agentic-flow
Overview
Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built with Claude Agent SDK, neural networks, and GitHub integration.
Best For
agentic-flow is a production-ready AI agent orchestration platform featuring 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms, integrated with Claude Agent SDK.
Decision Snapshot
Install
available
Usage
available
Docs
8 links
- • GitHub stars: 611
- • Forks: 137
- • Source provenance count: 1
- • Active signal: Updated this week from lifecycle signals.
- • Last seen: 4/15/2026
- • Published: 3/26/2026
Installation / Setup
# 1. Initialize your project && npx agentic-flow init && # 2. Bootstrap intelligence from your codebase && npx agentic-flow hooks pretrain
Usage
# 1. Initialize your project && npx agentic-flow init && # 2. Bootstrap intelligence from your codebase && npx agentic-flow hooks pretrain
Features
- • **🧠 ReasoningBank Learning Memory**: All 66 agents learn from every task execution
- • Store successful patterns with reward scores
- • Learn from failures to avoid repeating mistakes
- • Cross-agent knowledge sharing
- • Continuous improvement over time (+10% accuracy improvement per 10 iterations)
- • **🎯 Self-Learning Agents**: Every agent improves autonomously
- • Pre-task: Search for similar past solutions
- • During: Use GNN-enhanced context (+12.4% better accuracy)
Use Cases
- • Common usage themes: ai, ai-agents, ai-orchestration, agentic.
Compatibility Signals
- • Claude Desktop: mentions (Mentioned in approved metadata/docs evidence.)
- • GitHub: mentions (Mentioned in approved metadata/docs evidence.)
Prompt Examples
example
• # 1. Initialize your project && npx agentic-flow init && # 2. Bootstrap intelligence from your codebase && npx agentic-flow hooks pretrain
Notes / Requirements
- • Primary language: TypeScript/JavaScript
- • License: MIT
- • Documentation coverage: high
- • Parser coverage score: 1.00
- • Source feeds: npm Registry Search API
- • Topic cluster: coding
Official Links
Source Information
You can verify all information on this page against the source repository above.
Related MCP Tools
pilot-shell
A professional development environment for Claude Code with enforced tests, preserved context, and automated quality.
cursor-talk-to-figma-mcp
MCP integration between AI agents (Cursor, Claude Code) and Figma, enabling programmatic reading and modification of designs.
mcp-agent
mcp-agent is a Python tool for building effective agents using Model Context Protocol (MCP) and simple workflow patterns.
Unity-MCP
unity-mcp bridges AI assistants (e.g., Claude, Cursor) with Unity Editor via a local MCP Client, enabling LLMs to manage assets, control scenes, edit scripts, and automate tasks.
What To Do Next
Continue from this tool into a workflow and a learn guide to shorten implementation time.