AgentToolDrop

33 of 61

RocketRide

Builds AI pipelines as portable JSON in VS Code and runs them on a C++ engine with Python nodes

  • score 43
  • 17.7k stars
  • 71 stars/day since creation
  • pushed
  • vscode-v1.4.0 on
  • MIT

Pull and create the engine container with Docker

docker pull ghcr.io/rocketride-org/rocketride-engine:latest
docker create --name rocketride-engine -p 5565:5565 ghcr.io/rocketride-org/rocketride-engine:latest

Copied from the project's docs at github.com/rocketride-org/rocketride-server

Why you'd want it

RocketRide is a data pipeline builder and runtime for AI and ML workloads. Pipelines are saved as portable .pipe JSON files, built on a visual canvas in VS Code and run by a multithreaded C++ runtime. The README reports 100+ nodes covering LLM providers, vector databases, OCR, NER and PII anonymization, and says all nodes are Python-extensible. An agent node is an LLM allowed to call other nodes in a loop, and the Python and TypeScript SDKs call a pipeline from your own app, with an MCP SDK that exposes pipelines as tools for AI assistants.

Best for

  • Visual LLM and RAG pipelines in VS Code
  • Document processing on local models
  • Calling pipelines from Python or TypeScript apps

Use it when

You want AI workflows kept as diffable .pipe files that run on your own machine or in Docker, and that your Python or TypeScript code can call.

Skip it if

You only need a lightweight agent library; RocketRide is an engine with a VS Code extension and a node catalog. Recent releases are tagged prerelease. LLM and tool nodes need API keys, and agent nodes can call tool nodes such as GitHub and Slack, so check which credentials a pipeline holds before running it. The README says an SDK client run outside the folder holding the extension's .env falls back to RocketRide Cloud, so confirm where a client points before sending private data.

Editor's note

The README Quick Start installs the RocketRide extension from the IDE marketplace and picks a Local or On-Premises server; the Docker block is the shell install. SDKs: pip install rocketride and npm install rocketride. A hosted RocketRide Cloud is also offered.

Related tools

Same category or shared tags.

  1. Rank 27

    Mastra

    Framework

    Builds TypeScript agents and graph-based workflows with memory, RAG, evals and model routing

    • score 45
    • 28.9k stars
    • 18.2 stars/day last 4 days
    • pushed
    • @mastra/core@1.78.0 on
    • Apache-2.0

    Create a project with npm

    npm create mastra@latest
    Use it when, skip it if, stats for Mastra

    Why you'd want it

    Mastra is a TypeScript framework for agents and workflows that plugs into React, Next.js and Node apps or runs as a standalone server. It connects to 40+ model providers through one interface, has a graph-based workflow engine with .then(), .branch() and .parallel(), and can suspend an agent or workflow for human input and resume from stored state. It also covers conversation history, RAG, observational memory, MCP server authoring, evals and observability.

    Best for

    • TypeScript and Next.js teams
    • Agents with human approval steps
    • Apps that need memory and RAG in one stack

    Use it when

    You want agents, workflows, memory and evals in one TypeScript framework instead of assembling separate libraries.

    Skip it if

    You work in Python. Features in ee/ directories (for example auth) need a Mastra enterprise license for production use.

    Stats

    New and rising score
    45 of 100
    Stars per day, last 4 days
    18.2
    Release
    @mastra/core@1.78.0,
    License
    Apache-2.0
    Pricing
    Open source
    Forks
    3,010
    Open issues
    597
    GitHub checked

    Full stat block for Mastra

  2. Claude Agent SDK

    Framework Standard

    Embeds Claude Code's agent loop, built-in tools and context management in Python or TypeScript apps

    • 8.3k stars
    • 3.8 stars/day last 4 days
    • pushed
    • v0.2.168 on
    • Python repo MIT

    Install with pip

    pip install claude-agent-sdk
    Use it when, skip it if, stats for Claude Agent SDK

    Why you'd want it

    The Agent SDK is a library that runs the Claude Code binary, so your agent gets the same tools (read, write and edit files, run commands, search the web), agent loop and context management that power Claude Code. You can add custom tools as in-process MCP servers, run hooks at points in the agent lifecycle, spawn subagents, control which tools run automatically through permissions, and resume or fork sessions. It is available for Python (claude-agent-sdk) and TypeScript (@anthropic-ai/claude-agent-sdk).

    Best for

    • Agents that edit files and run commands
    • Teams already using Claude Code
    • Embedding a coding agent in your own app

    Use it when

    You want Claude Code's tool set and permission model inside a process you operate, instead of writing the tool loop yourself.

    Skip it if

    You want to use non-Claude models. It needs an Anthropic API key or Claude through Amazon Bedrock, Google Cloud or Microsoft Foundry, and third-party products may not offer claude.ai login unless approved by Anthropic.

    Stats

    Stars per day, last 4 days
    3.8
    Release
    v0.2.168,
    License
    Python repo MIT
    Pricing
    Paid
    Forks
    1,361
    Open issues
    569
    GitHub checked

    Full stat block for Claude Agent SDK

  3. Strands Agents

    Framework Standard

    Runs a model-driven agent loop in your own process, in Python or TypeScript, with any model provider

    • 8.9k stars
    • 10.4 stars/day last 4 days
    • pushed
    • python/v1.61.1 on
    • Apache-2.0

    Install with pip

    pip install strands-agents strands-agents-tools
    Use it when, skip it if, stats for Strands Agents

    Why you'd want it

    Strands is an SDK for cases where you would otherwise write your own agent loop: it runs in your process with no hosted control plane and covers turn limits, token budgets, cancellation, tools, structured output, MCP, multi-agent patterns, memory, sessions, streaming, guardrails, tracing and evals. It has first-class support for Amazon Bedrock, Anthropic, OpenAI and Gemini plus other and custom providers, and hooks let you intercept any step of the loop. Strands harness (create_harness() in Python, createHarness() in TypeScript) gives a fully assembled agent with preset defaults.

    Best for

    • Replacing a hand-rolled agent loop
    • Amazon Bedrock users
    • Mixed Python and TypeScript stacks

    Use it when

    You want to own the agent loop in your own process, with lifecycle limits, hooks and tracing built in and the option to swap model providers.

    Skip it if

    You want a hosted agent platform rather than a library. The Python SDK needs Python 3.10+ and the TypeScript SDK needs Node.js 22+.

    Stats

    Stars per day, last 4 days
    10.4
    Release
    python/v1.61.1,
    License
    Apache-2.0
    Pricing
    Open source
    Forks
    1,399
    Open issues
    1,028
    GitHub checked

    Full stat block for Strands Agents

For agents

The same entry, as files an agent can read without scraping this page. 

# read one entry
curl -s https://agenttooldrop.com/tools/rocketride.md

# list the MCP servers in the catalog
curl -s https://agenttooldrop.com/tools.json \
  | jq -r '.tools[] | select(.category=="mcp-server") | .slug'