# Self-improving skills for remote Agents
**Date de l'événement :** 25/04/2026
* Publié le 25/04/2026

### Date
25/04/2026

### Galerie d'image
![1.png](https://firebasestorage.googleapis.com/v0/b/memory-ai.appspot.com/o/prod%2FrKxsdSTpqCfzIFY8Y2hg%2FprojectsMedias%2Fo1hugcik7PSHX5QTh0L8%2Fthumbs%2F1_1600x900.png?alt=media&token=1d81729d-6668-493d-a1d5-88523f37b8d6) 

### Ville
`#San Francisco` 

## Description
🧠 AI-Memory Hackathon #2 🚀 This hackathon is for developers who want to build AI agents that learn from experience and self-improve over time. 🏆$1,500+ Cash Pool Main Prizes 🥇 Prize: $800 cash 🥈 Prize: $500 cash 🥉 Prize: $200 cash Special Prizes 🎖️ TBA 🧰 Build Agents That Learn In this hands-on hackathon, you will use Cognee’s open-source memory engine to equip remote agents with persistent memory and self-improving skills. Instead of starting from scratch on every task, your agents will be able to remember past actions, reflect on outcomes, and adapt their behavior over time. Think: Remote agents that execute workflows across tools and environments Agents that learn which actions work best and refine their behavior Skill-based agents that build reusable capabilities over time Systems that combine memory, feedback, and reasoning in the cloud ☁️ And all of that on cloud You will build and run your applications in a cloud environment, enabling agents to operate remotely with access to a decentralised memory layer that shares persist knowledge across your agents. 💥 Show us what you got You will have 3 minutes to stand out: Present your idea and explain how you leverage agent self-improvement Run a live demo that showcases your agent in action ⏱️ Schedule 12:00 PM — Doors open + Networking 12:30 PM — Opening remarks + partner demos 1:00 PM — Hacking begins 4:30 PM — Project Submission Deadline - finalists selection 5:00 PM — Finalist presentation & judging 5:30 PM — Awards ceremony 6:00 PM — Event wrap-up & doors close 🚀 Technology & Venture Partners TBA 🧠 About Cognee Cognee is an open-source AI memory engine that transforms unstructured data into persistent, queryable memory. It enables AI agents to store, retrieve, and reason over information across time, making it possible to build more reliable, adaptive, and stateful AI systems. About Pebblebed Pebblebed is a technical early stage VC founded by Pam Vagata (cofounder of OpenAI, ran AI for Stripe, inventor of FBLearner Flow); Keith Adams (founded Facebook AI Research, was chief architect at Slack, 20th engineer at VMWare) and Tammie Siew (former Sequoia Southeast Asia investor, former Sequoia & Notable Capital backed founder)

**Lien de l'évènement :** [https://luma.com/event/evt-fxoG2NdzHtTFYrK](https://luma.com/event/evt-fxoG2NdzHtTFYrK)

### Pays
`#United States` 

### Continent
`#North America` 

**Médias associés :**
[Média 1](https://80954c1d.sibforms.com/serve/MUIFABojU8UBbDiX_TdcGa7Wv5VMoVB_nBZ92mkLkGlS1pJLpP7s-pVJusyN-7cG9KPrSuv3fv7TmXwuw_AoyNUShR8jZhmNDgUbZPJO2V5xYXlNz4YXOTjSb8X7Lj7PRIPzgzEWlLbA4f4uw_F8RM51EUsjSfQQko0qaby98GHMdYJVWLIXd5JzzaXBGmqN2CcYOFuqnbnaYEnw) 

## event_id
evt-fxoG2NdzHtTFYrK@events.lu.ma

### Outils
`#Cognee` 



---
### Navigation pour IA
- [Index de tous les contenus](https://ai-memory.io/llms.txt)
- [Plan du site (Sitemap)](https://ai-memory.io/sitemap.xml)
- [Retour à l'accueil](https://ai-memory.io/)