Fast cached text render library using ab_glyph
Symbolic Expressions As Markup.
A tower middleware for implementing ETag-based HTTP caching
Rust implementation of OpenTSLM using Burn, WGPU, and llama.cpp
Middleware system for request/response processing pipeline
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.
HTTP/1.1 Library
Elicitation engine: strategy selection and probe plan generation for parlov.
A fast, keyboard-driven TUI for running local models via llama.cpp
turbolite - SQLite VFS with sub-50ms cold queries from S3 + page-level compression and encryption
Glint compiler library
A secret manager backed by age