DeepJIT

JAX is a Python library for accelerator-oriented array computation and program transformation, designed for numerical computing and large-scale machine learning. It transforms Python and NumPy-style functions through automatic differentiation with `jax.grad`, automatic batching and vectorization with `jax.vmap`, and just-in-time compilation with `jax.jit`. It uses XLA to compile computations for GPUs, TPUs, and other accelerators. JAX supports compiler-driven multi-device execution: `Mesh`, `PartitionSpec`, and `NamedSharding` declare array placement across device meshes, allowing distributed training code to include automatically managed parallel work such as gradient synchronization. Its compilation tools also include ahead-of-time compilation, portable artifact export with `jax.export`, and conversion to TensorFlow SavedModels through `jax2tf` for serving integrations. The project describes itself as a research project rather than an official Google product.

DeepSelect is a high-performance CUDA and PyTorch implementation of TopK kernels for DeepSeek Sparse Attention and sampling workloads. It replaces vanilla `torch.topk` for supported inputs, covering bfloat16 lightning-indexer workloads and float32 sampling workloads, with configurable sorting, index type, value output, variable-length rows, and NaN handling. The repository reports 2–20× speedups against `torch.topk` on its benchmarks. It is distributed as an installable Python package from the `deepseek-ai` GitHub repository. Supported TopK values are limited to 4096 or less, and input tensors must meet specified stride and contiguity requirements; the optimized sampling case targets vocabularies of approximately 128K.

jit is a local-first macOS command-line secrets manager from jitpass that moves development credentials from plaintext files such as .env, AWS credentials, shell exports, npm configuration, and MCP configurations into an encrypted vault protected by Touch ID. It rewrites source files with decoys so existing tools can continue working while the real value is released only to an authorized process. It provides credentials through per-process environment injection, native credential protocols such as AWS credential_process and Docker or Git credential helpers, and a named-pipe mount for tools that only read files. The named pipe is a mode-0600 POSIX FIFO: authorized reads receive decrypted values through the kernel pipe buffer without writing them to disk, while ambient readers receive decoys. jit is macOS-only for Apple Silicon and is still in development; the project states that it does not protect credentials after they enter the requesting process's memory.

DwarfStar is a self-contained, model-specific native inference engine for running DeepSeek V4 Flash, GLM 5.2, and, on high-memory systems, DeepSeek V4 PRO locally. It combines model loading, prompt rendering, tool calls, persistent KV state, an HTTP server, and a coding agent rather than serving as a general GGUF runner. The engine supports Metal on Macs, CUDA including multi-GPU systems, and ROCm on Strix Halo hardware; it also provides SSD streaming for machines with insufficient RAM, distributed tensor and pipeline parallelism, and server-side micro-batching for multi-user inference. The repository includes tooling and data for GGUF, imatrix, quality, and speed testing, and acknowledges code and design contributions from llama.cpp and GGML.

jcode is an open-source, Rust-based terminal harness for AI coding agents and LLM workflows, designed for interactive development across multiple sessions. It supports resumable sessions, session search, multi-agent swarm and helper-agent workflows, compatible model-provider integrations, MCP, browser automation, and a self-development mode; installation scripts target macOS, Linux, and Windows. For automatic memory, jcode embeds turns and responses as semantic vectors, searches a graph of stored memories using cosine similarity, and feeds relevant results into the conversation. A memory sideagent can verify and expand retrieval, while periodic extraction stores new memories and ambient consolidation reorganizes entries and checks for staleness and conflicts. Explicit memory tools and traditional retrieval over previous sessions are also available. Its terminal UI includes side panels, diff views, inline Mermaid diagrams, information widgets, custom scrolling, and real-time rendering. The project supplies a Mermaid renderer without browser or TypeScript dependencies and publishes benchmarks covering RAM consumption, startup and input-readiness times, and memory scaling across multiple active sessions.