AI Agents news and analysis on Web Pulse: 12406 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A developer's memory engineering system for AI assistants uses a promotion lifecycle with explicit rejection rules, treating memory like code review. The system, documented in 'ai-assistant-dot-files', requires human app…
A debate in AI agent development argues that MCP servers are unnecessary for single-user tasks, where simple 'skills'—folders of instructions and scripts—suffice. Skills run in the user's own context with existing creden…
A developer deployed a coding agent that scored 94% on an industry benchmark but failed in production on the first real edge case because the benchmark measured single-turn success while actual work required multi-turn r…
CodeRabbit launched its AI agent on Discord, offering open source maintainers a free tool to automate repetitive tasks like answering setup questions, triaging bug reports, and drafting fixes. The agent, already used by …
A security researcher demonstrated a prompt injection attack on Anthropic's Claude Code using the Fable-5 model, achieving remote code execution (RCE) 4 out of 10 times by tricking the agent into downloading and executin…
A researcher used Anthropic's Claude Code agent to implement puzzle solvers for two Kaggle competitions, IHES Picture Cube and Megaminx, reformulating them as Cayley graph searches. The agent wrote training scripts, beam…
Cockroach Labs partner solutions architect Amine El Kouhen explains how DBOS embeds durable execution directly into applications as a library, using CockroachDB to persist workflow state and recover from failures without…
Developer Emile Silvis compared two approaches to building a Plants vs Zombies clone with LLMs: a highly controlled agent that grilled him on specs versus an autonomous agent given only a creative goal. The autonomous ve…
Hermes Agent now supports a headless server setup with remote desktop access, requiring two server processes (serve backend and gateway) and a single client connection. The architecture separates the API/dashboard from m…
The U.S. Department of Commerce cleared OpenAI for a broad public rollout of its GPT-5.6 model family (Sol, Terra, Luna) on July 9, 2026, marking the first time a frontier AI model was released on the government's schedu…
A developer built an AI agent with a memory architecture that runs preflight instructions, retrieving relevant skills from a library of ~90 workflow files before executing tasks. The system uses a local 35B model for 80%…
A developer benchmarked 14 AI agent models and found that the true cost of a simple greeting like "Hi" is not the token price (as low as $0.005) but the waiting time, which can cost up to $5.10 per greeting at an average…
The rise of AI agents in 2025 has driven the need for agentic orchestration, a structured execution framework that combines the flexibility of autonomous agents with deterministic workflow engines to ensure auditable, go…
A new integration pattern called 'code mode' over the Model Context Protocol (MCP) is emerging, where agents execute small programs via a single MCP tool instead of making many individual tool calls. This approach reduce…
Eve now supports Chat SDK adapters, enabling a single agent to connect to Facebook Messenger, WhatsApp, Resend, Liveblocks, and other surfaces. The new Chat SDK channel mounts webhook routes, shows typing indicators, han…
A developer created a Context Engineering Framework that treats the AI context window as a budget rather than a junk drawer. The framework, hosted in the ai-assistant-dot-files repo, defines canonical agents, skills, and…
CyrusNewDay launched a CLI tool called 'social' that lets AI agents interact with LinkedIn and X accounts via JSON commands, with caching and local mirroring to reduce costs. The tool is designed for agent-first usage, s…
A developer built MarketNow, a marketplace that security-audits every MCP server before listing, after 30 CVEs were filed against MCP servers in 60 days. The audit pipeline, Sentinel, includes static analysis, behavioral…
A developer building MarketNow, a marketplace for MCP servers, shares findings from auditing 8,764 MCP servers using gVisor for sandboxing. They found that about 50% of MCP servers fail to start under gVisor due to unsup…
Perplexity has developed an internal AI coding tool codenamed Teammate, designed for long-horizon engineering tasks such as owning projects and monitoring services, which company engineers have used since May. The tool i…