A Flutter and AI engineer released BrAIn, an open-source framework that uses a NATS pub/sub bus with reactive nodes instead of a chat loop for AI agents. The system allows nodes to have their own inte…
Moss launches a semantic search engine with sub-10 ms retrieval latency, eliminating the need for vector databases and enabling real-time AI applications in browser, edge, device, or cloud environment…
LlamaIndex released legal-kb, an open-source reference application demonstrating agentic retrieval over legal documents using Index v2. The app provides an agent with filesystem-style tools—retrieve, …
Ably released AI Transport v0.4.0, adding optional database hydration support for storing and reconciling AI conversation history. The feature allows developers to persist completed runs to an externa…
HTTP streaming (SSE) lacks built-in session recovery, causing AI chat streams to break on page refresh, network drop, or device change. The Vercel AI SDK's Redis-backed replay handles page-reload resu…
Gusto CTO Eddie Kim and a team of four built a new AI product, Gusto Cofounder, from scratch in 10 weeks using Claude Code and a radical process that eliminated Figma, Jira, and documentation. The tea…
Search SDK launches a unified TypeScript SDK for integrating web search into AI agents, supporting multiple providers like Firecrawl, Tavily, Exa, Brave, and Serper with a single API. The SDK provides…
A developer published a side-by-side comparison of 15 AI agent frameworks, filtering by use case (RAG, multi-agent, structured output) and language (Python, TypeScript, .NET), updated weekly. The comp…
A developer built four domain-specific AI chatbots—JazzQuery, RennQuery, WristQuery, and Celiac vs Me—using a shared architecture with Claude Code and curated knowledge bases to keep costs low and ans…
Vercel AI SDK's useChat hook lacks a session layer for multi-device sync, multi-user conversations, and resumable streams. Ably AI Transport replaces the default transport to add these features, enabl…
Developers using the Vercel AI SDK are discovering that calling chat.stop() only closes the client connection, not the server-side generation, leading to continued billing. Fixing this requires a dedi…
GluonDB has developed a method to securely serve a large fleet of persistent agents on a small infrastructure footprint by decoupling orchestration, filesystem, and sandboxed execution. The company ar…
Lelu, an authorization engine for AI agents, detects prompt injection and low-confidence decisions to gate agent actions, offering four outcomes: allow, human review, compute (sandbox), or deny. The o…
Ably and Vercel released Wayfarer, an open-source demo of a collaborative AI travel-planning app that uses a durable session to synchronize real-time agent streams, shared state, and multi-user presen…
A developer outlines the repetitive infrastructure—auth, billing, AI features, and deployment—required for every AI SaaS product, arguing that the real challenge is turning an AI API call into a monet…
LangChain agents built on LangGraph use a tool-calling loop until a final answer is returned. The high-level createAgent function accepts a model, tools defined with tool(), and an optional system pro…
Developer Salim Assili is building AI CostGuard, a local-first TypeScript/Node.js runtime safety layer that blocks costly AI agent calls before they reach provider APIs. The tool addresses failure mod…
LangChain.js provides a standardized framework for building LLM applications in TypeScript and Node.js, enabling developers to compose prompts, models, tools, and retrievers into reusable pipelines an…
Sanity launched three major updates in June 2026: a deploy_studio command in the Sanity MCP for one-click Studio deployment from AI tools, Sanity Context for building user-aware agents, and Content Ag…
SigNoz has released a guide for setting up OpenTelemetry-based observability and monitoring for the Vercel AI SDK, enabling developers to trace AI function calls, request durations, and custom metadat…