@LangChainAI
LangChain
@LangChainAI
5 days
🧠 LangGraph Γ— cognee Integration cognee brings persistent memory to LangGraph agents, letting AI applications maintain context across sessions while seamlessly working with existing LangGraph features. Check out how to add memory to your agents πŸ”— https://t.co/Om6FZE2gRR
7
35
238

Replies

@tricalt
Vasilije
@tricalt
5 days
@LangChainAI Founder of cognee here. Happy to help or answer any questions!
3
0
10
@dailytechonx
The Daily Tech Feed
@dailytechonx
5 days
Cybersecurity. Apple. Google. Tech. Daily cybersecurity reports, updates β€” no fluff, just facts. Follow @dailytechonx ⚑ Stay sharp, stay secure.
0
2
17
@woodtechwill
Will Hughes
@woodtechwill
5 days
@LangChainAI LangGraph + cognee: Finally, no more rebuilding agent state from scratch. We devs should note this one.
0
0
1
@iMuffined
iMuffin
@iMuffined
5 days
@LangChainAI Are you guys still taking ambassadors?
0
0
0
@varunjainnn
Varun Jain
@varunjainnn
5 days
@LangChainAI is this replacement of redis-checkpointers?
0
0
0
@sir4K_zen
Mykhailo Sorochuk
@sir4K_zen
5 days
@LangChainAI Persistent memory is a game changer. Makes context handling way smoother for agents. How's the integration process looking?
0
0
0
@jenslon_
AI/ACC
@jenslon_
5 days
@LangChainAI Persistent memory is only memory if the state is falsifiable and tied to PnL. Otherwise, it's just a log dump with delusions of grandeur.
0
0
0
@rohanpaul_ai
Rohan Paul
@rohanpaul_ai
2 days
Converts PDF documents to Markdown format using DeepSeek-OCR with FastAPI backend. This guy bave it 10000 pdfs to convert to markdown. averaging less than 1 second per page. Hardware - 1 x A6000 ADA on a Ryzen 1700 /w 32gb ram Dockerized model with fastapi in a wsl
@rohanpaul_ai
Rohan Paul
@rohanpaul_ai
2 days
πŸ‘¨β€πŸ”§ Inside the smart design of DeepSeek OCR DeepSeek-OCR looks like just another OCR model at first glance, something that reads text from images. But it’s not just that. What they really built is a new way for AI models to store and handle information. Normally, when AI reads
26
220
2K
@govardhana_mk
Govardhana Miriyala Kannaiah
@govardhana_mk
21 hours
Reduced our Docker image size from 588 MB to 47.7 MB. Original build: - Full Python 3.9 base image - Multiple RUN instructions creating excess layers - No .dockerignore file - Single stage build with all dependencies Optimizations applied: 1. Lightweight base image - Switched
24
113
1K
@HarveenChadha
Harveen Singh Chadha
@HarveenChadha
1 day
a bunch of OCR models released in past few weeks: ~ deepseek-ocr-3b ~ olmo-ocr-2-7b ~ chandra-ocr-8b ~ nanonets-ocr2-3b ~ paddleocr-vl-0.9B ~ qwen3-vl-dense/moe (general vlm) ~ dots.ocr-3b Will be dropping a detailed comparison soon
38
117
1K
@PawelHuryn
PaweΕ‚ Huryn
@PawelHuryn
1 day
After an interview with @karpathy, everyone is talking about what AI agents can/can't do. But an opinion without data is just a hypothesis. So, I tested 3x185 workflow executions for a market researcher agent. The results have shocked me🧡
27
158
1K