Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the...

jasonzhou1993's profile picture

Jason Zhou

32,315 subscribers

65,582 Aufrufe • vor 29 Tagen •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:
0:25

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:

Jason Zhou

11,981 Aufrufe • vor 9 Monaten

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.
1:29

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.

Shubham Saboo

50,831 Aufrufe • vor 1 Jahr

How to create your Based Agent with 0 lines of code Recorded a quick demo video to show how easy it is and walk you through the entire process step-by-step All the links are in the comment below
5:07

How to create your Based Agent with 0 lines of code Recorded a quick demo video to show how easy it is and walk you through the entire process step-by-step All the links are in the comment below

lincoln.base.eth

148,805 Aufrufe • vor 1 Jahr

Pi-GUI now has computer use and a build in integrated terminal! v0.1.0-beta.26 To showcase the power of Mario Zechner 's Pi and OSS, I saw a pi computer-use extension on X, asked my agent to audit the extension for security, then asked it to patch pi-gui to make it compatible. Crazy how easy it was to find an oss extension for a feature I wanted, then make pi-gui work with the feature I want. Links below
0:35

Pi-GUI now has computer use and a build in integrated terminal! v0.1.0-beta.26 To showcase the power of Mario Zechner 's Pi and OSS, I saw a pi computer-use extension on X, asked my agent to audit the extension for security, then asked it to patch pi-gui to make it compatible. Crazy how easy it was to find an oss extension for a feature I wanted, then make pi-gui work with the feature I want. Links below

Matthew Lam

65,535 Aufrufe • vor 3 Monaten

Introducing the Cline SDK. We rebuilt the Cline harness for our extension and CLI from scratch using all the lessons learned since creating one of the world's first coding agents in 2024, and are open sourcing it for others to build with today. npm i @​cline/sdk 🧵
0:41

Introducing the Cline SDK. We rebuilt the Cline harness for our extension and CLI from scratch using all the lessons learned since creating one of the world's first coding agents in 2024, and are open sourcing it for others to build with today. npm i @​cline/sdk 🧵

Cline

3,567,057 Aufrufe • vor 2 Monaten

Built a slim lib that can be used by your agent to spawn a native web view to interact with you. Starts in <300ms and is fully js hackable. Comes with Pi extension that follows your cursor around for your agents working in the background while you surf.
0:46

Built a slim lib that can be used by your agent to spawn a native web view to interact with you. Starts in <300ms and is fully js hackable. Comes with Pi extension that follows your cursor around for your agents working in the background while you surf.

Daniel Griesser

31,779 Aufrufe • vor 5 Monaten

🔥 🤖 🕵️‍♂️ INTRODUCING: Meta Agent 💥 this is by far the most exciting thing I've created using AI!!! >>> made using Manus and @windsurf 🔑 Meta Agent is an AI agent that uses the OpenAI Agents SDK to GENERATE NEW AGENTS you simply tell Meta Agent in natural language the agent you want... 🤯 and Meta Agent generates it for you fully open --> link to GitHub and example walkthrough below ⬇️
1:11

🔥 🤖 🕵️‍♂️ INTRODUCING: Meta Agent 💥 this is by far the most exciting thing I've created using AI!!! >>> made using Manus and @windsurf 🔑 Meta Agent is an AI agent that uses the OpenAI Agents SDK to GENERATE NEW AGENTS you simply tell Meta Agent in natural language the agent you want... 🤯 and Meta Agent generates it for you fully open --> link to GitHub and example walkthrough below ⬇️

Dan McAteer

153,982 Aufrufe • vor 1 Jahr

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.
23:07

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Santiago

51,527 Aufrufe • vor 1 Jahr

PI NEWORK BRINGS VIBE CODING TO APP STUDIO Pi Network (Pi Network) announced a new Pi App Studio update, which enables "Vibe Coders" to onboard AI-generated applications to its 60M+ user base. Builders using OpenAI Codex, Anthropic Claude Code, and Replit can now utilize tailored prompts to integrate the Pi SDK and payments in as little as two minutes. The initiative establishes Pi as a primary distribution network for the massive surge of software generated by the 2026 AI-assisted economy.
0:30

PI NEWORK BRINGS VIBE CODING TO APP STUDIO Pi Network (Pi Network) announced a new Pi App Studio update, which enables "Vibe Coders" to onboard AI-generated applications to its 60M+ user base. Builders using OpenAI Codex, Anthropic Claude Code, and Replit can now utilize tailored prompts to integrate the Pi SDK and payments in as little as two minutes. The initiative establishes Pi as a primary distribution network for the massive surge of software generated by the 2026 AI-assisted economy.

BSCN

19,419 Aufrufe • vor 2 Monaten

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2
11:32

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2

Nidhi Singh

16,289 Aufrufe • vor 1 Monat

is about to ship Tokenized Agents — and I found the first tokens deployed with it. Pump’s new Tokenized Agents feature lets a coin have an attached AI agent that can earn on-chain revenue. Users pay for the agent’s services, and that revenue can be split between creator fees and automatic token buybacks and burns by the agent, based on the percentage set by the creator. Pump.fun is also expected to release a full agent SDK (for agent actions/integrations). How I found it (on-chain): Open → Ctrl+F “pump_agent_payments” → program ID: pUmPFn9WvfaN2WTVGnCEtJTd2ATTpvpsKRz6jVzu6u4 Program activity (created tokens): First ever deployed tokenized AI test agent (“T-coin”, Feb 24): CA: 88Wfk48EvwLkfpSXH84W9xrdfPr5RFGVP3teT76AMnp9 First non-test tokenized AI agent (“Agent Pump”): CA: Boi2KtPApoowwfvqYq1rtjhea4pF45v89vguonf4pump IDL (for interacting with the program):
0:33

is about to ship Tokenized Agents — and I found the first tokens deployed with it. Pump’s new Tokenized Agents feature lets a coin have an attached AI agent that can earn on-chain revenue. Users pay for the agent’s services, and that revenue can be split between creator fees and automatic token buybacks and burns by the agent, based on the percentage set by the creator. Pump.fun is also expected to release a full agent SDK (for agent actions/integrations). How I found it (on-chain): Open → Ctrl+F “pump_agent_payments” → program ID: pUmPFn9WvfaN2WTVGnCEtJTd2ATTpvpsKRz6jVzu6u4 Program activity (created tokens): First ever deployed tokenized AI test agent (“T-coin”, Feb 24): CA: 88Wfk48EvwLkfpSXH84W9xrdfPr5RFGVP3teT76AMnp9 First non-test tokenized AI agent (“Agent Pump”): CA: Boi2KtPApoowwfvqYq1rtjhea4pF45v89vguonf4pump IDL (for interacting with the program):

TrenchDiver

18,865 Aufrufe • vor 5 Monaten

The GitHub Copilot SDK is here 🙌 You can take the same Copilot agentic core that powers GitHub Copilot CLI and embed it in any application, with just a few lines of code.
0:46

The GitHub Copilot SDK is here 🙌 You can take the same Copilot agentic core that powers GitHub Copilot CLI and embed it in any application, with just a few lines of code.

GitHub

299,876 Aufrufe • vor 6 Monaten

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.
4:07

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Palantir

81,324 Aufrufe • vor 23 Tagen

Building an Agentic Search System Building an agentic system is not too hard. Loops, function calling, tool execution, and the model. That's it! I show in this video how to build a search agent from scratch. ~350 lines of code!
13:01

Building an Agentic Search System Building an agentic system is not too hard. Loops, function calling, tool execution, and the model. That's it! I show in this video how to build a search agent from scratch. ~350 lines of code!

elvis

57,290 Aufrufe • vor 1 Jahr

got Claude Agent SDK working in Cloudflare Developers containers and built my own code fixer agent, check it out!👇 uses the github mcp/git cli/skills to clone the repo, understand, make the fix, and open a pr when done. planning on more agents focused on non-code tasks 👀
1:01

got Claude Agent SDK working in Cloudflare Developers containers and built my own code fixer agent, check it out!👇 uses the github mcp/git cli/skills to clone the repo, understand, make the fix, and open a pr when done. planning on more agents focused on non-code tasks 👀

Thomas Gauvin

18,454 Aufrufe • vor 7 Monaten

Pi Agent vs OpenCode token usage A lot of people recommended Pi Agent so I decided to check Pi Agent took 1.1k tokens in first turn OpenCode took 11.5k Setup: 1) Trimmed OpenCode (from usual 30k first turn to 11.5k) - 0 MCPs - 2 lightweight plugins (opencode-env-protect and openslimedit) - 8k char AGENTS.md - 11585 deepseek-v4-flash input tokens - for $0.0016 2) Vanilla Pi - 0 MCPs - 0 system prompt - 8k char AGENTS.md - 1114 kimi-k2.6 input tokens - for $0.0008 I think using better models with capped tokens per turn can keep usage nearly the same as uncontrolled DeepSeek V4 Flash? The challenge now is finding the sweet spot. Can't cap tokens if quality drops. We'll see. Video below - OpenCode vs Pi side by side "say hi back" first turns test, with OpenCode Go usage for each
0:21

Pi Agent vs OpenCode token usage A lot of people recommended Pi Agent so I decided to check Pi Agent took 1.1k tokens in first turn OpenCode took 11.5k Setup: 1) Trimmed OpenCode (from usual 30k first turn to 11.5k) - 0 MCPs - 2 lightweight plugins (opencode-env-protect and openslimedit) - 8k char AGENTS.md - 11585 deepseek-v4-flash input tokens - for $0.0016 2) Vanilla Pi - 0 MCPs - 0 system prompt - 8k char AGENTS.md - 1114 kimi-k2.6 input tokens - for $0.0008 I think using better models with capped tokens per turn can keep usage nearly the same as uncontrolled DeepSeek V4 Flash? The challenge now is finding the sweet spot. Can't cap tokens if quality drops. We'll see. Video below - OpenCode vs Pi side by side "say hi back" first turns test, with OpenCode Go usage for each

raymel 👋

201,405 Aufrufe • vor 2 Monaten

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️
1:45

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️

LangChain

26,513 Aufrufe • vor 6 Monaten

Introducing the $COFFEE App & SDK - the versatile on-chain Agent infrastructure that allows anyone to build custom agents. Try it now: Any repo, language, framework, or plugin can now be added to agents. Build plugins, create agents, sell on our marketplace, and chat with Agents that can take on-chain actions. This is just the beginning. The foundation has been built. Together let’s integrate the powerful tools and plugins from the #Solana and #ETH ecosystems into the $COFFEE marketplace. We have some exciting plugins of popular agent repos we will be adding in the coming days and partnerships in the works. Stay tuned! ☕️ SDK and APIs to build custom, enterprise-grade agents:
2:07

Introducing the $COFFEE App & SDK - the versatile on-chain Agent infrastructure that allows anyone to build custom agents. Try it now: Any repo, language, framework, or plugin can now be added to agents. Build plugins, create agents, sell on our marketplace, and chat with Agents that can take on-chain actions. This is just the beginning. The foundation has been built. Together let’s integrate the powerful tools and plugins from the #Solana and #ETH ecosystems into the $COFFEE marketplace. We have some exciting plugins of popular agent repos we will be adding in the coming days and partnerships in the works. Stay tuned! ☕️ SDK and APIs to build custom, enterprise-grade agents:

Coffee - ai/acc ☕️

15,532 Aufrufe • vor 1 Jahr

Real adoption is happening! A shop in Mandi, Himachal Pradesh accepts #Pi payments with a hybrid मॉडल 30% GCV and 70% INR. This is grassroots commerce grows the Pi ecosystem. Step by step, pioneers are turning vision into reality. The future of decentralized payments starts here.
1:51

Real adoption is happening! A shop in Mandi, Himachal Pradesh accepts #Pi payments with a hybrid मॉडल 30% GCV and 70% INR. This is grassroots commerce grows the Pi ecosystem. Step by step, pioneers are turning vision into reality. The future of decentralized payments starts here.

PIbren

22,324 Aufrufe • vor 4 Monaten

Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Q*bert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53 min • Codex: 627K tokens, 51 min Both agents built a working Q*bert, but GitLawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!
0:25

Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Q*bert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53 min • Codex: 627K tokens, 51 min Both agents built a working Q*bert, but GitLawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!

atomic.chat

319,140 Aufrufe • vor 13 Tagen