Log inSubmit server
Agentic Flow logo

Agentic Flow

by @sparkleideas

Routes coding tasks across specialized agents, self-learning hooks, background workers, and 213 MCP tools.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Agentic Flow

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "sparkleideas-agentic-flow": {
      "command": "npx",
      "args": [
        "-y",
        "agentic-flow"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command didn't complete successfully in our automated test.

npx -y agentic-flow

author of the relevant native addon; alternatives are available. npm warn deprecated @opentelemetry/sdk-trace-node@2.7.1: Use @opentelemetry/sdk-trace package npm warn deprecated node-domexception@1.0.0: Use your platform's native DOMException instead npm warn deprecated @opentelemetry/propagator-jaeger@2.7.1: Package no longer supported. See https://github.com/open-telemetry/opentelemetry-js/pull/7077 npm warn deprecated @opentelemetry/sdk-trace-base@2.7.1: Use @opentelemetry/sdk-trace package

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1d ago.

Overview

@sparkleideas/agentic-flow provides task routing, agent orchestration, adaptive learning hooks, background workers, and swarm-coordination tools for coding workflows. It initializes a project workspace, bootstraps context from the codebase, and can run as an MCP server for Claude Code. Use it when development tasks benefit from specialized agents, learned routing, or coordinated multi-agent execution. A TypeScript API is also available for routing tasks programmatically.

Use cases

  • Route implementation tasks to specialized coding agents
  • Pretrain hooks against an existing codebase
  • Dispatch background workers for learning, optimization, or auditing
  • Coordinate multi-agent coding and review workflows

Key features

  • Task routing with confidence reporting
  • Self-learning hooks and adaptive memory
  • 213 MCP tools for swarm coordination
  • 66 specialized agent roles
  • Keyword-triggered background workers
  • TypeScript API for programmatic routing

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

Supply-chain signal

1 high-severity advisory on record for this package. Most advisories affect transitive dependencies and may not be exploitable in this server's actual usage — this is a directional signal, not a security audit.

Critical 0High 1Medium 0Low 0

Scanned 2d ago via OSV.dev · agentic-flow (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars830Stargazers on the source repository.
npm downloads415Package downloads in the last 30 days.
Last commit2d agoMost recent push to the default branch.
Install checkInconclusiveInstall command did not finish in our automated test.

How Agentic Flow works

What @sparkleideas/agentic-flow does

@sparkleideas/agentic-flow organizes coding work across specialized agents and exposes the orchestration layer through MCP. Its feature set includes task routing, self-learning hooks, background workers, adaptive memory, and swarm coordination. The project describes 66 specialized agents and 213 MCP tools, covering roles such as coding, testing, reviewing, planning, research, coordination, and performance analysis.

The platform also includes ReasoningBank-based learning, GNN-enhanced context, attention mechanisms, and SONA for adaptive learning. These capabilities are intended to help the system learn from prior task outcomes, select agents, and coordinate multiple agents during execution.

How it works

A typical workflow begins by initializing the project:

Terminal
npx agentic-flow init
npx agentic-flow hooks pretrain
claude

Initialization prepares the workspace, while hooks pretrain bootstraps intelligence from the codebase. Once the hooks are active, tasks can be routed to an appropriate agent with a command such as:

Terminal
npx agentic-flow hooks route "implement user authentication"

The routing result identifies an agent and reports a confidence value. Learning metrics are available through hooks metrics. Keyword-triggered background workers can be dispatched with commands such as workers dispatch "ultralearn how caching works".

For MCP use with Claude Code, start the server with:

Terminal
npx agentic-flow mcp start

Applications can also import AgenticFlow from the package, initialize it, and call route() from TypeScript.

Setup and configuration

The documented quick-start path requires Node.js 18 or newer and the agentic-flow package available through npx. Run the initialization command from the project you want to analyze, then pretrain the hooks against that codebase. The server can be started separately with the MCP command.

These profiles represent different trade-offs among latency, throughput, learning quality, and memory usage. The Balanced profile is described as the default.

Tools and capabilities

  • Route tasks to specialized agents and inspect routing confidence.
  • Provide self-learning hooks that record and reuse task patterns.
  • Dispatch background workers for operations such as ultralearning, optimization, and auditing.
  • Coordinate autonomous multi-agent swarms through MCP tools.
  • Use ReasoningBank memory and cross-agent pattern sharing.
  • Select among attention and routing strategies, including flash, multi-head, linear, hyperbolic, and mixture-of-experts approaches.
  • Expose 213 MCP tools for orchestration and swarm coordination.
  • Integrate programmatically through the AgenticFlow TypeScript API.

The listed agent roles include coder, reviewer, tester, planner, researcher, hierarchical coordinator, mesh coordinator, adaptive coordinator, issue tracker, release manager, and performance analyzer.

Limitations and notes

The quick-start workflow is centered on Claude Code. SONA and AgentDB capabilities are presented as part of the v2 platform, with some components described using alpha release labels. Performance figures in the project materials are benchmark claims tied to particular runtimes, profiles, or workloads rather than general guarantees.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Agentic Flow

@sparkleideas/agentic-flow is an MCP server that connects Claude Code and initialized project workspaces to agent orchestration features, including task routing, background-worker dispatch, self-learning hooks, and swarm-coordination tools. It exposes 213 MCP tools and supports programmatic task routing through the AgenticFlow TypeScript API.

Run it through npx rather than a separate installation step: initialize the project with `npx agentic-flow init`, bootstrap context with `npx agentic-flow hooks pretrain`, and start MCP with `npx agentic-flow mcp start`. The documented runtime requirement is Node.js 18 or newer.

Run `npx agentic-flow hooks route "your task"` to route a task through the hooks system. The result identifies the selected agent and includes a confidence value. TypeScript applications can instead initialize `AgenticFlow` and call its `route()` method.

Use `npx agentic-flow workers dispatch "your instruction"` to dispatch a background worker. The documented examples use keyword-driven instructions such as ultralearning a topic, optimizing a workflow, or auditing a project.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAgentic Flow AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/sparkleideas-agentic-flow?style=directory)](https://allmcps.com/mcp/sparkleideas-agentic-flow)
HTML Embed
<a href="https://allmcps.com/mcp/sparkleideas-agentic-flow"><img src="https://allmcps.com/api/badge/sparkleideas-agentic-flow?style=directory" alt="Agentic Flow on AllMCPs" /></a>