LangChain has launched SmithDB, a dedicated data layer designed to handle agents' complex trace data.
LangChain Deep Agents v0.6 delivers performance and cost optimization with a code interpreter and delta channels
Claude now provides separate monthly credits for the Agent SDK and `claude -p`.
Explicitly stating source boundaries was needed for LLMs to distinguish text usable as grounds for an answer.
mimalloc is an open-source allocator that serves as a drop-in replacement for malloc/free, optimized for large-scale multithreading.
Anthropic unveiled **Claude for Small Business**, expanding automation for small business operations.
Resemble AI has released DramaBox, a voice synthesis model based on LTX 2.3.
Airbnb has unveiled Viaduct 1.0, turning an internal tool into a community project.
Ardent launched to create Postgres replicas in seconds so AI coding agents can safely test against production data.
Before launching on GameLift Servers, teams need to prepare limit increases, load testing, and Blue/Green deployment.
Cline has released the Cline SDK, a plugin-based open-source agent runtime.
This article summarizes server testing, session, and observability standards to review before adopting Amazon GameLift Servers.
SenseNova has released U1 A3B, a multimodal model based on NEO-unify.
Microsoft has unveiled GridSFM, which predicts grid AC-OPF in milliseconds.
A summary of 10 open-source roguelikes that survived through community forks and maintenance.
Sipeed unveiled the K3 RISC-V SBC series, touting 60 TOPS and 30B LLM operation.
TextExpander has launched an MCP server that lets Claude directly read and edit users' snippet libraries.
This summarizes major AI industry trends including AI supply chain security, capital concentration, regulatory pressure, and bioweapon design risks.
You can integrate Claude Code with Ollama models via the open-source LLM router Manifest to reduce costs.
An open-source MCP tool has been released that lets AI agents directly control the desktop by leveraging the OS's accessibility layer.
A claim that complexity theory proves the impossibility of human-level performance based on ML has been refuted.
A ransomware breach at Foxconn reportedly exposed Apple and Nvidia design documents along with AI data center topology.
A tool has been released that removes duplicate data within LLM context to increase effective token capacity.
PullMD v2.4.1 has been released, natively supporting claude.ai web custom connectors.