#LLMInfra
We're excited to roll out a packed update over ~15 releases focused on real-time, incremental data processing — all with developers in mind at @cocoindex.bsky.social . Here's what's new 🎉

#Opensource #buildinpublic #AIInfra #DataEngineering #LLMInfra #PythonDev #DataInfrastructure #LLM #GitHub
June 3, 2025 at 6:12 AM
🚀 Introducing CocoInsight - Make your AI data pipeline exceptionally easy to understand — step-by-step.

🌟Works with CocoIndex: github.com/cocoindex-io...
🎉Now live: youtube.com/watch?v=MMrp...

#AI #DataEngineering #LLM #RAG #OpenSource #VibeCoding #AIInfrastructure #MLOps
#LLMInfra #CocoIndex
June 26, 2025 at 8:03 AM
Want your AI agent to act with purpose — not panic?

Hivemind CEO @eschmiegelow.bsky.social
shares what actually works:
The Dos and Don’ts of Event-Driven Agentic AI
🗓 June 25 · Data Night Londond · Cloudflare Office

More: lu.ma/jbw4a35m
#AgenticAI #DataInfra #LLMInfra #DataNightLondon
June 24, 2025 at 8:47 AM
🤔 Building LLM-native apps is exciting, but exposing internal APIs securely and quickly? Not so much!

That’s why we built Micepe:
🔧 Zero-code #MCP server
⚡ Translate REST, #gRPC, #GraphQL

We shared the full story of why we built it:
🧠 micepeio.medium.com/why-micepe-d...

#LLMInfra #LLMApps
August 19, 2025 at 2:31 PM
Unify your LLM stack.

LiteLLM is a drop-in proxy for OpenAI-compatible APIs that supports Anthropic, Mistral, Groq, and more—complete with tracing, caching, rate-limiting, and observability.

www.litellm.ai

#LLMInfra #AIEngineering #OpenSourceAI
LiteLLM
LLM Gateway (OpenAI Proxy) to manage authentication, loadbalancing, and spend tracking across 100+ LLMs. All in the OpenAI format.
www.litellm.ai
May 16, 2025 at 1:12 PM
LLMs need more than prompts—they need access.

On May 22 at 12PM EDT, we’re hosting a live webinar to show how Model Context Protocol (MCP) connects Claude, OpenAI & Gemini to your actual business tools.

RSVP here 👉 www.linkedin.com/eve...

#MCP #Webinar #LLMInfra #OpenSource #EnterpriseAI
MCP WEBINAR | LinkedIn
Welcome to the MCP Webinar! The Model Context Protocol (MCP) is a new open-source standard that enables secure, two-way connections between your data sources and AI assistants. Connect tools like Claude, and soon Gemini and OpenAI, to your content repositories, business tools, and development environments—giving your AI assistants the context they need for more relevant responses and the ability for LLM to access your tools directly. MCP simplifies integration by replacing fragmented connectors with a universal protocol. Learn how to implement pre-built servers for systems like Google Drive, Slack, GitHub, and more. In this webinar, experienced architects will share practical implementation strategies and help you navigate common challenges they've encountered while working with this emerging technology. Don't miss out on this opportunity to level up your web development knowledge. Register now and secure your virtual seat!
www.linkedin.com
May 20, 2025 at 1:00 PM
Harper now has an officially listed MCP server.

Unlike others, our MCP runs in-process with the database — no external fetches, no I/O lag. You get lower latency, higher throughput, and a simpler architecture.

See the announcement: buff.ly/rDq6ble

#MCP #LLMInfra
July 2, 2025 at 2:25 PM
🧠 Working on a layered stack:

🔗 DLT for data trust

🧭 Cognee for semantic retrieval

🐥 DuckDB for fast analytics

🌳 Neo4j + Kùzu for graph navigation
Data isn't just stored—it's understood.

#DLT #GraphDB #LLMInfra #LLMZoomcamp
July 18, 2025 at 8:36 AM
Remote MCP servers are coming—and fast. But with great flexibility comes… a lot of complexity.
🧵 Let’s unpack why this shift is inevitable—but not easy 👇
#AI #AgenticAI #MCP #LLMInfra
May 19, 2025 at 9:32 PM
Model Context Protocol (MCP) support is now available in Beta — for smarter collaboration between tools, more consistent logic across tasks, & deeply personalized outputs at scale.

Log in now and give it a try!

#AI #MCP #ModelContextProtocol #PromptEngineering #LLMInfra #AIOrchestration #Prompteus
May 2, 2025 at 3:40 PM