Nightshade

Notte is a browser framework and platform for building and running AI agents, providing tools to simplify web-based LLM tasks, handle CAPTCHAs, and offer developer tooling for agent development and deployment.

Nsight Systems is an NVIDIA performance-analysis tool used to inspect engine processes and GPU work when investigating performance issues. In the cited use, it supports tracing and examining the interaction between inference-engine processes and GPU activity.

Heretic is a command-line tool for automatically removing safety alignment from transformer-based language models without post-training. It combines directional ablation (abliteration) with a Tree-structured Parzen Estimator optimizer powered by Optuna, co-minimizing refusal counts and KL divergence from the original model to select ablation parameters automatically. For supported transformer components, currently attention output projections and MLP down-projections, Heretic computes per-layer residual directions from the difference between first-token hidden states for harmful and harmless prompts, then orthogonalizes the associated weight matrices against those directions. Its optimizer can interpolate between residual directions and select separate, flexible layer-weight kernels for different components. The tool supports most dense models, many multimodal models, several mixture-of-experts architectures, and some hybrid architectures; pure state-space models and certain research architectures are not supported out of the box. Heretic runs in a Python 3.10+ environment with PyTorch 2.2 or later, supports optional bitsandbytes 4-bit quantization, and can save or upload generated models, launch a chat evaluation, and run standard benchmarks. An optional research installation provides residual-vector visualization using PaCMAP and residual-geometry analysis. The project is distributed under the GNU Affero General Public License version 3 or later.

An AI image-generation and image-editing model from Google, also known as Gemini 3 Pro Image. It generates images from text prompts and can create or modify specific visual compositions, such as depicting a model holding a supplied object.

Needle 2 is an open-source, 45-million-parameter foundation model for tool calling, device use, and structured extraction on small devices. Its weights are compressed into a single 14 MB binary and integrated with its inference engine; the repository reports that a full session uses about 28 MB of RAM and performs inference without network access after setup. The model converts text and tool descriptions into schema-constrained JSON calls using a byte-level grammar, attaches a learned confidence score for threshold-based escalation, and can retrieve the top five tools from a larger catalogue. It uses a 256-token sliding window with tools pinned as key-value sinks to bound memory, and its Simple Attention Network combines a Hadamard MLP, grouped-query attention, engram key-value memory, and multi-lane hyper-connections. The Python package supports inference, LoRA fine-tuning, and checkpoint export; the inference engine is fetched from Hugging Face and cached, while the training stack is an optional installation.