Archive
Agent、MCP、coding agent、工作流自動化與評測。
最新模型
NVIDIA announced Nemotron 3.5 Super VL on October 15, offering BF16 and NVFP4 weights and combining text, image, and video understanding with tool calling. The company published throughput benchmarks for long-running agent tasks, though practical results still depend on hardware, cache reuse, and concurrency settings.
GitHub Repo
A report on October 15 found that Node.js SDK’s `toText()` may miss workflow text and append content moderation replacement messages to the original answer. The fix includes regression tests but has not been merged; an official release version is still unconfirmed.
最新模型
On October 15, PrismML unveiled the Qwen3.5-based Bonsai 2 2B, 4B, and 9B models under the Apache 2.0 license. The smallest packages sharply reduce file size, but visual modules, runtime memory, and agent capabilities still need to be assessed separately.
GitHub Repo
Hugging Face released Transformers 5.20.0 on October 15, adding quantization during export and distributed checkpoint improvements. The project also warned of a performance regression in expert parallel inference; deployments using legacy cache interfaces will need code changes.
GitHub Repo
A report from the Open WebUI community on October 15 says streaming replies rewrite the accumulated full text to Redis token by token, increasing transfer costs for long-running agent tasks. The report includes measurements using a simulated model and reproduction steps, but an official fix and the impact on production deployments remain unconfirmed.
GitHub Repo
NousResearch released Hermes Agent v0.22.2 on October 15, correcting a build that mistakenly included unreleased gateway code. The update also addresses false timeouts on long prompts with local models and gateway startup failures after reboot, though some sessions created by the previous release still cannot be deleted.
GitHub Repo
A Dify community report on October 14 said editing an Integration Trigger draft could immediately stop a published workflow from receiving events, without leaving failed execution records. A proposed fix includes two regression tests but has not been merged; effects on other integration triggers remain unverified.
GitHub Repo
A report posted on October 13 says Curator may approach the model context limit while consolidating a large skill library, then mark a truncated response as complete. Two draft fixes propose propagating failure states and reserving output space, but neither has been merged.
GitHub Repo
Community reports from October 13–14 indicate that receiving large tool responses over stdio in the MCP Python SDK can add substantial latency because of repeated buffer copies. Contributors have shared a minimal reproduction and before-and-after test results, but no official fix has been released.
GitHub Repo
REA released version 6.5.0 on October 14, allowing CLI and MCP users to specify JavaScript files for analysis and page through retained analysis evidence. The release separates source selection from summary output, but does not provide a performance comparison with full analysis.
GitHub Repo
Ollama released v0.40.5-rc0 on October 14, adding CUDA ports of three groups of MLX custom kernels and reducing fallback to computation graph operations. The author measured more than a twofold increase in prompt throughput for two Nemotron models on an RTX 6000 Ada, but results have yet to be validated across hardware and full workloads.
GitHub Repo
Noiz AI and the Hong Kong University of Science and Technology’s HelixWorld project released HelixBench on October 12, with 1,015 fixed test cases and evaluation code. The benchmark separately checks audio quality, audio-video synchronization, and spatial sound consistency. The public package does not include the source videos, so take care to follow the scoring protocol when reproducing results.