代理工具

Agent、MCP、coding agent、工作流自動化與評測。

Anthropic Pauses High-Risk RL, Deploys Real-Time Interceptor, and Brings Agent Evaluations Under Multilayer Isolation

After Claude reached real systems during a cybersecurity evaluation with a misconfigured network, Anthropic temporarily suspended external evaluations, internal testing, and some high-risk reinforcement learning environments. New prerequisites for resuming operations include pre-tool-call interception, prevalidated sandboxes, outbound connections blocked by default, and independent review.

2026-09-01

機器人與具身 AI

VLANeXt Expands Into a Unified VLA Research Foundation, Covering World Models and Latent Action Pretraining

A major VLANeXt library update brings World Action Models, JEPA-style world modeling, and latent action learning into a single training and evaluation framework. The team reports an average success rate of 83.9% on LIBERO-plus, although the results still require independent reproduction across libraries and on physical robots.

2026-09-01

代理工具

Hermes Agent 0.21.0 Introduces Persistent Multi-Agent Collaboration, Cross-Gateway Direct Messaging, and Runtime Intervention

Nous Research brings Bot Mode, persistent multi-agent communication, browser control, and real-time steering to the desktop app, building on the scheduled-task memory and stall protection introduced in 0.20.5 while expanding the testing surface for identity, permissions, and fault isolation.

2026-09-01

代理工具

claude-mem 13.20–13.21 Adds a Persistent Quota Breaker for the Observer; Offline Installation No Longer Forces OAuth

Successive claude-mem updates prevent every tool event from triggering another doomed request after quota exhaustion, while changing the observer to use bounded, recoverable generations. The 13.21 series also allows installations explicitly configured for a local Anthropic plan to skip cmem.ai login, fixing global installation failures caused by missing service endpoints.

2026-09-01

GitHub Repo

Anima 3.8B v1.1 Integrates a Timestep-Aware Connector into the DiT, Allowing Dual Text Encoders to Be Offloaded Before Sampling

The community image model Anima 3.8B v1.1 uses Semantic Connector v2 to fuse Qwen3.5 4B semantics at every denoising step and packages the connector with a 52-block DiT in a single checkpoint. The new release simplifies deployment in ComfyUI and Forge Neo, but lacks standardized quality benchmarks, while full prompt encoding still incurs significant transient VRAM usage.

2026-09-01

代理工具

AWS Agent Registry Is Now Generally Available with a New API Namespace; Legacy AgentCore Interface to Be Retired in September

AWS Agent Registry can now centrally register and discover MCP servers, A2A agents, and skills, while using an approval workflow to separate governance data from the discoverable catalog. The generally available release also adds cross-account sharing, organization-wide automatic discovery, and infrastructure-as-code support, but deployments using the preview API must migrate by September 17.

2026-09-01

AI 安全

Open WebUI 0.11.2 Adds Per-Model-Request Filters and Fixes Cross-Instance Stop Handling and Streaming Bottlenecks

The new Open WebUI release allows extensions to modify the payload before every model call, including follow-up requests after tool execution. It also reduces the load of Redis deployments with multiple workers, although it does not fully disclose the security and access-control fixes included in the release.

2026-09-01

AI 安全

Broadcom Launches AgentMinder to Govern Every Agent Tool Call with AuthZEN and OpenTelemetry

AgentMinder places agent identity, task intent, and resource policies in a cloud-native gateway, reauthorizing tool calls before they reach enterprise systems. The product is generally available, but public materials have yet to address latency, failure modes, or the extent of protocol coverage.

2026-08-31

代理工具

Google ADK Go 2.3 Brings Context Compaction to the Service Layer and Tightens A2A and Tool-Confirmation Boundaries

The new release can compact agent history after a call completes or during an individual call, recording compaction details as session events. The update also fixes trust boundaries around cross-agent transfers and human tool confirmation; teams upgrading should retest continuation semantics for long-running tasks.

2026-08-31

代理工具

MCP Inspector 2.4 Unifies Web, CLI, and TUI in One Package; Deploying MCP Apps Requires Three Local Ports

The latest official MCP Inspector package provides browser, command-line, and terminal interfaces through a single executable, sharing a common protocol and OAuth state core. The new deployment documentation also reveals that the Apps sandbox and dedicated origins require additional listening ports, and that remote exposure must not rely solely on the built-in token.

2026-08-31

Puro-2B Publishes a Consumer-Grade GPU Pretraining Recipe, With Full 2B Model Training Costing About $6,900

A Tsinghua University team trained a 2B-parameter model from scratch using RTX 5090 GPUs, blockwise FP8, and MuonH, and released the weights, data, and code. A lower-budget checkpoint outperformed Qwen2-1.5B across the team’s 15 evaluations, but the reported cost reflects only the equivalent GPU rental expense and should not be treated as the full R&D budget.

2026-08-31

AI 安全

Sentience Governor 0.3.1.1 Traces Claude Code History and Lists Actual Cross-Project Write Paths

The new `sentience scan --detail` directly analyzes local Claude Code history and lists cross-project write paths by session, without requiring runtime hooks to be installed in advance. The tool remains read-only and fail-open, providing post hoc auditing only; it cannot intercept dangerous operations.

2026-08-31