Anthropic released a reference blueprint, "Commerce Agents," for building shopping and merchant agents on its Claude platform, featuring two fictional agents (a shopping agent for customers and a merc…
Anthropic's Claude Fable 5.1 API now rejects requests when prior conversation turns are modified, unless the `prefix_mismatch_behavior` is set to `"drop_block"`, a change enforced by default for new a…
Hypha's ablation study of its Agent Tools on a SQL retrieval eval, with 300+ runs and three trials per case, found that limiting tool output size and using progressive disclosure reduce latency and co…
Memory-MCP, a remote Model Context Protocol (MCP) server, provides a shared memory layer for AI agents, enabling multiple agents and teammates to store, search, and forget memories in multi-tenant spa…
A developer built AgentPostmortem, a public registry of AI-agent failure incidents, and Casebook MCP, a remote Model Context Protocol server that exposes the registry as tools any agent can call. The …
Iterathon's 2026 benchmark analysis finds that a single agent matches or outperforms multi-agent configurations on 64% of tasks at roughly half the cost, with multi-agent systems adding only 2.1 perce…
A developer reconstructed a blueprint for a personal AgentOS from Danny Postma's talk on building an agent control plane using Anthropic's Claude Agent SDK. The system automates coding and operational…
Anthropic has added optional usage credits for paid Claude plans, allowing Pro, Max 5x, and Max 20x subscribers to continue using Claude after hitting included session limits at standard API rates, wi…
Developerz AI has released Claude Task Master, an open-source orchestration system built on the Claude Agent SDK that automates end-to-end PR workflows. The tool handles planning, code changes, pull r…
Mnemara, a Claude conversation runtime that re-reads a role document on every turn and pins it as the system prompt, reported zero out-of-lane writes and zero protocol violations in a 101-turn coding …
Microsoft's Agent Harness and Foundry Hosted Agents reached general availability, completing the company's pivot from an agent-building library to a production runtime for governing agents. The releas…
Microsoft announced at Build 2026 the general availability of its Agent Harness and Foundry Hosted Agents, a production-ready runtime for AI agents. The company emphasizes that the harness infrastruct…
Lasso Security reported on August 3 that changing only the agent harness altered outcomes across a 1,000-attack autonomous red-team test. The two harnesses averaged similar objective success rates, ab…
Microsoft Agent Framework reached version 1.0 general availability on April 2, 2026, and at Build 2026 (June 2-3) the Agent Harness and Foundry Hosted Agents reached general availability, providing a …
Visual Studio Code now runs Anthropic's Claude as a first-party coding agent, reusing the Claude Agent SDK and running it in a dedicated Agent Host process, allowing a single GitHub Copilot subscripti…
Omnigent, an open-source framework, enables a policy-governed multi-agent financial research workflow that retrieves live USD-to-EUR exchange rates from the Frankfurter API, delegates drafting to a te…
Mutagent, an AI engineer that reads traces, diagnoses failures, and ships fixes on a loop, launched today in research preview as a free tool. The company reports that running it on an AI recruiting co…
Mutagent, an AI engineer that reads traces, finds failures, and ships fixes on a loop, is now live in research preview and free to try. In production tests, it reduced an AI recruiting company's month…
Nous Research's open-source Hermes Agent has surpassed 214,000 GitHub stars as of late July 2026, signaling strong developer adoption driven by its persistent memory, auto-generated skills, and model-…
Anthropic takes a model-first approach to AI agents, providing Claude as a reasoning engine alongside open-source components like the Model Context Protocol (MCP) and the Claude Agent SDK. Developers …