Загрузка видео...

Не удалось загрузить видео

На главную

Deploy any ML model as an MCP server! LitServe: The easiest way to deploy agents, RAG, and any ML model. Now supports MCP. 100% open-source.

akshay_pachaar's profile picture

Akshay 🚀

284,218 subscribers

60,086 просмотров • 1 год назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

Link to LitServe GitHub repo: (don't forget to star 🌟)

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

If you found it insightful, reshare with your network. Find me → @akshay_pachaar ✔️ For more insights and tutorials on LLMs, AI Agents, and Machine Learning!

Фото профиля Avi Chawla
Avi Chawla1 год назад

This is a really really cool idea. Love it

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

Glad you liked it Avi! :)

Фото профиля Shawn Chauhan
Shawn Chauhan1 год назад

Open-source makes it way more accessible for devs

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

Absolutely 💯

Фото профиля Truong Hoang Dung
Truong Hoang Dung1 год назад

what a pity, it uses Python.

Фото профиля Rusty Ray
Rusty Ray1 год назад

Open-source support makes deployment far more flexible.

Фото профиля Riley Debuggs
Riley Debuggs1 год назад

Open-source MCP support widens LitServe’s applicability. Interested to see benchmarks versus alternative deployment frameworks.

Фото профиля Code Weaver
Code Weaver1 год назад

Curious—what performance impact comes with deploying via MCP compared to alternatives?

Похожие видео

Agents & MCP are great... but how can you DEPLOY an agent with MCP tools? Here's the fastest way I've found to build and deploy with the OpenAI Agents SDK in <3 minutes.
3:46

Agents & MCP are great... but how can you DEPLOY an agent with MCP tools? Here's the fastest way I've found to build and deploy with the OpenAI Agents SDK in <3 minutes.

matt palmer

64,690 просмотров • 1 год назад

I made a thing, and it's 100% open-source. Introducing ModelFetch: 🥳 Deploy MCP servers anywhere TypeScript or JavaScript runs. 🚀 1️⃣ Write your MCP server once using the official MCP TypeScript SDK. 2️⃣ Deploy it anywhere using the ModelFetch runtime packages. Link below 👇
1:28

I made a thing, and it's 100% open-source. Introducing ModelFetch: 🥳 Deploy MCP servers anywhere TypeScript or JavaScript runs. 🚀 1️⃣ Write your MCP server once using the official MCP TypeScript SDK. 2️⃣ Deploy it anywhere using the ModelFetch runtime packages. Link below 👇

Minh-Phuc Tran

12,751 просмотров • 1 год назад

MCP meets Ollama! In this video you'll learn how build a 100% local MCP client that you can connect to any MCP server. 100% open-source code, step-by-step guide:
14:53

MCP meets Ollama! In this video you'll learn how build a 100% local MCP client that you can connect to any MCP server. 100% open-source code, step-by-step guide:

Akshay 🚀

92,848 просмотров • 1 год назад

Introducing Asterisk MCP - An MCP server that fixes security vulnerabilities while you vibe code. Supports Cursor, Windsurf, Cline, Claude, and any IDE that supports the model context protocol. It can perform codebase-wide scans, analyze snippets in your conversation history, and verify changes/fixes for security issues. mcp dot asterisk dot so
0:57

Introducing Asterisk MCP - An MCP server that fixes security vulnerabilities while you vibe code. Supports Cursor, Windsurf, Cline, Claude, and any IDE that supports the model context protocol. It can perform codebase-wide scans, analyze snippets in your conversation history, and verify changes/fixes for security issues. mcp dot asterisk dot so

mufeed vh

14,353 просмотров • 1 год назад

AI Engineers gonna love this MCP server! KitOps MCP serve eliminates the "it works on my machine" problem by packaging AI/ML projects (models, datasets, code, config) into a shareable, deployable ModelKit. Sharing projects is as easy as sharing zip files! 100% open-source.
11:13

AI Engineers gonna love this MCP server! KitOps MCP serve eliminates the "it works on my machine" problem by packaging AI/ML projects (models, datasets, code, config) into a shareable, deployable ModelKit. Sharing projects is as easy as sharing zip files! 100% open-source.

Akshay 🚀

87,067 просмотров • 1 год назад

INCREDIBLE!! An MCP server to browse the web like humans! Bright Data MCP server provides 30+ powerful tools that allow AI agents to access, search, crawl, and interact with the web without getting blocked. 100% open-source, works at scale!
0:37

INCREDIBLE!! An MCP server to browse the web like humans! Bright Data MCP server provides 30+ powerful tools that allow AI agents to access, search, crawl, and interact with the web without getting blocked. 100% open-source, works at scale!

Akshay 🚀

90,404 просмотров • 1 год назад

Metorial (Metorial (YC F25)) makes it easy for AI agents to use tools and data. Deploy 600+ MCP integrations in three clicks and connect them to agents in a single function call. Open-source and the only serverless MCP platform built for multi-tenant systems.
1:58

Metorial (Metorial (YC F25)) makes it easy for AI agents to use tools and data. Deploy 600+ MCP integrations in three clicks and connect them to agents in a single function call. Open-source and the only serverless MCP platform built for multi-tenant systems.

Y Combinator

15,381 просмотров • 11 месяцев назад

The only MCP server you'll ever need! I just built an MCP server that connects to 200+ data sources and runs locally on my machine. 100% open source.
9:27

The only MCP server you'll ever need! I just built an MCP server that connects to 200+ data sources and runs locally on my machine. 100% open source.

Akshay 🚀

64,167 просмотров • 1 год назад

An MCP server to create Grant Sanderson animations (open-source):
0:29

An MCP server to create Grant Sanderson animations (open-source):

Daily Dose of Data Science

12,376 просмотров • 11 месяцев назад

Dedalus Labs (Dedalus Labs) is building the infrastructure layer for agentic AI—the simplest way to build and deploy complex agents across any model and any tool. Congrats on the launch, Cathy Di & Windsor Nguyễn!
1:47

Dedalus Labs (Dedalus Labs) is building the infrastructure layer for agentic AI—the simplest way to build and deploy complex agents across any model and any tool. Congrats on the launch, Cathy Di & Windsor Nguyễn!

Y Combinator

138,607 просмотров • 11 месяцев назад

Introducing Wingman: a model-agnostic, MCP-native coding assistant. You can now get the Claude Code experience with ANY model for FREE. - MIT-licensed - MCP-native - Model-agnostic > pip install wingman-cli
2:00

Introducing Wingman: a model-agnostic, MCP-native coding assistant. You can now get the Claude Code experience with ANY model for FREE. - MIT-licensed - MCP-native - Model-agnostic > pip install wingman-cli

Dedalus Labs

39,454 просмотров • 8 месяцев назад

Build a 100% local, private, and secure MCP client. You can connect it to any MCP server. Step-by-step guide:
14:53

Build a 100% local, private, and secure MCP client. You can connect it to any MCP server. Step-by-step guide:

Akshay 🚀

15,560 просмотров • 9 месяцев назад

5️⃣ Jupyter MCP server An MCP server to control Jupyter notebooks from Claude, you can: - Create code cells - Execute code cells - Create markdown cells 100% open-source and free to use! Check this👇
0:36

5️⃣ Jupyter MCP server An MCP server to control Jupyter notebooks from Claude, you can: - Create code cells - Execute code cells - Create markdown cells 100% open-source and free to use! Check this👇

Akshay 🚀

16,578 просмотров • 1 год назад

🆕Fin now supports MCP as a client, and Intercom supports MCP as a server. This little example shows Fin connecting to Stripe's MCP server letting Fin list products, prices, and even create payment links. This lets Fin resolve customer questions better, faster, and cheaper
4:07

🆕Fin now supports MCP as a client, and Intercom supports MCP as a server. This little example shows Fin connecting to Stripe's MCP server letting Fin list products, prices, and even create payment links. This lets Fin resolve customer questions better, faster, and cheaper

Des Traynor

23,935 просмотров • 1 год назад