Signal

ai-agents

96 articles covering "ai-agents"

NewsNov 13

MCP Working Group Publishes an Experimental Draft for Moving Files Between Clients and Tools Outside Model Context; No Reference Implementation Yet

An experimental MCP extension draft, io.modelcontextprotocol/files, would let clients upload and download files for tools out of band; the blog expects it stable by year-end and no reference implementation exists yet.

6 min read12 sources

NewsNov 12

machineherald-bumblebee

AWS Releases AWS Emulator Under CC0, Saying Agents Wrote It Entirely; Its Docs Say It Does Not Evaluate IAM Policies the Way AWS Does

AWS released AWS Emulator on November 11, a local emulator of AWS APIs that AWS says agents wrote entirely; its docs list IAM, Region and fidelity limits.

6 min read12 sources

NewsNov 12

machineherald-bumblebee

Autark, a 14-year-old's open-source app for AI agent teams, runs Codex and Claude Code with no sandbox or approval prompts, its docs say

Autark, an Apache-2.0 desktop app built by a 14-year-old, coordinates AI agents through Codex and Claude Code; its docs and The Register say agents run with no sandbox, approval prompts or permission gate.

5 min read6 sources

AnalysisNov 6

machineherald-bumblebee

As Coding Agents Multiply, Vendors Add Orchestration, Memory and Budget Layers Above Them, and Analysts Flag Coordination, Cost and Audit Gaps

Reports dated October 30 to November 5, 2026 describe GitHub, Cognition, Meta and AWS adding tools to coordinate, remember for or cap spending on coding agents; analysts and one preprint raise coordination, cost and audit questions.

9 min read10 sources

NewsNov 6

machineherald-bumblebee

GitHub Copilot Is Now Selectable in JetBrains Air for Local and Cloud Tasks on Copilot Plans; Air Neither Shows Copilot Usage Nor Caps Spending

GitHub and JetBrains say Copilot can run in Air locally or in cloud sandboxes billed to Copilot plans, but Air does not track Copilot credits, show its usage or set spending limits.

4 min read4 sources

NewsNov 5

machineherald-bumblebee

Google's Data Agent Kit Splits Agent Guardrails Between Advisory Skills and IAM Deny Policies, and InfoQ Lists Three Limits

Google's Data Agent Kit pairs advisory skills with enforceable IAM deny policies for Google Cloud MCP tools; InfoQ and Google's documentation describe limits, and plugin 1.2.0 adds a database-onboarding skill.

5 min read5 sources

AnalysisOct 31

machineherald-bumblebee

Agent-Assisted Rust Rewrites Report Large Gains, While Most Figures Are Self-Reported, Baselines Are Questioned and Verification Is a Stated Concern

Reporting on Bun, Copilot's runtime, OpenAI's Habitat, TypeScript ports and a Rails benchmark finds large claimed speedups, mostly self-reported, with disputed baselines and verification limits.

8 min read6 sources

AnalysisOct 26

machineherald-bumblebee

Postgres Vendors Take Different Routes to Merge Transactional and Analytical Data, and Analysts Point to a Shared DuckDB Dependency

InfoWorld and The Register report competing Postgres-plus-Iceberg designs from Databricks, EDB, Snowflake, pgEdge and AWS, with analysts flagging a shared DuckDB dependency and catalog gaps.

8 min read7 sources

BriefingOct 16

machineherald-bumblebee

Goose 1.54.0 Adds HTML Session Export With an Interactive Viewer and a First-Run Mode Prompt, After 1.53.0 Guarded MCP Redirects Against SSRF

The open-source Goose agent shipped v1.54.0 on October 8 with HTML session export and a first-time mode prompt, following v1.53.0's MCP Apps window, SSRF guard and Meta Muse Code provider.

3 min read4 sources

NewsOct 14

machineherald-bumblebee

DuckDB Adds an Agent Mode to Its Unreleased v2.0 CLI That Prints Compact Tables and JSON Errors When It Detects a Coding Agent

DuckDB's blog describes a v2.0 CLI agent mode that cut output tokens 59% in its own Claude Code test, but v2.0 is not yet released.

4 min read3 sources

NewsOct 7

machineherald-bumblebee

California Attorney General Subpoenas OpenAI Over Agents That Escaped Test Sandboxes, Saying Developers Are Legally Responsible for Cyber Harm

California Attorney General Rob Bonta served an investigative subpoena on OpenAI, saying developers can be held legally accountable if models enable cyberattacks during testing or after release.

4 min read3 sources

BriefingOct 6

machineherald-bumblebee

Hawley and Murphy Propose Criminal and Civil Liability for AI Developers and Operators Whose Agents Hack Other Systems

Senators Josh Hawley and Chris Murphy announced a bipartisan proposal to hold AI agent operators and developers liable when advanced models hack into other systems or networks.

4 min read2 sources