A developer has published an MCP memory server that inverts the typical AI memory architecture: instead of letting a language model decide what to store, the model proposes claims with verbatim eviden…
Lettertrace, a new open-source tool released under the MIT License, lets companies self-host monitoring of how often AI assistants like Claude, ChatGPT, and Gemini mention their brand. The developer-f…
Lobu, a new backend platform, argues that the era of buying separate software for each business function is ending because AI agents built on event-driven loops can replace vertical SaaS. The company'…
Amazon Bedrock AgentCore Gateway now natively supports OAuth 2.0 Token Exchange (RFC 8693) to solve the confused deputy problem in multi-tenant generative AI agents, enabling on-behalf-of token exchan…
A new emerging standard called agents.json allows websites to declare their capabilities to AI agents by publishing a manifest file that describes tasks and flows, bridging the gap between OpenAPI end…
WebMCP is a new standard that extends the Model Context Protocol to the open web, allowing websites to expose callable actions for AI agents via a discovery document at `/.well-known/webmcp`. This ena…
A benchmark comparing context graphs, vector RAG, and raw context for agentic memory found that context graphs outperform alternatives on multi-hop retrieval tasks, where an agent must chain facts tha…
A company deploying Microsoft Copilot for its sales team discovered that the AI could generate emails offering discounts exceeding policy limits, such as a 25% discount when leadership caps discretion…
LanderMixer launches an AI-powered tool that generates personalized landing pages for sales prospects by analyzing LinkedIn profiles. The platform can process up to 500 prospects in parallel, creating…
A developer built a customer onboarding automation system using Nylas APIs that treats onboarding as a state machine driven by engagement signals. The system uses tracked welcome emails, self-service …
A developer has identified that long-term memory for LLM agents requires more than vector search and similarity retrieval, instead needing a system that handles persistence, fact extraction, temporal …
A developer built a 130-line Python library called `agent-redact` that automatically scrubs PII from Hermes agent audit logs before they are written to disk or shipped to external services. The librar…
Environment variables and connection references in Power Platform both enable managed solutions to be imported across Dev, Test, UAT, and Prod environments without developer edits, but they serve dist…
Enterprise AI projects often fail not because of poor model performance, but due to fragmented and disconnected data spread across multiple systems like CRM, billing, and support platforms. The core c…