If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs.Avi Chawla (@_avichawla):Pytest for LLM Apps is finally here!DeepEval turns LLM evals into a two-line test suite to help you identify the best models, prompts, and architecture for AI workflows (including MCPs).Works with all frameworks like LlamaIndex, CrewAI, etc.100% open-source with 11k stars! https://t.co/Xayu1aFGFV ...

Hugging Face co-founder Thomas Wolf joins TechCrunch Disrupt 2025 to share how open-source and moonshot projects are shaping AI. Register now to save. https://t.co/boxacnqqj0 ...

Technology Advancement - MCP servers are now capable of delivering UI-rich experiences, a feature previously unavailable in Claude/Cursor [1] - The new mcp-ui allows for the addition of interactive web components, enhancing the output rendered by the MCP client [1] - The solution is 100% open-source [1]

Build human-like memory for your Agents (open-source)!Every agentic and RAG system struggles with real-time knowledge updates and fast data retrieval.Zep solves these issues with its continuously evolving and temporally-aware Knowledge Graph.Like humans, Zep organizes an Agent's memories into episodes, extracts entities and their relationships from these episodes, and stores them in a knowledge graph:(refer to the image below as you read)1) Episode Subgraph: Captures raw data with timestamps, retaining ever ...

Conversational LLM Evaluation - DeepEval enables evaluation of conversational LLM applications like ChatGPT in three steps [1] - Unlike single-turn tasks, conversational LLMs require consistent, compliant, and context-aware behavior across multiple messages [1] DeepEval Features - DeepEval allows defining multi-turn test cases as ConversationalTestCase [1] - DeepEval allows defining metrics with ConversationalGEval in plain English [1] - DeepEval provides a detailed breakdown of conversation success/failure and a score distribution [2] - DeepEval offers a full UI to inspect individual turns [2] Open-Source Aspects - DeepEval is 100% open-source with approximately 10 thousand stars [2] - DeepEval can be self-hosted, ensuring data privacy [2]

Evaluate conversational LLM apps like ChatGPT in 3 steps (open-source).Unlike single-turn tasks, conversations unfold over multiple messages.This means that the LLM's behavior must be consistent, compliant, and context-aware across turns, not just accurate in one-shot output.In DeepEval, you can do that with just 3 steps:1) Define your multi-turn test case as a ConversationalTestCase.2) Define a metric with ConversationalGEval in plain English.3) Run the evaluation.Done!This will provide a detailed breakdow ...

Product Overview - Motia is presented as a unified system for AI agents, integrating APIs, background jobs, events, and agents as plug-and-play steps [1] - The system is 100% open-source [2] Technical Features - Supports Python, JS & TypeScript in the same workflow [2] - Includes built-in observability [2] - Offers one-click deployment [2]

Key Features of MCP Server - MongoDB released an open-source MCP Server enabling AI tools to interact directly with MongoDB deployments [1] - The MCP server allows users to write production-grade queries using natural language [1] - It eliminates the need for manual queries or memorizing syntax [1] Functionality and Use Cases - Users can perform tasks like "Show me the most active users," "Create a new database user with read-only access," and "What's the schema for my orders collection?" using natural language [1] - The Agent handles the execution of these tasks [1] Platform Compatibility - The MCP server is compatible with Atlas, Community Edition, and Enterprise Advanced [1]

SGLang Overview - SGLang is an open-source, high-performance serving framework for large language models (LLMs) and large vision models (VLMs) [5] - SGLang supports day zero releases for new models from labs like Quen and DeepSeek, and has a strong open-source community [7] - The project has grown rapidly, from a research paper in December 2023 to nearly 15,000 GitHub stars in 18 months [9] Usage and Adoption - Base 10 uses SGLang as part of its inference stack for various models [8] - SGLang is also used by XAI for their Glock models, inference providers, cloud providers, research labs, universities, and product companies like Koser [8] Performance Optimization - SGLang's performance can be optimized using flags and configuration options, such as CUDA graph settings [20] - Eagle 3, a speculative decoding algorithm, can be used to improve performance by increasing the token acceptance rate [28][42][43] - The default CUDA graph max batch size on L4 GPUs is eight, but it can be adjusted to improve performance [31][36] Community and Contribution - The SGLang community is active and welcomes contributions [7][54] - Developers can get involved by starring the project on GitHub, filing issues, joining the Slack channel, and contributing to the codebase [9][54][55] - The codebase includes the SGLang runtime, a domain-specific front-end language, and a set of optimized kernels [58]

Agentic Apps Development - AG-UI protocol simplifies front-end Agentic app development, making it 10x easier [1] - AG-UI is becoming the standard for apps where Agents are part of the interface [1] Agent Communication Protocols - MCP connects agents to tools [1] - A2A connects agents to other agents [1]