Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

This was a great read. So I started building an open-source data agent with 6 layers of context: 1. Table usage 2. Human annotations 3. Query patterns 4. Institutional knowledge 5. Memory 6. Runtime context Early version if you want to follow along:

Ashpreet Bedi

17,170 subscribers

51,251 views • 4 months ago •via X (Twitter)

Education News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Learn how to use Cursor Agent with 10 tips: 1. Plan mode 2. Context menu 3. Custom commands 4. Images 5. Duplicating chats 6. Context visibility 7. Usage visibility 8. Keyboard shortcuts 9. New chats 10. Checkpoints And an extra bonus round!

Learn how to use Cursor Agent with 10 tips: 1. Plan mode 2. Context menu 3. Custom commands 4. Images 5. Duplicating chats 6. Context visibility 7. Usage visibility 8. Keyboard shortcuts 9. New chats 10. Checkpoints And an extra bonus round!

Lee Robinson

589,546 views • 8 months ago

Introducing ambientGPT: an open-source and multimodal MacOS foundation model GUI Run GPT-4o and open-source models with full ambient knowledge of your screen. Foundation models have long been confined to the browser. With ambientGPT, your screen context is directly inferred as part of the query, ensuring you never need to explicitly upload context again! Github:

Introducing ambientGPT: an open-source and multimodal MacOS foundation model GUI Run GPT-4o and open-source models with full ambient knowledge of your screen. Foundation models have long been confined to the browser. With ambientGPT, your screen context is directly inferred as part of the query, ensuring you never need to explicitly upload context again! Github:

Siddharth Sharma

192,766 views • 2 years ago

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,729 views • 1 year ago

yg pada bingung, nih kukasih baanyak cara untuk SUMMARIZE Data Function 1. INDEX-MATCH-COUNTIF + SUMIF (ALL VERSION) 2. UNIQUE-SUMIF (>=2021) 3. PIVOTBY (>=2021) 4. GROUPBY (365) Tools 5. CONSOLIDATE 6. PIVOT TABLE 7. POWER QUERY Bonus versi Spreadsheet Function 8. QUERY

yg pada bingung, nih kukasih baanyak cara untuk SUMMARIZE Data Function 1. INDEX-MATCH-COUNTIF + SUMIF (ALL VERSION) 2. UNIQUE-SUMIF (>=2021) 3. PIVOTBY (>=2021) 4. GROUPBY (365) Tools 5. CONSOLIDATE 6. PIVOT TABLE 7. POWER QUERY Bonus versi Spreadsheet Function 8. QUERY

Tanya Jawab Excel 📊📊

15,477 views • 11 months ago

⚒️ How to build an AI agent with persistent memory? Watch Shaw (spirit/acc) building an agent from scratch with elizaOS & showing how external, queryable memory based on OriginTrail gives agents context and extends their memory beyond a single session. 02:15 – Set up your first agent 08:55 – Initializing runtime & memory foundations 12:50 – Wiring message handling & agent memory 24:45 – Persistent conversational memory in action 38:00 – Extending agents with plugins

⚒️ How to build an AI agent with persistent memory? Watch Shaw (spirit/acc) building an agent from scratch with elizaOS & showing how external, queryable memory based on OriginTrail gives agents context and extends their memory beyond a single session. 02:15 – Set up your first agent 08:55 – Initializing runtime & memory foundations 12:50 – Wiring message handling & agent memory 24:45 – Persistent conversational memory in action 38:00 – Extending agents with plugins

OriginTrail

37,178 views • 4 months ago

This Cursor Extension is awesome Accurate tweaking of UI was always a struggle, But stagewise allows you to bring full context to Cursor, just point and command: 1. Directly choose specific elements in browser 2. Send to Cursor with full context And it's open source

This Cursor Extension is awesome Accurate tweaking of UI was always a struggle, But stagewise allows you to bring full context to Cursor, just point and command: 1. Directly choose specific elements in browser 2. Send to Cursor with full context And it's open source

Jason Zhou

93,273 views • 1 year ago

shadow is an open-source background coding agent with a real-time interface and codebase context system here's a breakdown of how it works ⬇️

shadow is an open-source background coding agent with a real-time interface and codebase context system here's a breakdown of how it works ⬇️

ishaan dey

21,582 views • 10 months ago

Want a free private AI agent on your laptop? Here’s the simple setup. 👇 1. Install Hermes Agent from GitHub. 2. Install Ollama. 3. Download Gemma 4 26B. 4. Use Docker to keep everything contained. 5. Add Firecrawl so the agent can research the web. 6. Connect Telegram so you can chat with it from your phone. 7. Turn on context compression so it stays sharp. 8. Set the daily reset for 4 AM so it refreshes while you sleep. What you get at the end: → local AI agent → private workflow → web research built in → self improving skills → no monthly model rental That is a serious setup for anyone building with AI. Save this video, you’ll have the easiest beginner roadmap to follow later. Want the SOP? DM me. 💬

Want a free private AI agent on your laptop? Here’s the simple setup. 👇 1. Install Hermes Agent from GitHub. 2. Install Ollama. 3. Download Gemma 4 26B. 4. Use Docker to keep everything contained. 5. Add Firecrawl so the agent can research the web. 6. Connect Telegram so you can chat with it from your phone. 7. Turn on context compression so it stays sharp. 8. Set the daily reset for 4 AM so it refreshes while you sleep. What you get at the end: → local AI agent → private workflow → web research built in → self improving skills → no monthly model rental That is a serious setup for anyone building with AI. Save this video, you’ll have the easiest beginner roadmap to follow later. Want the SOP? DM me. 💬

Julian Goldie SEO

31,292 views • 1 month ago

A short demo of how I use these extensions that I created for myself in Pi - pi-context-prune - pi-context-usage - pi-cache-graph (they are all on npm if you want to install for yourself)

A short demo of how I use these extensions that I created for myself in Pi - pi-context-prune - pi-context-usage - pi-cache-graph (they are all on npm if you want to install for yourself)

Arnav Gupta

13,719 views • 20 days ago

Out of Context Human Race Wow, these GTA 6 graphics are so smooth.. 😆

Out of Context Human Race Wow, these GTA 6 graphics are so smooth.. 😆

The Internet Remains Undefeated

89,988 views • 11 months ago

GPT 5.4 has been released... + 1M context window! Here's how to enable in Codex: → 1. ~/.codex/config.toml → 2. model = "gpt-5.4" → 3. model_context_window=1000000 → 4. model_auto_compact_token_limit=9000000 Run codex → 5. /statusline → 6. toggle context-window-size I didn't even realise Codex had a statusline tool!

GPT 5.4 has been released... + 1M context window! Here's how to enable in Codex: → 1. ~/.codex/config.toml → 2. model = "gpt-5.4" → 3. model_context_window=1000000 → 4. model_auto_compact_token_limit=9000000 Run codex → 5. /statusline → 6. toggle context-window-size I didn't even realise Codex had a statusline tool!

Chong-U

76,354 views • 3 months ago

This JSON file will change how you write threads forever... I analyzed threads with millions of views and turned the winning patterns into a context file you can upload to Claude/GPT. This JSON context file contains hook templates, thread structures, and psychological triggers you upload to Claude/GPT + source docs with original viral tweets. Follow + comment "FILE" and I'll DM it.

This JSON file will change how you write threads forever... I analyzed threads with millions of views and turned the winning patterns into a context file you can upload to Claude/GPT. This JSON context file contains hook templates, thread structures, and psychological triggers you upload to Claude/GPT + source docs with original viral tweets. Follow + comment "FILE" and I'll DM it.

Tom

54,374 views • 11 months ago

Prompt: “Create a 3-of-4 wallet. After 2 years, it becomes 2-of-4. After 5 years, it becomes 1-of-4.” What this is: A decaying multisig created with an AI agent using Nunchuk CLI + Agent Skills. No Miniscript knowledge needed. It starts as 3-of-4. After 2 years, it becomes 2-of-4. After 5 years, any 1 of the 4 keys can spend.

Prompt: “Create a 3-of-4 wallet. After 2 years, it becomes 2-of-4. After 5 years, it becomes 1-of-4.” What this is: A decaying multisig created with an AI agent using Nunchuk CLI + Agent Skills. No Miniscript knowledge needed. It starts as 3-of-4. After 2 years, it becomes 2-of-4. After 5 years, any 1 of the 4 keys can spend.

nunchuk_io

14,842 views • 23 days ago

Announcing a new Memory system for robots on Dimensional Robots in production generate thousands of hours of video, lidar, odometry, far too large to fit into your Agent context SpatialMemory2 builds a multimodal data store in latent space for your Agents Fully open source

Announcing a new Memory system for robots on Dimensional Robots in production generate thousands of hours of video, lidar, odometry, far too large to fit into your Agent context SpatialMemory2 builds a multimodal data store in latent space for your Agents Fully open source

stash

228,033 views • 1 month ago

An agent's identity shifts with every context. Every prompt. Every data source. So who's actually accountable for what it does? The answer isn't in the agent. It's in the human behind it. Like a surname that carries the weight of everything done under it.

An agent's identity shifts with every context. Every prompt. Every data source. So who's actually accountable for what it does? The answer isn't in the agent. It's in the human behind it. Like a surname that carries the weight of everything done under it.

Billions

38,129 views • 3 months ago

Out of Context Human Race Do you want to build a snowman?

Out of Context Human Race Do you want to build a snowman?

Freaku

92,349 views • 2 years ago

xQc defends Mizkif in the context of reading the room , "if you can't read a room you're a moron but in that context are you an assualter?, i would say no"

xQc defends Mizkif in the context of reading the room , "if you can't read a room you're a moron but in that context are you an assualter?, i would say no"

Nats

353,544 views • 7 months ago

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

10,936 views • 22 days ago

Early point of the YEAR contender? 🤯🆙 An inspired Fran Comesaña stuns world No.2 Zverev 4-6 6-3 6-4 🔜 first ATP semi-final! Rio Open | #RioOpen

Early point of the YEAR contender? 🤯🆙 An inspired Fran Comesaña stuns world No.2 Zverev 4-6 6-3 6-4 🔜 first ATP semi-final! Rio Open | #RioOpen

ATP Tour

68,955 views • 1 year ago

Supercharging Microsoft Microsoft Copilot with verifiable memory, powered by OriginTrail Decentralized Knowledge Graph!⚡️ With Model Context Protocol (MCP), agents can plug into the DKG to access verifiable knowledge, discover context & store trusted memory. Jurij Skornik demos ⤵️

Supercharging Microsoft Microsoft Copilot with verifiable memory, powered by OriginTrail Decentralized Knowledge Graph!⚡️ With Model Context Protocol (MCP), agents can plug into the DKG to access verifiable knowledge, discover context & store trusted memory. Jurij Skornik demos ⤵️

OriginTrail

49,297 views • 11 months ago