Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground
This repository also configures its own agents. See what Agentflow tells them →
Skill Claude CodeCodex
Perform thorough code reviews, identify bugs, suggest improvements, and explain code quality issues. Use when the user shares code and asks for a review, bug hunt, or quality feedback.
Skill Claude CodeCodex
Help users analyse data, interpret statistics, explain trends, and answer data-related questions. Use when the user shares numbers or datasets, or asks about averages, trends, or statistical results.
Skill Claude CodeCodex
Remove AI writing patterns and make text sound natural and human-written. Use when the user asks to humanize text, make it sound less AI-generated, or rewrite it to read naturally.
Skill Claude CodeCodex
Help users write, edit, proofread, and improve any type of written content. Use when the user asks to draft, rewrite, proofread, or polish emails, messages, or documents.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: