agent sdk
30 articles about agent sdk in AI news
Anthropic Reverses Claude Agent SDK Billing Overhaul Before Launch
Anthropic paused its June 15 billing overhaul for the Claude Agent SDK, keeping usage within regular subscription limits, amid a brewing price war with OpenAI and its own upcoming IPO.
ForeverSolar Uses Claude Agent SDK to Automate Solar Permitting, Cutting Approval Times
Solar installation company ForeverSolar is using Anthropic's Claude Agent SDK to automate permitting documentation, a major bottleneck in solar deployment. This represents a concrete enterprise application of agentic AI beyond software development.
Claude Agent SDK's a2a Tool Lets You Build Persistent, Observable AI Assistants
Use the a2a CLI tool to add persistent memory, skill management, and observability to your Claude Code projects, moving prototypes to production.
Anthropic Ejects Programmatic Claude Use From Pro Subscriptions
Anthropic gives Pro subscribers a $20 monthly credit for Agent SDK usage starting June 15, separating programmatic use from interactive subscription limits.
Anthropic Splits --print Into $100/Mo Credit, Torpedoes CLI Workarounds
Anthropic splits `claude --print` and Agent SDK usage into separate monthly credits. Pro gets $20/mo, Max gets $100-$200/mo. Credits don't roll over.
Anthropic's Accidental Code Release: Inside the Claude Code CLI That Wasn't Meant to Be Seen
Anthropic's Claude Agent SDK inadvertently includes the entire minified Claude Code CLI executable, revealing the inner workings of their AI coding assistant. The 13,800-line bundled JavaScript file contains everything from agent orchestration to UI rendering, raising questions about security and transparency in AI tooling.
Anthropic Tightens Security: OAuth Tokens Banned from Third-Party Tools in Major Policy Shift
Anthropic has implemented a significant security policy change, prohibiting the use of OAuth tokens and its Agent SDK in third-party tools. This move comes amid growing enterprise adoption and heightened security concerns in the AI industry.
social.plus Vise: Workflow Governance for AI Coding Agents Building SDK
social.plus launched Vise, a workflow governance platform for AI coding agents building SDK integrations, enforcing policy controls and audit trails.
Stop Writing SDK Docs for AI Agents: Build MCP Servers Instead
MCP servers replace SDKs for AI agents. Claude Code users should expose APIs as MCP servers so agents discover capabilities autonomously, not via docs. First sentence: BridgeXAPI argues MCP servers transform messaging APIs into discoverable execution infrastructure for Claude Code agents.
Cursor SDK Turns AI Agent Runtime into Programmable Infrastructure
Cursor is releasing an SDK that turns its agent runtime into programmable infrastructure for headless use in CI/CD pipelines, internal tools, and third-party products. Revenue scales with compute tokens, not seats, enabling higher volume without human-in-the-loop.
OpenAI Open-Sources Agents SDK, Supports 100+ LLMs
OpenAI has open-sourced its internal Agents SDK, a lightweight framework for building multi-agent systems. It features three core primitives, works with over 100 LLMs, and has gained 18.9k GitHub stars immediately.
OpenAI Agents SDK Gains Containerized Execution & Step Control
OpenAI has released new capabilities for its Agents SDK, including containerized execution and granular step control, giving developers more tools to build and manage long-running AI agents.
Symbolica's Agentica SDK Scores 36.08% on ARC-AGI-3, Claiming Cost-Effective Agentic Breakthrough
Symbolica's Agentica SDK reportedly achieved a 36.08% score on the new ARC-AGI-3 benchmark in one day, using an agentic approach claimed to be far cheaper than brute-forcing with a frontier model.
9-Line Agent: Cursor Beats Claude, OpenAI SDKs in Dev Build Test
A developer built the same agent in Cursor (9 lines), Claude Code (47 lines), and OpenAI Codex (31 lines). The gap is in tool orchestration architecture, not model capability.
Run Claude Code in Any Sandbox with One API: AgentBox SDK
Swap coding agents and sandbox providers without changing code. Preserves full interactive capabilities (approval flows, streaming).
C# SDK for MCP 2.0 Ships with Streaming, Native AOT Support
Microsoft's C# SDK for MCP 2.0 adds streaming, native AOT, and DI improvements for .NET AI agents, signaling enterprise adoption of the Anthropic-originated standard.
GitAgent Aims to Unify AI Agent Development with Git-Based Standard
GitAgent introduces an open specification that defines AI agents through files in a Git repository, enabling portability across frameworks like Claude Code, OpenAI Agents SDK, and CrewAI while leveraging Git's native version control and collaboration features.
AgentShare MCP Registry: Discover and List MCP Servers via agent.json and
AgentShare MCP Registry provides a curated, machine-readable directory via agent.json for Claude Code users. Agents can submit listings using x402 micropayments and track analytics.
4 Gemini API Managed Agent Features That Change How You Build Agentic
Gemini's `background: true` flag in the Interactions API lets you run agents asynchronously. Pair it with remote MCP servers to connect private data without custom proxies.
AWS Unveils Production Blueprint for Evaluating AI Agents with Strands and
AWS released Strands and AgentCore, a production blueprint for evaluating AI agents. It generates realistic scenarios and tracks metrics like completion rate and cost, addressing the gap between lab benchmarks and real-world performance—critical for retail AI deployments.
Native Acquires Frontline Research Group to Expand Agentic AI Platform
Native acquired Frontline Research Group to expand its agentic AI platform, integrating research capabilities for enterprise automation. This matters as agentic AI adoption accelerates across industries.
The One Decorator That Makes Your Script Agentic: @mcp.tool() vs. Subprocess
Wrap your Claude Code helper scripts in @mcp.tool() to expose typed, discoverable interfaces agents can reason about—the schema, not the AI call, is what makes it agentic.
Smartsheet Deploys Remote MCP Server on AWS for Agent Tool Access
Smartsheet deployed a remote MCP server on AWS ECS Fargate, enabling Claude agents to query and update sheets via standardized tool calls without a local client.
Harbor Adds LangSmith Sandbox Support, Making Agent Eval Backends Swappable
Harbor, an open-source agent-evaluation framework, now integrates LangSmith sandboxes. This allows users to run the same eval across multiple providers (Daytona, Modal, E2B, LangSmith) with a single flag change, eliminating per-provider setup tax.
Google DeepMind adds async agents, MCP support to Gemini API
Google DeepMind added background execution and MCP support to Gemini API Managed Agents. Four new features target developers building long-running, stateful agent workflows.
Google ADK Go 2.0 Adds Graph Engine, Human-in-Loop for Agents
Google released ADK Go 2.0 on July 2, 2026, adding a graph-based workflow engine and human-in-the-loop for multi-agent orchestration, targeting production reliability.
x402 Lets Agents Pay Per API Call — No Wallet Required
x402 lets AI agents pay per API call via USDC micropayments. The Stall now adds a fiat rail: buy credits with a card from $5/100 calls.
MCP Hits 10K Servers, 97M Monthly SDK Downloads by May 2026
Anthropic's MCP hit 10K+ servers and 97M monthly SDK downloads by May 2026, with all major AI vendors adopting it natively. Enterprise production adoption stands at 41%.
Claude Code's June 15 Agentic Credit Split: How to Avoid Hitting the $20 Wall
Claude Code's June 15 agentic credit split moves `claude -p` and CI workflows to a separate $20/month bucket on Pro. Upgrade to Max 5x or switch to direct API for production pipelines.
Dynamic Workflows: A New Agent Primitive Emerges
Dynamic workflows generate harnesses on the fly for agent orchestrators, enabling branching and verified tasks across coding agents like Claude Code and Codex.