LLM client pipeline with circuit breaker, ML model router, semantic cache, and multi-format translation
LLM client pipeline with circuit breaker, ML model router, semantic cache, and multi-format translation
AXON v1.5.1 — first crates.io publication of the AXON language full-stack runtime. Lexer/parser/type-checker/IR generator (re-exported from axon-frontend) plus the native Rust runtime: typed channels (TypedEventBus with QoS×5, π-calculus mobility, capability extrusion via shield D8 — Fase 13.f.2), Free Monad CPS handlers (Fase 2), lease kernel + reconcile loop (Fase 3+5), Epistemic Security Kernel (ESK Fase 6), Trust Types + ReplayLog (Fase 11.a+11.c), Stateful PEM over WebSocket (Fase 11.d), Ontological Tool Synthesis (Fase 11.e), Mobile Typed Channels (Fase 13). Crate publishes as `axon-lang` to mirror the Python PyPI package; library import remains `use axon::*` so existing call sites keep working unchanged.
Fastest size-aware LRU cache with highest hit rate via LHD algorithm / 最快的大小感知 LRU 缓存，基于 LHD 算法实现最高命中率
Idiomatic Rust wrappers for the NVIDIA CUDA stack (Driver API, Runtime API, NVRTC, cuBLAS, cuDNN, NCCL, NVML, ...). Umbrella crate.
Terminal session manager for Claude Code — browse, preview, and resume sessions with per-model cost tracking.
AI Context Protocol - Token-efficient and context enhancing code documentation for AI systems
smalloc is a simple, fast allocator
CLI tool to detect AI-generated code and attribute it to a model family
Detect AI-generated code and attribute it to Claude, GPT, Gemini, Copilot, or Human
Git-aware tree-sitter-based code-graph builder. Emits Mermaid diagrams at five zoom levels, materializes per-commit bundles into a content-addressed cache, and computes coloured structural diffs between any two refs. Single binary `a2m` with ten subcommands.
NER, coreference resolution, relation extraction, PII detection, and zero-shot entity types