섹 retweeted
Setting up OpenClaw just went from 2 hours to 2 minutes 🤯
Emergent lets you deploy Clawdbot (MoltBot/OpenClaw) directly from your browser.
→ No Mac mini needed
→ No terminal
→ No API key exposure
It keeps everything sandboxed and away from your main machine.
섹 retweeted
Prompting GPT-5.2 Codex for long-running tasks:
섹 retweeted
Hidden AI Tools That Feel Like Superpowers.
1. claude.ai – Writing like a human
2. gamma.app – Presentation
3. Cleanup.app – Image cleaner
4. Brandmark.io – Logo maker
5. Notion.ai – Smart notes
6. Luma.ai – 3D capture
7. Snackprompt.com – Prompt ideas
8. Reface.ai – Face swap
9. Otter.ai – Voice notes
10. Krea.ai – Creative AI
11. Deepdreamgenerator.com – Art styles
12. Fireflies.ai – Meeting recorder
[ Bookmark for later 🔖 ]
섹 retweeted
🧠 OpenMemory: AI Memory Engine
An open-source memory system enhancing LLM apps through LangGraph integration. Features structured memory with 2-3× faster recall and 10× lower costs than hosted solutions.
Check it out 🔍
github.com/CaviraOSS/OpenMem…
섹 retweeted
The new Nano banana is like a Photoshop on steroids.
It lets you do INSANE things that weren't possible before.
Here are the 20 coolest examples I've found 🧵
섹 retweeted
Make your vibe coded apps look unique AF for the @boltdotnew Hackathon. No More Vanilla UIs.
🧵 Here's 11 ways to make your apps stand out:
섹 retweeted
PROMPT:
You are Lyra, a master-level AI prompt optimization specialist. Your mission: transform any user input into precision-crafted prompts that unlock AI's full potential across all platforms.
## THE 4-D METHODOLOGY
### 1. DECONSTRUCT
- Extract core intent, key entities, and context
- Identify output requirements and constraints
- Map what's provided vs. what's missing
### 2. DIAGNOSE
- Audit for clarity gaps and ambiguity
- Check specificity and completeness
- Assess structure and complexity needs
### 3. DEVELOP
- Select optimal techniques based on request type:
- **Creative** → Multi-perspective + tone emphasis
- **Technical** → Constraint-based + precision focus
- **Educational** → Few-shot examples + clear structure
- **Complex** → Chain-of-thought + systematic frameworks
- Assign appropriate AI role/expertise
- Enhance context and implement logical structure
### 4. DELIVER
- Construct optimized prompt
- Format based on complexity
- Provide implementation guidance
## OPTIMIZATION TECHNIQUES
**Foundation:** Role assignment, context layering, output specs, task decomposition
**Advanced:** Chain-of-thought, few-shot learning, multi-perspective analysis, constraint optimization
**Platform Notes:**
- **ChatGPT/GPT-4:** Structured sections, conversation starters
- **Claude:** Longer context, reasoning frameworks
- **Gemini:** Creative tasks, comparative analysis
- **Others:** Apply universal best practices
## OPERATING MODES
**DETAIL MODE:**
- Gather context with smart defaults
- Ask 2-3 targeted clarifying questions
- Provide comprehensive optimization
**BASIC MODE:**
- Quick fix primary issues
- Apply core techniques only
- Deliver ready-to-use prompt
## RESPONSE FORMATS
**Simple Requests:**
```
**Your Optimized Prompt:**
[Improved prompt]
**What Changed:** [Key improvements]
```
**Complex Requests:**
```
**Your Optimized Prompt:**
[Improved prompt]
**Key Improvements:**
• [Primary changes and benefits]
**Techniques Applied:** [Brief mention]
**Pro Tip:** [Usage guidance]
```
## WELCOME MESSAGE (REQUIRED)
When activated, display EXACTLY:
"Hello! I'm Lyra, your AI prompt optimizer. I transform vague requests into precise, effective prompts that deliver better results.
**What I need to know:**
- **Target AI:** ChatGPT, Claude, Gemini, or Other
- **Prompt Style:** DETAIL (I'll ask clarifying questions first) or BASIC (quick optimization)
**Examples:**
- "DETAIL using ChatGPT — Write me a marketing email"
- "BASIC using Claude — Help with my resume"
Just share your rough prompt and I'll handle the optimization!"
## PROCESSING FLOW
1. Auto-detect complexity:
- Simple tasks → BASIC mode
- Complex/professional → DETAIL mode
2. Inform user with override option
3. Execute chosen mode protocol
4. Deliver optimized prompt
**Memory Note:** Do not save any information from optimization sessions to memory.
섹 retweeted
🚀 Hello, Kimi K2! Open-Source Agentic Model!
🔹 1T total / 32B active MoE model
🔹 SOTA on SWE Bench Verified, Tau2 & AceBench among open models
🔹Strong in coding and agentic tasks
🐤 Multimodal & thought-mode not supported for now
With Kimi K2, advanced agentic intelligence is more open and accessible than ever. We can't wait to see what you build!
🔌 API is here: platform.moonshot.ai
- $0.15 / million input tokens (cache hit)
- $0.60 / million input tokens (cache miss)
- $2.50 / million output tokens
🔗 Tech blog: moonshotai.github.io/Kimi-K2…
🔗 Weights & code: huggingface.co/moonshotai
🔗 Github: github.com/MoonshotAI/Kimi-K…
Try it now at Kimi.ai or via API!
섹 retweeted
Introducing NotebookLlama - an open-source version of NotebookLM! 📓🦙
NotebookLlama is a full implementation of NotebookLM that includes all the capabilities that makes it so great for researchers+business users:
✅ Create a knowledge repository of documents. Has likely higher accuracy than NotebookLM since it’s using LlamaCloud under the hood for high-quality parsing/extraction over complex docs.
✅ Generate summaries and knowledge graph mind-maps 🤯
✅ Generate podcasts thanks to @ElevenLabs 🗣️
✅ Agentic chat with docs and view metrics with @opentelemetry
This all lives within an open-source repo so you can clone/modify at will to swap in your own components!
Huge shoutout to @itsclelia for leading this.
Repo: github.com/run-llama/noteboo…
LlamaCloud helps power the parsing/ingestion. You can always use your own stuff too, but in the meantime you can check out LlamaCloud here: cloud.llamaindex.ai/
🔍 Extracting the core knowledge from documents is a common problem for many people, from students to corporate employees - and many people have found @NotebookLM useful .
But what if you could have your own, fully open-source NotebookLM, running on your computer at any time you want?
That's exactly what we built at LlamaIndex: NotebookLlaMa, your smart assistant for your smartest tasks.
We built it on top of our very own LlamaCloud, with best-in-class agentic- and OCR-driven parsing to get the best out of your files, as well as highly intelligent extraction agents to find the most valuable knowledge across your documents, and accurate, fully-automated document ingestion, indexing and retrieval pipelines so that your knowledge is always only a question away!
And we're just getting started: we do not only provide you with a document chat, a summary of your document, the highlights of it and a detailed Q&A section, but we also create mind maps, leveraging the structured output capabilities of @OpenAI, and in-depth, podcast-like audio conversations, about your document employing @ElevenLabs text-to-speech models!
To cap it all, we also integrate with @opentelemetry giving you real-time insights on your workflows.
👀Curious to give it a try?
You can set it up from the GitHub repo: github.com/run-llama/noteboo…
And don't forget to explore our LlamaCloud services: cloud.llamaindex.ai
And learn more about it in our docs: docs.cloud.llamaindex.ai
섹 retweeted
We love this DeepSeek-based Perplexity clone from Karan Vaidya -- and it takes less than 100 lines of code to implement!
Check out the video below, or the code here:
github.com/ComposioHQ/compos…
Build your own DeepSeek based Perplexity!!
We built an AI Research Agent that can analyse and research topics, and then it creates a detailed report on Google Docs
- Deepseek analyses the topic
- Generates a list of questions
- Directs another model to research answers to these questions
- Report is generated on based on this research
Built with @composio @llama_index @GroqInc @ExaAILabs
Here's the code: dub.composio.dev/gR65na7
섹 retweeted
Memory is a key ingredient for autonomous agents, but most memory implementations are exceedingly simple.
Check out memary - a reference long-term memory implementation using knowledge graphs 🧠🕸️
1️⃣ Use LLMs to extract agent inputs/responses in a knowledge graph backed by @neo4j. This knowledge graph is also a tool that the agent can explicitly search over.
2️⃣ Stream incoming entities/timestamps into a memory module. Capture the timeline of interactions and extract themes
3️⃣ Rank the most popular entities in an entity store, and feed this into the agent context window.
Powered by core @llama_index abstractions around agents, tool use, indexing, KGs, and more.
This project is by @JulianSaks, Kevin Li, Seyeong Han et al. - make sure to check it out!
github.com/kingjulio8238/mem…
섹 retweeted
AI is taking over advertising.
ChatGPT 4o is on FLORA AI canvas now, you can edit image, let anyone wear any outfit, hold any product in video ads and..
use Topaz upscale to 4K
step by step tutorial:
섹 retweeted
ChatGPT-4o image gen is insane.
People can't stop finding new creative ways to use it.
10 wild examples + prompts & how to:
섹 retweeted
Goodbye Sora,
Stanford just dropped FramePack, and it's INSANE
13 Wild Examples so far (Don't miss the 5th one)
섹 retweeted
MCP is going viral.
AI agents can now talk to real tools & apps and actually get stuff done.
This changes everything.
10 wild examples:
섹 retweeted
We just pushed a massive update for MCP Servers to @tryhighlight:
- All new design for the on-screen assistant (type instantly!)
- Ability to @ mention MCP Servers in follow ups
- Native window controls
- New in-app registry design
- More! 👇
섹 retweeted
Microsoft open-sourced a no-code data analysis tool!
Introducing Data Formulator, an LLM-powered, no-code tool that transforms data in a snap and creates stunning visualizations using AI.
100% open source
섹 retweeted
MCP is going crazy viral right now🤯
AI apps can now instantly connect to any tool or live data.
USB-C moment for AI.
10 wild examples:






























