Archive
GitHub 熱門專案、開源工具、框架、runtime 與重要 release。
代理工具
Agno 3.0.6 introduces stateless MCP transport, allowing any replica to handle requests without session affinity. The framework also adds protocol version negotiation and a Server Card, but retains the legacy session-based mode as the default for compatibility with existing deployments.
向量資料庫與 AI 基礎設施
Qdrant 1.19.1 adds prefetching and batched SIMD to TurboQuant scoring while reducing extra allocations in HNSW search and the query plane. The release also strengthens fault recovery for shard transfers, but Qdrant has yet to publish comprehensive performance comparisons across different processors and datasets.
推論系統
Uno attaches lightweight diffusion weights to an autoregressive LLM, then uses Ψ-Spec to propose multiple tokens at once while preserving the original model’s sampling distribution. The authors report speedups of up to 3×, though the current figures are limited to the research team’s specific models, hardware, and inference engine.
GitHub Repo
The new release adds Parity-aware BPE, enabling tokenizers to prioritize improving the language with the worst compression at each merge instead of merely pursuing the highest overall frequency. The feature can be used to train new vocabularies, but it does not automatically reduce Chinese token costs in existing models.
代理工具
New research turns source code, documentation, and tests into operational knowledge that can be loaded on demand, delivering gains across four research benchmarks with the same underlying model and agent framework. Skill-building costs are accounted for separately, however, and the results remain the authors’ own evaluation, so they should not be treated as evidence that skills can replace model training at low cost.
代理工具
The Claude Platform CLI adds `ant apply`, which synchronizes managed agent resources from Markdown, YAML, or JSON files in a repository. It provides previews, dependency ordering, and drift detection, but its state file still contains organization identifiers, and it currently manages only the Anthropic platform.
AI 安全
The open-source AI penetration testing tool Shannon 3.0 adds multi-stage code analysis, candidate vulnerability reconciliation, and native SARIF support. The new version triggers pipeline gates only for successfully reproduced vulnerabilities, but it can modify the target’s state, and 2.x workspaces cannot be resumed.
最新模型
Ant Group’s inclusionAI has released LLaDA-Image weights and Diffusers inference code. A single model handles text-to-image generation, reference-image editing, and Chinese and English text rendering. The distilled version uses Twin-DMD to reduce the recommended sampling process from 50 steps to 4, but training code and independent performance validation are still unavailable.
推論系統
The new open-source inference server Magnitude benchmarks hardware before recommending a complete combination of model, quantization, context length, and estimated speed. It automates the memory and concurrency settings most often misconfigured for local agents, though performance and model quality currently still depend largely on the project’s catalog and testing.
最新模型
Puffin-World uses a nine-channel Omni-Camera condition to unify absolute physical orientation with relative camera motion, while handling understanding, generation, and 3D reconstruction within a single architecture. The code, weights, and Puffin-16M dataset have been released, but its physical state modeling is currently focused mainly on gravity and latitude in static scenes.
代理工具
Hugging Face has open-sourced Funes, which writes turn-by-turn logs from Claude Code, Codex, pi, and Hermes into a single Lance dataset. Retrieval and reranking run locally by default, but cross-machine synchronization, residual secrets, and prompt injection through external memory still require user-managed safeguards.
最新模型
Hcompany has open-sourced the 260M- and 800M-parameter NeoMME models, which process text tokens and raw image patches with the same encoder instead of attaching a vision tower or causal decoder. Its retrieval variants produce both dense and late-interaction representations, although the current efficiency and accuracy figures come primarily from evaluations conducted by the authors.