🔧 Agent Infrastructure
Google launched Gemini Spark, a 24/7 personal AI agent in the Gemini App that ta...
Google launched Gemini Spark, a 24/7 personal AI agent in the Gemini App that takes autonomous actions and integrates with Gmail, Google Docs, and Slides for workflow automation.
Forge is an open-source reliability layer that adds guardrails to local LLM tool...
Forge is an open-source reliability layer that adds guardrails to local LLM tool-calling, boosting an 8B model from 53% to 99% on multi-step agentic tasks without modifying the model itself.
'Code as Agent Harness' surveys how code has evolved from LLM output to the oper...
'Code as Agent Harness' surveys how code has evolved from LLM output to the operational substrate for agent reasoning, action execution, and environment modeling in agentic systems.
Argus is a deep research agent system using cooperative Searcher and Navigator a...
Argus is a deep research agent system using cooperative Searcher and Navigator agents to assemble complementary evidence pieces like a jigsaw, avoiding the diminishing returns of naive parallel search.
VeilGate is a deception reverse proxy aimed at detecting and deceiving AI pentes...
VeilGate is a deception reverse proxy aimed at detecting and deceiving AI pentest agents, developed by a practitioner who regularly finds critical vulnerabilities using LLM agent loops against production targets.
Google released an Agents API for building and running custom agents in sandboxe...
Google released an Agents API for building and running custom agents in sandboxed Linux environments; LlamaIndex built a template integrating it with LlamaParse for unstructured document processing.
Gemini 3.5 Flash demonstrated deploying multiple subagents to autonomously desig...
Gemini 3.5 Flash demonstrated deploying multiple subagents to autonomously design and build an entire virtual city, showcasing multi-agent orchestration capabilities.
Google Flow introduces an AI agent powered by Gemini Omni that acts as a creativ...
Google Flow introduces an AI agent powered by Gemini Omni that acts as a creative partner, reasoning through complex tasks to help users brainstorm, create, and edit content.
This paper introduces the stochastic-deterministic boundary (SDB) as a core arch...
This paper introduces the stochastic-deterministic boundary (SDB) as a core architectural primitive for production LLM agents and presents a catalog of six runtime patterns for agent coordination, state, and control.
GoogleDeepMind introduces new Antigravity interfaces including a mission control...
GoogleDeepMind introduces new Antigravity interfaces including a mission control UI for multi-agent collaboration, a CLI, and an SDK for programmatic AI integration.
ArizeAI open-sourced a coding agent tracing tool supporting Claude Code, Cursor,...
ArizeAI open-sourced a coding agent tracing tool supporting Claude Code, Cursor, Codex, and Gemini CLI that captures prompts, tool calls, shell commands, file edits, retries, and latency across full agent runs.
OpenAI launches Codex in the ChatGPT mobile app, enabling users to start tasks, ...
OpenAI launches Codex in the ChatGPT mobile app, enabling users to start tasks, review outputs, and steer agent execution remotely while Codex runs on a local machine.
APWA introduces a distributed multi-agent architecture that enables high-through...
APWA introduces a distributed multi-agent architecture that enables high-throughput parallel processing of complex agentic workloads, addressing coordination and scaling bottlenecks in LLM-based multi-agent systems.
MagicPath 2.0 launches as a multiplayer canvas enabling humans and AI coding age...
MagicPath 2.0 launches as a multiplayer canvas enabling humans and AI coding agents like Codex and Claude Code to collaboratively design and build functional prototypes in real time.
GoogleDeepMind expands the Antigravity developer ecosystem, aiming to reduce deb...
GoogleDeepMind expands the Antigravity developer ecosystem, aiming to reduce debugging overhead and let developers focus on architecture and design.
Arize AI highlights that agent failures in production most commonly stem from to...
Arize AI highlights that agent failures in production most commonly stem from tool selection errors, emphasizing the importance of tracing and debugging tool calls.
xAI announces SpaceX is trialing NVIDIA's Vera CPU, a processor purpose-built fo...
xAI announces SpaceX is trialing NVIDIA's Vera CPU, a processor purpose-built for agentic AI workloads, marking an early partnership milestone.
PopPy automatically uncovers parallelization opportunities in Python compound AI...
PopPy automatically uncovers parallelization opportunities in Python compound AI applications by optimizing around slow external ML model calls, reducing end-to-end latency without changing application code.
Reversa is a multi-agent reverse documentation engineering framework that conver...
Reversa is a multi-agent reverse documentation engineering framework that converts legacy codebases into traceable operational specifications to provide reliable context for AI coding agents.
InsForge (YC P26) is an open-source Apache 2.0 backend platform acting as a Hero...
InsForge (YC P26) is an open-source Apache 2.0 backend platform acting as a Heroku-like deployment and operations layer specifically designed for AI coding agents.
A developer built a shared persistent Linux workspace that gives multiple AI too...
A developer built a shared persistent Linux workspace that gives multiple AI tools (Claude, Claude Code, MCP-compatible agents) access to the same filesystem and knowledge base, solving the context-loss problem between sessions for ~$10/month.
Grok subscribers can now use their subscription within the Nous Research Hermes ...
Grok subscribers can now use their subscription within the Nous Research Hermes Agent, expanding Grok's integration into third-party agent frameworks.
Proposes paper.json, a lightweight JSON companion file for academic papers that ...
Proposes paper.json, a lightweight JSON companion file for academic papers that enables LLM agents to reliably extract sub-claims, scope boundaries, and reproducibility steps with stable IDs.
OpenAI is rolling out the Codex mobile app preview on iOS and Android globally, ...
OpenAI is rolling out the Codex mobile app preview on iOS and Android globally, with Windows phone-to-desktop support coming soon.
Perplexity AI's 'Computer' product now connects to Snowflake, enabling natural-l...
Perplexity AI's 'Computer' product now connects to Snowflake, enabling natural-language querying of live warehouse data with SQL, source tables, and metrics — functioning as an on-call data science assistant.
Arize AI discusses how AI agents and RAG pipelines consume documentation differe...
Arize AI discusses how AI agents and RAG pipelines consume documentation differently than humans—truncating and skipping content—and shares how they optimized their docs for agent readability.
Developer built a native macOS Markdown viewer using Tauri 2 where every line of...
Developer built a native macOS Markdown viewer using Tauri 2 where every line of code was written by AI coding agents, showcasing a fully agent-driven software development workflow.
xAI integrates Grok and X Premium subscriptions into the OpenClaw platform, enab...
xAI integrates Grok and X Premium subscriptions into the OpenClaw platform, enabling chat, image/video generation, and X post search within agent workflows.
Developer asks HN for recommendations on code intelligence MCP servers for AI co...
Developer asks HN for recommendations on code intelligence MCP servers for AI coding agents, noting the space is fragmented with no clear winner for semantic search and symbol lookup.
An agentic LLM-guided re-optimization framework allows end users to update opera...
An agentic LLM-guided re-optimization framework allows end users to update operations research models via natural language, dynamically selecting re-optimization techniques as conditions change.
Proposes the Oats Protocol, an open architecture pattern for standardized tool-c...
Proposes the Oats Protocol, an open architecture pattern for standardized tool-calling in local coding agents, addressing fragmentation between different LLM tool-calling approaches.
xAI's Hermes Agent now supports X Premium subscriptions and can search X posts, ...
xAI's Hermes Agent now supports X Premium subscriptions and can search X posts, expanding its real-time data access capabilities.
ArizeAI highlights key challenges of scaling multi-agent systems in production, ...
ArizeAI highlights key challenges of scaling multi-agent systems in production, including context loss during handoffs and excessive token consumption.
Langfuse introduces the 'AI Engineering Loop', a structured process the best AI ...
Langfuse introduces the 'AI Engineering Loop', a structured process the best AI teams use to ship complex AI systems to production, with a supporting academy series.
Langfuse launches Langfuse Academy, a free open educational resource covering th...
Langfuse launches Langfuse Academy, a free open educational resource covering the full AI engineering lifecycle including tracing, monitoring, evaluation, and experimentation.
A developer building a multi-agent FX trading analyst desk using 5 LLM agents se...
A developer building a multi-agent FX trading analyst desk using 5 LLM agents seeks advice on finding early users before MVP completion, highlighting trust challenges in fintech.
ArizeAI advocates for integrating agent tracing into regular engineering feedbac...
ArizeAI advocates for integrating agent tracing into regular engineering feedback loops to improve shared workflows, build reusable skills, and expand evaluation coverage for coding agents.
ArizeAI highlights how coding harness tracing enables teams to identify unnecess...
ArizeAI highlights how coding harness tracing enables teams to identify unnecessary tool calls, extract reusable workflows, and benchmark different coding agent and model combinations.
Smallcode is an AI coding agent optimized to run efficiently on small LLMs, targ...
Smallcode is an AI coding agent optimized to run efficiently on small LLMs, targeting resource-constrained environments.
AI agent harnesses like OpenClaw are reportedly influencing the design of LLMs, ...
AI agent harnesses like OpenClaw are reportedly influencing the design of LLMs, inference systems, and CPU architectures, though details are sparse.
Arize AI discusses how Cursor integrates AI observability into the developer wor...
Arize AI discusses how Cursor integrates AI observability into the developer workflow, highlighting the operational challenges at Cursor's scale.
Perplexity AI expands its Snowflake integration to support dashboard and automat...
Perplexity AI expands its Snowflake integration to support dashboard and automation building for pipeline analysis and customer segmentation, with admin-level access controls.
Retweet of Google Flow's announcement introducing an AI agent and Gemini Omni mo...
Retweet of Google Flow's announcement introducing an AI agent and Gemini Omni model for creative collaboration and content production.
xAI thanks SpaceX and Elon Musk for trying out the NVIDIA Vera CPU, a chip desig...
xAI thanks SpaceX and Elon Musk for trying out the NVIDIA Vera CPU, a chip designed for agentic AI.
A developer built OpenClaw, a minimalist self-hosted Telegram bot interfacing wi...
A developer built OpenClaw, a minimalist self-hosted Telegram bot interfacing with a Pi AI agent harness, supporting shell commands, cron tasking, and session switching from mobile.
Langfuse is hosting an in-person training session in San Francisco on May 26th c...
Langfuse is hosting an in-person training session in San Francisco on May 26th covering how to bring agents to production using Langfuse observability tools.
Retweet of NVIDIA thanking SpaceX and Elon Musk for trialing the Vera CPU built ...
Retweet of NVIDIA thanking SpaceX and Elon Musk for trialing the Vera CPU built for agentic AI.
Langfuse posted a brief informal message expressing enthusiasm for traces, likel...
Langfuse posted a brief informal message expressing enthusiasm for traces, likely referencing their tracing/observability product.
Langfuse shared a link with no accompanying text, providing minimal context abou...
Langfuse shared a link with no accompanying text, providing minimal context about the content.
Retweet of Langfuse's in-person SF training announcement for bringing agents to ...
Retweet of Langfuse's in-person SF training announcement for bringing agents to production using Langfuse.