parallel-spawns them with identical briefs, and synthesizes consensus + dissent into structured recommendations.
Autonomous prediction market trading agent for Polymarket — discovers markets, estimates probabilities with web research, sizes via Kelly criterion, and evolves its own strategy from experience. Powered by Claude Code.
Add a description, image, and links to the meta-agent topic page so that developers can more easily learn about it.
To associate your repository with the meta-agent topic, visit your repo's landing page and select "manage topics."