Termsslug: agent-runtime

Agent Runtime

智能体运行时

Infrastructure layer responsible for agent scheduling, lifecycle management, and resource allocation.

Curated Intelligence

18 items · Page 1/2
AWS Machine Learning BlogT1·Agents
38 pts
AWS and Okta Scale Cross-App Access Governance for AI Agents

AWS published Part 2 of its series on governing AI agent access using Okta Cross App Access with Amazon Bedrock AgentCore. The post moves from Part 1's single-agent, two-MCP-server proof of concept to a topology that supports hundreds of agents and thousands of tools, shifting authorization checks out of individual MCP servers into a centralized gateway.

InfoQ 中文T2·Agents
22 pts
AICon Beijing Unveils Agent Engineering Track, Tencent to Share Dev Toolchain Rebuild

AICon Beijing will run Dec 18-19 with 13 tracks spanning agent engineering, inference optimization, and agent evaluation and safety. Tencent engineer Chen Siying will present an AI-native enterprise dev toolchain in the Agentic Software Engineering track, covering tool protocolization, agent runtime engineering, context engineering platforms, and a friction-signal feedback loop. The piece is primarily an agenda announcement without concrete technical parameters or verifiable results.

InfoQ 中文T2·Industry
38 pts
Tencent Cloud Unveils Agent Productivity Stack Spanning Office, Data and Runtime

At its 2026 Digital Ecosystem Summit, Tencent Cloud framed enterprise agent adoption as a connectivity problem and rolled out 40-plus product capabilities across office collaboration, enterprise data, permission governance and runtime infrastructure, including WorkBuddy Enterprise, ADP, AgentHosting, Agent Runtime and TokenHub. The announcement is a broad vendor showcase rather than a technical disclosure, with few concrete specs or verifiable benchmarks, so its value lies mainly in mapping Tencent's agent product portfolio.

Hacker News AIT2·Agents
78 pts
Octomind Launches: Open-Source Rust AI Agent Runtime with MCP Support

Octomind is released as a Rust-based, CLI-first AI coding agent runtime that grants LLMs real access to repositories via MCP tools for file operations and shell execution. It supports multiple modes including interactive, piped stdin, background daemons, and WebSocket, featuring built-in hooks and validators to replace manual approvals in autonomous workflows.

InfoQ 中文T2·Industry
45 pts
Tencent Cloud Upgrades MaaS to Shift Agents from API Calls to Task Delivery

Tencent Cloud announced a major upgrade to its MaaS product line at the Global Digital Ecosystem Conference, shifting focus from simple API calls to controllable task delivery via components like TokenHub, TI-ONE, and Agent Runtime. This move addresses enterprise challenges in multi-model scheduling, governance, and cost accounting, aiming to push AI applications into production environments.

IT之家 · 智能时代T2·Industry
48 pts
CITIC Securities Backs DeepSeek's Harness for Ecosystem Growth

CITIC Securities reports that DeepSeek's open-source agent runtime framework, Harness, is pivotal for its transition from model provider to platform ecosystem. The framework leverages plugin architecture and cross-agent collaboration to convert engineering advantages into commercial revenue and user stickiness.

宝玉 (@dotey)T2·Agents
78 pts
Nadella Proposes 'Insider Risk' Framework for AI Agents: Seven Principles Enforce External Permissions and Independent Audits

Microsoft CEO Satya Nadella published a manifesto treating AI models as high-privilege 'insiders,' advocating for the separation of intelligence provision from control. He outlined seven core security principles—including model diversity, full observability, and independent auditing—emphasizing that enterprises must implement externalized permission management rather than relying on vendor guarantees.