代理工具

Agent、MCP、coding agent、工作流自動化與評測。

OpenMAIC 1.0.2 Fixes DNS Rebinding and Cloud Metadata SSRF, Blocks Classroom Overwrites

OpenMAIC’s media proxy previously resolved DNS again after validating a domain, allowing an external hostname to point to an internal network at connection time; another path permitted access to an Alibaba Cloud metadata address. Version 1.0.2 now connects using a pinned resolution result and generates classroom IDs server-side, but the changes may affect deployments that access local models over CGNAT ranges used by Tailscale and similar services.

2026-09-15

代理工具

dbt Charts Rewrites Dashboards as YAML, Enabling AI Agents to Generate, Validate, and Version-Control Them

dbt Labs has released dbt Charts, replacing drag-and-drop BI editing with YAML, SQL, and Git while offering a CLI, workflow Skills, and an optional MCP server. The initial release still cannot query the dbt Semantic Layer directly, and sharing an environment with dbt v2 may cause package downgrades.

2026-09-15

AI 安全

MCP Tool Annotations Remain Too Limited to Support Transaction Safety, Study Catalogs Eight Types of Agentic External-Side-Effect Anomalies

A new study categorizes eight types of external-state anomalies caused by agent retries, parallel execution, and compensation, showing that a successful response from an individual tool does not guarantee consistency across the overall workflow. A survey of 98,291 MCP tools found that annotation fields are common but cannot express outcome confirmation, staged commits, compensation, or cross-call dependencies.

2026-09-15

代理工具

GitHub Copilot Auto Adds Three Routing Preferences, but Cost Mode May Still Choose Large Models for Complex Prompts

Copilot Auto now lets users adjust the weighting of cost, quality, and latency across three tiers—Efficiency, Balance, and Intelligence—but all three share the same model pool. Actual charges still depend on the model selected by the router and the number of tokens used; tier names are neither price caps nor guarantees of a specific model.

2026-09-15

代理工具

ElevenLabs Connects More Than 50 Media Models to Its Hosted MCP, Letting Agents Generate Complete Assets in a Single Session

The updated ElevenLabs MCP brings speech, transcription, dubbing, music, image, and video generation into a single OAuth connection. It streamlines cross-media agent workflows, but also places costly generation operations, workspace content, and agent-management permissions within the same trust boundary.

2026-09-15

Atria Dawn Preview Releases 744B MoE Weights, Trained for Long-Horizon Research Agents in Verifiable Environments

The Shanghai AI Laboratory has released Atria Dawn Preview, along with FP8 weights and inference recipes, positioning it as a full-loop agent capable of searching, coding, and running experiments. The organization claims the best reported results on five of 16 benchmarks, though model scale, test-time compute, and its in-house evaluation setup still limit comparability.

2026-09-15

代理工具

GitHub Agentic Workflows 0.89 Series Adds MCP Call Tracing and Narrows Workflow Credential Exposure

GitHub released 17 `gh-aw` versions in one week, enabling JSON logs to identify the server, tool, and timestamp for each MCP call. The latest patch also stops persistently storing `GITHUB_TOKEN` in the slash command router’s Git configuration, though the 0.89 series remains on a prerelease cadence.

2026-09-15

代理工具

Otis Unifies llama.cpp, Local Model Selection, and Agent Permissions in a Single Desktop and Terminal Interface

In a concentrated public promotion push on September 13–14, Otis recommends and downloads GGUF models based on the user’s hardware, then launches a local agent using its bundled llama.cpp. Offline mode requires no account, but search, PAIR clusters, and Fireworks inference operate across distinct data and trust boundaries.

2026-09-14

AI 安全

K-Bench Expands the Observability Surface for Machine Unlearning: A Leak-Free Final Answer Does Not Mean an Agent Has Truly Forgotten

K-Bench expands evaluation beyond a model’s final response to six agent channels, including reasoning, tool calls, and retrieval results. Experiments show that even when existing benchmarks report no leakage, deployed agents may still expose target data in 22% to 86% of queries.

2026-09-14

代理工具

macOS 27’s Private Inference Interface Can Replace Siri’s Planning Model, but It Is Not Yet a Third-Party API

Reverse-engineering experiments show that macOS 27’s `Inference Providing` path can pass Siri’s planning prompts, tool definitions, and execution results to an external model. The demo requires disabling system protections and using a private Apple entitlement, so it should not be interpreted as meaning users can now officially replace Siri’s model.

2026-09-14

推論系統

llama.cpp Mainline Adds Maple 20B-A1B Ternary MoE, With Initial Support Targeting CPUs

Architecture support merged on September 14 allows Maple-Preview to be loaded and converted without relying on DeepGrove’s llama.cpp fork. The model activates only about 1 billion parameters per token, but GPU backends, quality evaluations, and official speed claims still require separate verification.

2026-09-14

代理工具

Study Reveals Referential Drift in Multi-Model Review Pipelines: Validators May Misclassify Correct Rollbacks as Errors

New experiments show that relative terms such as `previous` in “draft–validate–revise” pipelines may change referents as model roles shift. Increasing reasoning effort can dramatically improve some models, but model selection matters more than simply adding test-time compute.

2026-09-14