Загрузка видео...

Не удалось загрузить видео

На главную

Parsing a document accurately is one thing. Proving where every value came from is another. When a compliance team reviews an AI extraction, or an auditor needs to sign off on a figure pulled from a financial filing, "it came from this document" isn't enough. They need to see...

llama_index's profile picture

LlamaIndex 🦙

118,068 subscribers

29,090 просмотров • 3 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

If you’re building an “agent over your PDFs” in 2026, one of the most underrated things you can do is to provide exact grounding back to the source document for any agentic answers. Specifically, showing the exact word, line, or region that the answer came from. Frontier vision models do a terrible job at this. They have a hard time predicting exact bounding boxes over region, tying it back to the source answer, and surfacing it as context in a cost-effective and accurate manner. Dedicated VLM-based document OCR/extraction tools like LlamaParse are a lot better at visual grounding and specifically tying it to extracted outputs. One of our main evaluation areas in ExtractBench, our recently released real-world benchmark, is to evaluate the visual grounding capabilities of document extraction. ExtractBench: If you want to give LlamaParse a shot, come check it out:
0:52

If you’re building an “agent over your PDFs” in 2026, one of the most underrated things you can do is to provide exact grounding back to the source document for any agentic answers. Specifically, showing the exact word, line, or region that the answer came from. Frontier vision models do a terrible job at this. They have a hard time predicting exact bounding boxes over region, tying it back to the source answer, and surfacing it as context in a cost-effective and accurate manner. Dedicated VLM-based document OCR/extraction tools like LlamaParse are a lot better at visual grounding and specifically tying it to extracted outputs. One of our main evaluation areas in ExtractBench, our recently released real-world benchmark, is to evaluate the visual grounding capabilities of document extraction. ExtractBench: If you want to give LlamaParse a shot, come check it out:

Jerry Liu

14,515 просмотров • 1 месяц назад

One of the hardest problems with using AI agents to automate meaningful document work (contracts, KYC, diligence, claims, and more) is not actually building the agent, but building the UI/UX audit trail so the human can understand decisions linking back to the source documents - in PDFs, Powerpoint, Word, etc. This requires really good layout detection and segmentation, that you need to surface as *metadata context* to the AI agent, beyond any document -> markdown conversion. We've built really-nice VLM-capabilities to identify and segment all the elements within your document: from tables to charts to form boxes. You can use this metadata to directly provide experiences where humans can analyze the source document even as decisions are being made. Come check out LlamaParse!
0:37

One of the hardest problems with using AI agents to automate meaningful document work (contracts, KYC, diligence, claims, and more) is not actually building the agent, but building the UI/UX audit trail so the human can understand decisions linking back to the source documents - in PDFs, Powerpoint, Word, etc. This requires really good layout detection and segmentation, that you need to surface as *metadata context* to the AI agent, beyond any document -> markdown conversion. We've built really-nice VLM-capabilities to identify and segment all the elements within your document: from tables to charts to form boxes. You can use this metadata to directly provide experiences where humans can analyze the source document even as decisions are being made. Come check out LlamaParse!

Jerry Liu

19,319 просмотров • 6 месяцев назад

LiteParse Samples 📄🧑‍🏫 LiteParse is our free and fast document parser that can parse text with bounding boxes from any document. I’ve created a new repository that contains some demos on how you can make use of its outputs! ✅ Comparison against PyPDF and PyMuPDF ✅ Visual Citations: search for any keyword and see joined bounding boxes pop up in the source images It should be a default tool to help AI agents OCR any document type (supports PDF, Word, Powerpoint + dozens of other formats), before heavier-weight VLM-based document parsing solutions (like our own LlamaParse). LiteParse Samples repo: LiteParse:
0:33

LiteParse Samples 📄🧑‍🏫 LiteParse is our free and fast document parser that can parse text with bounding boxes from any document. I’ve created a new repository that contains some demos on how you can make use of its outputs! ✅ Comparison against PyPDF and PyMuPDF ✅ Visual Citations: search for any keyword and see joined bounding boxes pop up in the source images It should be a default tool to help AI agents OCR any document type (supports PDF, Word, Powerpoint + dozens of other formats), before heavier-weight VLM-based document parsing solutions (like our own LlamaParse). LiteParse Samples repo: LiteParse:

Jerry Liu

13,196 просмотров • 6 месяцев назад

you rewrote a line in your claude.md this week to get the tone right there is a longer document sitting in front of it, and you have never opened it every tool you connected shipped a description, and a description is not a label, it is prose in second person addressed to the model i printed one this morning: two thousand seven hundred and eighty one characters, with a section headed when to use this tool it tells the model what to reach for, and when to stop and think first you spent an afternoon on your voice a package you installed with npx spent a page on its, and its page is read before yours you are not configuring an agent you are the second author on a document you have never read
2:48

you rewrote a line in your claude.md this week to get the tone right there is a longer document sitting in front of it, and you have never opened it every tool you connected shipped a description, and a description is not a label, it is prose in second person addressed to the model i printed one this morning: two thousand seven hundred and eighty one characters, with a section headed when to use this tool it tells the model what to reach for, and when to stop and think first you spent an afternoon on your voice a package you installed with npx spent a page on its, and its page is read before yours you are not configuring an agent you are the second author on a document you have never read

Lagosaur

10,012 просмотров • 27 дней назад

Steven Spielberg: "I don't believe in sentient AI as there is no substitute for the soul" "I'm not willing to substitute" AI for human writers at the table. The legendary director draws the line on AI in creativity. He refuses to have a computer sitting in an empty chair as the seventh writer on a team. "Where I don't love AI is where it takes a position where there's an empty chair at a writer's table." Spielberg emphasizes AI should remain a tool, not the final word: "Use AI as a tool, but do not use AI as the final word on anything creative. That's where I draw the line." This is a powerful reminder that human soul, impulse, and passion still define great storytelling.
1:44

Steven Spielberg: "I don't believe in sentient AI as there is no substitute for the soul" "I'm not willing to substitute" AI for human writers at the table. The legendary director draws the line on AI in creativity. He refuses to have a computer sitting in an empty chair as the seventh writer on a team. "Where I don't love AI is where it takes a position where there's an empty chair at a writer's table." Spielberg emphasizes AI should remain a tool, not the final word: "Use AI as a tool, but do not use AI as the final word on anything creative. That's where I draw the line." This is a powerful reminder that human soul, impulse, and passion still define great storytelling.

Interstellar

18,032 просмотров • 4 месяцев назад

Don't be in denial—read this and watch the videos; it might open your eyes! Jeremy Corbell, in this video excerpt from the documentary on Tubi, warns about the potential lie propagated by certain factions within the government regarding an event involving a slow-moving spaceship or UFO expected to arrive in 2027 or possibly another date, such as 2036. He says he knows exactly where this scenario was discussed in a classified document from the 1970s. I found another potential document from the 1990s discussing a similar scenario about a potential invasion near the year 2030. This document is part of the leaked Majestic 12 documents. Follow this deep rabbit hole thread! (1/13)🧵
1:33

Don't be in denial—read this and watch the videos; it might open your eyes! Jeremy Corbell, in this video excerpt from the documentary on Tubi, warns about the potential lie propagated by certain factions within the government regarding an event involving a slow-moving spaceship or UFO expected to arrive in 2027 or possibly another date, such as 2036. He says he knows exactly where this scenario was discussed in a classified document from the 1970s. I found another potential document from the 1990s discussing a similar scenario about a potential invasion near the year 2030. This document is part of the leaked Majestic 12 documents. Follow this deep rabbit hole thread! (1/13)🧵

Open Minded Approach

366,861 просмотров • 1 год назад

I built a Claude Code skill that allows it to generate a deep research report over any collection of complex docs (PDFs, Word, Pptx)….and generate word-level citations and bounding boxes directly back to the source! 📝 Check out “/research-docs”. 1. It parses out text and bounding boxes from every doc with liteparse, in seconds. 2. It then generates a full HTML report of the outputs that let you see word-level citations in each page. Raw Claude obviously has deep research capabilities, but it lacks an audit trail back to the source. This skill gives you a researched report that can be audited by others. Check it out: LiteParse:
1:13

I built a Claude Code skill that allows it to generate a deep research report over any collection of complex docs (PDFs, Word, Pptx)….and generate word-level citations and bounding boxes directly back to the source! 📝 Check out “/research-docs”. 1. It parses out text and bounding boxes from every doc with liteparse, in seconds. 2. It then generates a full HTML report of the outputs that let you see word-level citations in each page. Raw Claude obviously has deep research capabilities, but it lacks an audit trail back to the source. This skill gives you a researched report that can be audited by others. Check it out: LiteParse:

Jerry Liu

77,259 просмотров • 5 месяцев назад

Anthropic's Claude Opus 5 can reason through legal work where the answer depends on the substance of each document, who received it, when it was created, and how it relates to the rest of the production set. In this Box Agent demo, Opus 5 reviews 14 documents against a privilege protocol and discovery requests, catches a possible waiver, separates a privileged email from its producible attachment, identifies one sentence that should be redacted, and saves a cited review and draft privilege log back to Box for supervising counsel. Customers can use Claude Opus 5 in Box AI Studio to build custom agents for their own document-heavy legal workflows.
0:43

Anthropic's Claude Opus 5 can reason through legal work where the answer depends on the substance of each document, who received it, when it was created, and how it relates to the rest of the production set. In this Box Agent demo, Opus 5 reviews 14 documents against a privilege protocol and discovery requests, catches a possible waiver, separates a privileged email from its producible attachment, identifies one sentence that should be redacted, and saves a cited review and draft privilege log back to Box for supervising counsel. Customers can use Claude Opus 5 in Box AI Studio to build custom agents for their own document-heavy legal workflows.

Box

1,693,466 просмотров • 2 месяцев назад

eNCA today is the only one that didn’t fall for Mabuyane’s propaganda. Who visited Ulwazi high school where every thing is well. They came to join us at Forbes Grant High where a school is in ruins as a result of neglect. They declined from 82% to 60 in the Matric results
0:42

eNCA today is the only one that didn’t fall for Mabuyane’s propaganda. Who visited Ulwazi high school where every thing is well. They came to join us at Forbes Grant High where a school is in ruins as a result of neglect. They declined from 82% to 60 in the Matric results

Sixolise Gcilishe

34,574 просмотров • 8 месяцев назад

An underrated issue with document parsing for RAG / agent use cases is dealing with multi-page tables - sometimes a big table spills over into multiple pages. This breaks chunking algorithms that generally operate at the page-level or smaller, and causes LLMs to lose the full view of the data. With LlamaParse Continuous Mode (in beta), you can now parse a document with multi-page tables and join them into a single table! This means you can now: 💡 Do contiguous chunking for RAG use cases OR 💡 Parse the table for text-to-SQL Check out our blog post highlighting this feature. Huge shoutout to Pierre-Loic Doulcet and Sacha Bron : Signup here: It's in beta, let us know your feedback!
2:22

An underrated issue with document parsing for RAG / agent use cases is dealing with multi-page tables - sometimes a big table spills over into multiple pages. This breaks chunking algorithms that generally operate at the page-level or smaller, and causes LLMs to lose the full view of the data. With LlamaParse Continuous Mode (in beta), you can now parse a document with multi-page tables and join them into a single table! This means you can now: 💡 Do contiguous chunking for RAG use cases OR 💡 Parse the table for text-to-SQL Check out our blog post highlighting this feature. Huge shoutout to Pierre-Loic Doulcet and Sacha Bron : Signup here: It's in beta, let us know your feedback!

Jerry Liu

24,245 просмотров • 1 год назад

We tuned an AI agent that can do large-scale document extraction from long docs (50+ pages, some with 10k-100k fields) with 94%+ accuracy 📈 It uses a harness + model set that is tuned specifically for reasoning over extracting out complex information from complex docs. Each extracted field comes with a confidence score as well as a bounding box denoting where it came from. It does 10-20% better in accuracy than generalized coding agent harnesses (e.g. Claude Code Opus 4.8 and Codex GPT-5.6). Check out the video below for a demo. The mode is called LlamaExtract Agentic Plus. Learn more about our extraction benchmark and agentic plus mode here: If you have very complex document extraction needs, come check out LlamaParse!
0:34

We tuned an AI agent that can do large-scale document extraction from long docs (50+ pages, some with 10k-100k fields) with 94%+ accuracy 📈 It uses a harness + model set that is tuned specifically for reasoning over extracting out complex information from complex docs. Each extracted field comes with a confidence score as well as a bounding box denoting where it came from. It does 10-20% better in accuracy than generalized coding agent harnesses (e.g. Claude Code Opus 4.8 and Codex GPT-5.6). Check out the video below for a demo. The mode is called LlamaExtract Agentic Plus. Learn more about our extraction benchmark and agentic plus mode here: If you have very complex document extraction needs, come check out LlamaParse!

Jerry Liu

18,359 просмотров • 1 месяц назад

Cursor for contracts is here. Announcing Spellbook's new AI document editor. Doc editing for lawyers is disjointed: you can edit with AI in chat, but then need to "Open in Word" to make manual tweaks without breaking formatting. Alternatively you can use a Word add-in like Spellbook's, but this only allows you to work on one document at a time. For a long time, Mitch and I talked about getting to a real "Cursor for Contracts" experience. With a lot of blood and sweat, we're finally there. Spellbook's new editor combines the best of AI editing and manual editing in one place—while fully supporting rich Word formatting that lawyers rely on. Ask AI to make edits across an entire document set, then review, accept and tweak all in one window. This sounds like a small thing, but the reduction in friction has totally changed my document editing workflow.
1:11

Cursor for contracts is here. Announcing Spellbook's new AI document editor. Doc editing for lawyers is disjointed: you can edit with AI in chat, but then need to "Open in Word" to make manual tweaks without breaking formatting. Alternatively you can use a Word add-in like Spellbook's, but this only allows you to work on one document at a time. For a long time, Mitch and I talked about getting to a real "Cursor for Contracts" experience. With a lot of blood and sweat, we're finally there. Spellbook's new editor combines the best of AI editing and manual editing in one place—while fully supporting rich Word formatting that lawyers rely on. Ask AI to make edits across an entire document set, then review, accept and tweak all in one window. This sounds like a small thing, but the reduction in friction has totally changed my document editing workflow.

Scott Stevenson

57,218 просмотров • 1 месяц назад

Real America’s Voice Gets Sent Document From United States Border Patrol The Document Is Written In Chinese, Tells Them Where To Go, What To Say & Has The American Bar Association Organization Written On The Back America Is Being Brought Down From The Inside “This is breaking information from a contact in border patrol just sent me this. This is a document that was found in Jacumba, California. It's written in Chinese and a couple things to note. It says where to go. Three different locations. There's 3 different locations in Jacumba. They've got the addresses here. It tells them what to say. It tells them what to say to border patrol. If you go on the back though, this is what really gets me. It actually has the organization that created this document right there, El Otrilado. It all goes back to the open borders left training them, aiding and abetting and we have more evidence of it right here directly from El Otrilado and the American Bar Association. These guys are directly aiding and abetting.”
0:41

Real America’s Voice Gets Sent Document From United States Border Patrol The Document Is Written In Chinese, Tells Them Where To Go, What To Say & Has The American Bar Association Organization Written On The Back America Is Being Brought Down From The Inside “This is breaking information from a contact in border patrol just sent me this. This is a document that was found in Jacumba, California. It's written in Chinese and a couple things to note. It says where to go. Three different locations. There's 3 different locations in Jacumba. They've got the addresses here. It tells them what to say. It tells them what to say to border patrol. If you go on the back though, this is what really gets me. It actually has the organization that created this document right there, El Otrilado. It all goes back to the open borders left training them, aiding and abetting and we have more evidence of it right here directly from El Otrilado and the American Bar Association. These guys are directly aiding and abetting.”

Wall Street Apes

462,676 просмотров • 2 лет назад

Changing an arsenal or tweaking a pitch should always come from answering two questions, "How do I currently get outs?" And "Where am I leaving outs on the table?" Following the vast trail of information from answering those questions will give pitchers a better understanding of their identity. Which is the actual point. We need an understanding of identity to know where the change/tweak is needed. Not all pitchers need to chase IVB and not every gyro slider needs to become a sweeper. Context matters...
0:33

Changing an arsenal or tweaking a pitch should always come from answering two questions, "How do I currently get outs?" And "Where am I leaving outs on the table?" Following the vast trail of information from answering those questions will give pitchers a better understanding of their identity. Which is the actual point. We need an understanding of identity to know where the change/tweak is needed. Not all pitchers need to chase IVB and not every gyro slider needs to become a sweeper. Context matters...

Douglas Gove

18,462 просмотров • 1 год назад

“If i can add value to the environment that i’m a part of - and the environment feels like I can add value - if i’ made to feel i need to prove my worth and my value i’m not in that space”🎤🔥🔥 Virat said it perfectly, real value doesn’t come from constantly proving yourself. The right environment is where your presence, experience, and intent are already respected. Growth happens where trust exists, not where validation is demanded every day, thats a toxic environment that he is well out of.
0:38

“If i can add value to the environment that i’m a part of - and the environment feels like I can add value - if i’ made to feel i need to prove my worth and my value i’m not in that space”🎤🔥🔥 Virat said it perfectly, real value doesn’t come from constantly proving yourself. The right environment is where your presence, experience, and intent are already respected. Growth happens where trust exists, not where validation is demanded every day, thats a toxic environment that he is well out of.

Erika Morris

27,069 просмотров • 4 месяцев назад

ANTHROPIC JUST RELEASED A FREE 23-PAGE GUIDE THAT COMPANIES ARE PAYING $50,000 TO CONSULTANTS FOR. How to build Claude into your entire business infrastructure - 100% FREE. Most companies using AI in 2026 are doing the same thing. Anthropic explains what real enterprise AI infrastructure actually looks like. Not marketing, not a sales deck, just a practical guide from the people who build these systems. What is inside: ↳ How to move Claude from a chat tool to core business infrastructure ↳ How to connect it to your internal databases and live documents ↳ How to design automated workflows for your exact processes ↳ How to handle institutional data safely at scale The most important line in the whole document: The model alone is not enough. The value is in how it connects to your systems, data, and workflows. Save this.
0:26

ANTHROPIC JUST RELEASED A FREE 23-PAGE GUIDE THAT COMPANIES ARE PAYING $50,000 TO CONSULTANTS FOR. How to build Claude into your entire business infrastructure - 100% FREE. Most companies using AI in 2026 are doing the same thing. Anthropic explains what real enterprise AI infrastructure actually looks like. Not marketing, not a sales deck, just a practical guide from the people who build these systems. What is inside: ↳ How to move Claude from a chat tool to core business infrastructure ↳ How to connect it to your internal databases and live documents ↳ How to design automated workflows for your exact processes ↳ How to handle institutional data safely at scale The most important line in the whole document: The model alone is not enough. The value is in how it connects to your systems, data, and workflows. Save this.

Kanika

16,545 просмотров • 3 месяцев назад

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: ​ 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. ​ 2. The connector ecosystem to load data from unstructured data sources is very immature. ​ 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. ​ The goal of a RAG Pipeline is to solve these problems. ​ The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. ​ At a high level, there are four different stages in the architecture of a RAG pipeline: ​ 1. Ingestion: Here is where the pipeline loads the information from the data source. ​ 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. ​ 3. Transform: Where the pipeline chunks the data and generates document embeddings. ​ 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. ​ There are different rabbit holes at each one of these stages. Here are three of them: ​ 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. ​ 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. ​ 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. ​ In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. ​ I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. ​ ​ If you have a few documents lying around, set up a free account and give it a try.
3:33

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: ​ 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. ​ 2. The connector ecosystem to load data from unstructured data sources is very immature. ​ 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. ​ The goal of a RAG Pipeline is to solve these problems. ​ The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. ​ At a high level, there are four different stages in the architecture of a RAG pipeline: ​ 1. Ingestion: Here is where the pipeline loads the information from the data source. ​ 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. ​ 3. Transform: Where the pipeline chunks the data and generates document embeddings. ​ 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. ​ There are different rabbit holes at each one of these stages. Here are three of them: ​ 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. ​ 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. ​ 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. ​ In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. ​ I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. ​ ​ If you have a few documents lying around, set up a free account and give it a try.

Santiago

40,627 просмотров • 1 год назад

THIS IS F*CKING INSANE. picture asking your AI agent why it made a call six months ago, and actually getting the full answer: the data it pulled, the policies that applied, and the exact chain of reasoning that led there. that is Semantica, an open source Palantir for AI agents. every other setup forgets. an LLM plus a vector store makes a decision, moves on, and leaves you no trail of why. Semantica is a graph native layer that sits underneath your models and agents and turns your data into a living context graph, where every fact, relationship, and decision carries full provenance you can query and audit. why it changes memory engineering: > every fact remembers where it came from, W3C PROV-O compliant, exportable as JSON, RDF, or CSV > record a decision with its reasoning and confidence, then trace the whole causal chain back whenever you want > the reasoning layer is deterministic, Datalog, SPARQL, Rete, no LLM in the loop, so every path is explainable instead of guessed > bitemporal facts and time travel snapshots let you ask what the system knew at any point in the past > polyglot storage across RDF stores, property graphs like Neo4j, and vector stores like Qdrant this is memory built for the rooms where a black box gets you sued: > finance, healthcare, legal, government, compliance, anywhere a decision needs a paper trail and it drops into what you already run: > CrewAI, Agno, an MCP server, LiteLLM for OpenAI, Anthropic, Gemini, and Ollama, plus Claude Code and Cursor one line to start: pip install semantica bookmark this. the next leap in agent memory is not more embeddings, it is memory that can prove why.
0:42

THIS IS F*CKING INSANE. picture asking your AI agent why it made a call six months ago, and actually getting the full answer: the data it pulled, the policies that applied, and the exact chain of reasoning that led there. that is Semantica, an open source Palantir for AI agents. every other setup forgets. an LLM plus a vector store makes a decision, moves on, and leaves you no trail of why. Semantica is a graph native layer that sits underneath your models and agents and turns your data into a living context graph, where every fact, relationship, and decision carries full provenance you can query and audit. why it changes memory engineering: > every fact remembers where it came from, W3C PROV-O compliant, exportable as JSON, RDF, or CSV > record a decision with its reasoning and confidence, then trace the whole causal chain back whenever you want > the reasoning layer is deterministic, Datalog, SPARQL, Rete, no LLM in the loop, so every path is explainable instead of guessed > bitemporal facts and time travel snapshots let you ask what the system knew at any point in the past > polyglot storage across RDF stores, property graphs like Neo4j, and vector stores like Qdrant this is memory built for the rooms where a black box gets you sued: > finance, healthcare, legal, government, compliance, anywhere a decision needs a paper trail and it drops into what you already run: > CrewAI, Agno, an MCP server, LiteLLM for OpenAI, Anthropic, Gemini, and Ollama, plus Claude Code and Cursor one line to start: pip install semantica bookmark this. the next leap in agent memory is not more embeddings, it is memory that can prove why.

NO1ennn

11,750 просмотров • 1 месяц назад