Loading video...

Video Failed to Load

Go Home

opencode2 has tool search and codemode built in this means it can handle infinite mcps, custom tools, apis, etc and it's the simplest implementation we've seen

thdxr's profile picture

dax

155,775 subscribers

254,189 views • 1 day ago •via X (Twitter)

Science & TechnologyEducationHealth & Wellness
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I just built a Gmail MCP and connected it to Harmony and it's blowing my mind 🤯 It has 9 email tools: - send - draft - read - search - delete - modify labels - list labels - create labels - get thread Just tell it what to do and it can. p.s. tool calls will be 2x faster soon
1:16

I just built a Gmail MCP and connected it to Harmony and it's blowing my mind 🤯 It has 9 email tools: - send - draft - read - search - delete - modify labels - list labels - create labels - get thread Just tell it what to do and it can. p.s. tool calls will be 2x faster soon

Nathan Covey

25,176 views • 1 year ago

We’re excited to share the beta release of our tool use API! Now developers can easily equip any LLM with hosted open-source tools for web search, web crawling, and maps data (+ more coming soon). Under the hood, it's powered by MCP — but that's just an implementation detail ↓
3:19

We’re excited to share the beta release of our tool use API! Now developers can easily equip any LLM with hosted open-source tools for web search, web crawling, and maps data (+ more coming soon). Under the hood, it's powered by MCP — but that's just an implementation detail ↓

OpenTools

125,965 views • 1 year ago

I built an MCP server for WhatsApp It connects to your personal WhatsApp account You can search your messages, contacts and send messages It's fully open-source, self-hosted, and doesn't rely on third-party APIs
0:37

I built an MCP server for WhatsApp It connects to your personal WhatsApp account You can search your messages, contacts and send messages It's fully open-source, self-hosted, and doesn't rely on third-party APIs

Luke Harries

801,055 views • 1 year ago

Creating custom APIs for any website just got 100× easier. Suno AI has no public API for song generation - so I showed this agent the workflow once. It reverse-engineered the requests and built a reusable API I can call infinitely all in less than 5 mins. To which sites do you want to have APIs?
1:12

Creating custom APIs for any website just got 100× easier. Suno AI has no public API for song generation - so I showed this agent the workflow once. It reverse-engineered the requests and built a reusable API I can call infinitely all in less than 5 mins. To which sites do you want to have APIs?

Magnus Müller

106,079 views • 8 months ago

Introducing BuildShip v2 We've reimagined how production-grade AI workflow and backend can be built - visually Ideate, build and ship → APIs, scheduled jobs, automate any complex task on an infinite canvas. Best of No-Code x Code x AI
1:27

Introducing BuildShip v2 We've reimagined how production-grade AI workflow and backend can be built - visually Ideate, build and ship → APIs, scheduled jobs, automate any complex task on an infinite canvas. Best of No-Code x Code x AI

BuildShip

15,065 views • 1 year ago

We built an app called Hatch It enables Karpathy's entire LLM Knowledge Base workflow out of the box, in 2 or 3 clicks, in a single interface. No need to stitch together Obsidian + plugins + markdown files + custom tools + etc. Hatch is an AI workspace where files, docs, and chats all live together. Not only can the chats READ files and docs, but they can WRITE and ORGANIZE them as well. This means you can set up an LLM Wiki in literally 3 steps, as I show in this video.
11:58

We built an app called Hatch It enables Karpathy's entire LLM Knowledge Base workflow out of the box, in 2 or 3 clicks, in a single interface. No need to stitch together Obsidian + plugins + markdown files + custom tools + etc. Hatch is an AI workspace where files, docs, and chats all live together. Not only can the chats READ files and docs, but they can WRITE and ORGANIZE them as well. This means you can set up an LLM Wiki in literally 3 steps, as I show in this video.

Channing Allen

180,804 views • 4 months ago

Google just dropped Gemini CLI! This AI terminal can: - Handle codebases beyond 1M token limits - Generate apps from PDFs or sketches - Connect to MCP servers and tools - Utilize built-in Google Search 100% open-source (1k free requests/day)
0:28

Google just dropped Gemini CLI! This AI terminal can: - Handle codebases beyond 1M token limits - Generate apps from PDFs or sketches - Connect to MCP servers and tools - Utilize built-in Google Search 100% open-source (1k free requests/day)

Akshay 🚀

26,485 views • 1 year ago

IBM just released Granite-4.0 Nano, their smallest LLMs ever (300M & 1B)! 😍 The models demonstrate remarkable instruction following and tool calling capabilities, and can even run locally in-browser! This means they can interact with websites and call browser APIs for you! 🤯
1:04

IBM just released Granite-4.0 Nano, their smallest LLMs ever (300M & 1B)! 😍 The models demonstrate remarkable instruction following and tool calling capabilities, and can even run locally in-browser! This means they can interact with websites and call browser APIs for you! 🤯

Xenova

32,467 views • 9 months ago

we built pookie it's a helper that lives inside Slack it can search messages, generate memes, run code, and connect to your tools (Linear, GitHub, Stripe, even my bank!) fully open source and self hostable
1:05

we built pookie it's a helper that lives inside Slack it can search messages, generate memes, run code, and connect to your tools (Linear, GitHub, Stripe, even my bank!) fully open source and self hostable

Aiden Bai

45,831 views • 3 months ago

Cursor going entirely from ticket to PR! We've shipped several improvements to Cursor's agent, including support for custom tools, better semantic search, and the ability to fix lints.
0:27

Cursor going entirely from ticket to PR! We've shipped several improvements to Cursor's agent, including support for custom tools, better semantic search, and the ability to fix lints.

Cursor

638,373 views • 1 year ago

built the design using Claude and this is where ai can help you think through flows, ux, missed actions and states etc it's not perfect, but it help!
0:28

built the design using Claude and this is where ai can help you think through flows, ux, missed actions and states etc it's not perfect, but it help!

Nick

51,571 views • 4 months ago

You can build custom Integrations for any app or tool with remote MCP. Or integrate pre-built servers like Zapier and Asana. Once connected, Claude can take action across your tools: creating tasks, updating documents, and triggering workflows.
0:28

You can build custom Integrations for any app or tool with remote MCP. Or integrate pre-built servers like Zapier and Asana. Once connected, Claude can take action across your tools: creating tasks, updating documents, and triggering workflows.

Anthropic

34,843 views • 1 year ago

The Chat Playground is now the Prompts Playground—we've redesigned it to help you better test, compare, and iterate on prompts, including with tools like web search and file search. 🛝
0:28

The Chat Playground is now the Prompts Playground—we've redesigned it to help you better test, compare, and iterate on prompts, including with tools like web search and file search. 🛝

OpenAI Developers

94,686 views • 1 year ago

custom implementation of the unused hat cosmetic type from chapter 1 in og locker yes it has clipping issues and funny bugs
0:36

custom implementation of the unused hat cosmetic type from chapter 1 in og locker yes it has clipping issues and funny bugs

boredcrow24

34,379 views • 1 year ago

Search Stripe knowledge and call Stripe APIs directly in Cursor using the new Stripe MCP server! Use this command to get started: npx -y Stripe/mcp --tools=all --api-key=STRIPE_SECRET_KEY
0:54

Search Stripe knowledge and call Stripe APIs directly in Cursor using the new Stripe MCP server! Use this command to get started: npx -y Stripe/mcp --tools=all --api-key=STRIPE_SECRET_KEY

Stripe Developers

88,604 views • 1 year ago

Multi-Agent workflows are the future of AI. OpenAI released new Agent APIs today, and Box built an Agent that combines documents from Box and web search tools to generate answers. Enterprise devs can grab sample code from our GitHub repo to customize with their data.
0:44

Multi-Agent workflows are the future of AI. OpenAI released new Agent APIs today, and Box built an Agent that combines documents from Box and web search tools to generate answers. Enterprise devs can grab sample code from our GitHub repo to customize with their data.

Aaron Levie

102,062 views • 1 year ago

Wanted to learn more about MCPs this weekend. So I built this mini-tool called Here is how it works: 1️⃣ Tell the AI what you want. 2️⃣ It creates an MCP server with various tools. 3️⃣ Talk with AI to add/remove/modify these tools. 4️⃣ Click on Deploy and get your own MCP Server URL. You can directly use in url in Cursor / Claude Desktop or anywhere you want. Completely powered by Cloudflare Developers Durable Objects + Workers for Platforms
0:34

Wanted to learn more about MCPs this weekend. So I built this mini-tool called Here is how it works: 1️⃣ Tell the AI what you want. 2️⃣ It creates an MCP server with various tools. 3️⃣ Talk with AI to add/remove/modify these tools. 4️⃣ Click on Deploy and get your own MCP Server URL. You can directly use in url in Cursor / Claude Desktop or anywhere you want. Completely powered by Cloudflare Developers Durable Objects + Workers for Platforms

Bhanu Teja P

108,366 views • 1 year ago

Parallel Search + Extract tools in the @Vercel AI SDK make it easier than ever to give AI agents, apps, and workflows access to the most accurate and token-efficient web context. Here's our very own Manvesh demoing a simple implementation of the tools in an AI project.
2:06

Parallel Search + Extract tools in the @Vercel AI SDK make it easier than ever to give AI agents, apps, and workflows access to the most accurate and token-efficient web context. Here's our very own Manvesh demoing a simple implementation of the tools in an AI project.

Parallel Web Systems

21,913 views • 8 months ago

So Google has just released its own agent builder?! You can now add the agent block in Google Opal and "program it" in plain English. And it has natively: - Tool call (with Nano Banana, Veo, web search...) - Memory to save infos between sessions - Conditional logic Probably the easiest way to build AI agents I've seen so far.
0:35

So Google has just released its own agent builder?! You can now add the agent block in Google Opal and "program it" in plain English. And it has natively: - Tool call (with Nano Banana, Veo, web search...) - Memory to save infos between sessions - Conditional logic Probably the easiest way to build AI agents I've seen so far.

Paul Couvert

560,884 views • 5 months ago