Hybrid RAG Chatbot New customer support system combines Qdrant's miniCOIL and LangGraph to deliver precise, context-aware responses through hybrid semantic and term-based matching. Check out the implementation guide! https://
medium.aiplanet.com/advanced-retri
eval-and-evaluation-hybrid-search-with-minicoil-using-qdrant-and-langgraph-6fbe5e514078
…
OPEN SOURCE
-

Hybrid RAG Chatbot with Qdrant miniCOIL and LangGraph
By
–
-

Lightweight Web Automation Agent Built with LangGraph
By
–
Agentic AI Browser A lightweight web automation agent built with LangGraph that achieves powerful automation through intelligent design and behavioral caching, proving that efficiency beats raw compute power. Check it out here https://
github.com/esinecan/agent
ic-ai-browser
… -
Modify Script to Use LM Studio or Ollama Provider
By
–
Yes, so you could take my script and legit modify one line of code to use @lmstudio or @ollama as a provider and use your favorite model with it.
-
Open-source demo app built with Hono on Cloudflare Workers
By
–
Like all of our demo apps, this one is open-source, so you can use it as a starting point for your own apps. This one was built with Hono, and is hosted on Cloudflare Workers. Repo:
-

Open Agent Platform: No-Code AI Agent Creation and Orchestration
By
–
Open Agent Platform Create and orchestrate AI agents through an intuitive, no-code interface. The platform features multi-agent supervision, RAG capabilities, and integrations with GitHub, Dropbox, and email – all powered by the LangChain + Arcade ecosystem. Watch the
-
Modular Memory: OpenAI Adoption Risk and Competitive Differentiation
By
–
OpenAI is unlikely to make a first move here in making memory modular, but plenty of incentives for others to lead this approach (eg to differentiate from OpenAI’s closed approach), and if successful can get OpenAI etc to adopt (kind of like MCP). IMPO
-
R1 Open Source Model Rivals o3 Mini Performance
By
–
Of course Sonnet is superior. To me, this new R1 is closer to the o3 Mini, which is pretty wild considering it’s open source.
-

DeepSeek Engineer v2 Released with Native Function Calling Support
By
–
DeepSeek Engineer v2 is here! 🐋
— Pietro Schirano (@skirano) 31 mai 2025
After trying the latest checkpoint for r1 and being super impressed, I decided to update the repo on GitHub, now with function calling, which is supported natively by the model.
"A rotating cube with the solar system inside, all in HTML" pic.twitter.com/DRTzgTOyYKDeepSeek Engineer v2 is here! After trying the latest checkpoint for r1 and being super impressed, I decided to update the repo on GitHub, now with function calling, which is supported natively by the model. "A rotating cube with the solar system inside, all in HTML"
-
Open Models Data Gap: Why Algorithms Aren’t Enough
By
–
every new model is a combination of two things, training algorithms and data open-source algorithms are up-to-date. the things that work are usually fairly simple but the data is complex, massive, gatekept, ever-changing. here open models are way behind, and probably hopeless
-

DeepSeek Adds Function Calling Support for Developers
By
–
They just added function calling support to the new DeepSeek. Before you had to use all sorts of tricks, of course I know them. But now it's supported!