GitHub Repo

GitHub 熱門專案、開源工具、框架、runtime 與重要 release。

NemoClaw 0.0.114 Moves Read-Only MCP Calls Out of the Model Decision Path and Tightens Image and Installation Verification

NVIDIA has added deterministic read-only MCP calls to LangChain Deep Agents Code, allowing automated workflows to execute restricted tools without model involvement. The new release also pins container image digests, strengthens supply chain verification, and improves sensitive export cleanup, although “read-only” still depends on the accuracy of tool registration metadata.

2026-08-24

代理工具

AWS Open-Sources ADOP: A Multi-Agent Data Pipeline Generator That Runs Only Deterministic Artifacts in Production

ADOP uses about 15 agents to generate ETL, quality rules, a semantic layer, DAGs, and infrastructure configuration from natural-language specifications. It deliberately confines models to the development stage; production environments deploy only code that has passed human review and CI/CD validation.

2026-08-24

推論系統

llama.cpp 0.2.0 Separates Stable Releases from Nightly Builds, Finally Letting Package Maintainers Pin Compatible Versions

llama.cpp 0.2.0 officially introduces semantic versioning for slower-moving stable releases, while retaining the existing `b[number]` tags for development builds produced for nearly every commit. The new system reduces versioning risks for Debian, Homebrew, and downstream bindings, but “stable” does not mean long-term support or comprehensive validation across hardware platforms.

2026-08-24

WithEveryone Generates Group Portraits of Up to Ten People by Binding Identities to Layouts, but Weights Remain Unavailable

A team from Tencent Hunyuan and Fudan University has introduced WithEveryone, which first binds each reference person to a structured layout and then supervises generation using a regionalized identity loss. In the authors’ identity-disjoint evaluation, it improves subject coverage and reduces copy-and-paste artifacts, but the license of the existing base model prevents the team from releasing the research-version weights.

2026-08-24

GPT-5.6 Sol Temporarily Drops to $20 per Million Output Tokens, While Entire Requests With Ultra-Long Prompts Still Incur Higher Rates

OpenAI has cut GPT-5.6 Sol API input and output prices by 20% and 33%, respectively, with the promotional rates lasting at least through November 21. Once input exceeds 272K tokens, the higher rates still apply to the entire request, so long-context agent costs cannot be estimated from standard rates alone.

2026-08-24

代理工具

Cline SDK 0.0.78 Preserves Agent Work Through Event Replay; Unpinned Models May Switch to New Defaults

Cline has added draining, a persistent event log, and a run queue to the Hub, preventing agent work from being lost during upgrades or reconnections. The release also fixes a bug that silently removed all tools from custom OpenAI-compatible models, while catalog updates have changed the default models for some providers.

2026-08-24

AI 安全

Cloudflare API MCP Adopts Optional OAuth Scopes, Letting Agents Narrow Permissions to What Each Task Requires

Wrangler and Cloudflare API MCP Server now allow users to reject unnecessary scopes during authorization instead of requiring them to accept all requested permissions. Required scopes still cannot be deselected, and tool calls lacking the necessary scope can run only after reauthorization.

2026-08-24

推論系統

FreeToken Dynamically Allocates CPU, GPU, and PCIe Resources to Run a 35B MoE Model with 8GB of VRAM

Instead of using fixed offloading, FreeToken uses measured bandwidth to decide whether to transfer cache-missed experts to the GPU or execute them directly on the CPU. The paper also demonstrates a 753B model served by a single workstation GPU, but the full weights still require system memory; this should not be interpreted as “fitting all 753B parameters on one GPU.”

2026-08-23

AI 安全

Claude Code 2.1.239 Tightens Cloud Agent Egress and Fixes Bedrock Streaming Retries That Caused Double Billing

The new release forces some Claude Code web tool requests through the session network proxy and also fixes issues involving proxied environments, MCP reconnections, and sensitive input handling. It adds a Python SDK migration command, but Anthropic has not disclosed the vulnerabilities’ severity or the scale of impact.

2026-08-23

生成式視覺與 4D 重建

4DAnyone Releases Model and Inference Code, Expanding Monocular Human Videos into Up to 48 Reconstructed Views

The system uses a fixed-length reference context and view regrouping during diffusion to reduce structural drift when generating multiview videos in batches. The weights and inference pipeline are now public, but the fully open-source 4D Gaussian Splatting reconstruction and low-memory mode are not yet complete.

2026-08-23

代理工具

MCP’s New Roadmap Focuses on Agent Events, HTTP Transport, and Identity Security, but SDK Support for Tasks Remains Incomplete

The MCP maintainers are concentrating the next phase of specification work on five areas, including server-initiated events, agent identity, and progressive tool discovery. These items remain on the roadmap, while current SDK support for Tasks and extended notifications still has gaps.

2026-08-23

Marin Launches Open Training of a 535B-A23B Model, Publicly Trackable Across 11 GB200 NVL72 Systems

Marin has begun training a mixture-of-experts (MoE) model with 535B total parameters and approximately 23B active parameters per token. The project plans to use 11 GB200 NVL72 systems to process roughly 18T to 18.75T tokens. Configurations, scaling experiments, and real-time telemetry are public, but model quality, the long-context strategy, and the final token budget have yet to be finalized.

2026-08-23