The autonomous, self-improving AI agent. Single Rust binary. Every channel. Install with: cargo install opencrabs
Senior SysAdmin, Network Admin, Data Analyst, and Software Engineer living in your terminal. A high-precision local AI agent harness for LM Studio, Ollama, and other local OpenAI-compatible runtimes that runs 100% on your own silicon. Reads repos, edits files, runs builds, inspects full network state and workstation telemetry, and runs real Python/JS for data analysis.
GPU-accelerated tile-based compression engine with 32-way parallel decompression
Machine-wide hybrid code search service: BM25 + vector + KG, zero cold-start, MCP server
High-performance, schema-agnostic, backend-agnostic event bus
High-performance, schema-agnostic, backend-agnostic event bus
Fast word-length bucketing for text documents using SIMD
Out-of-band scanner for forbidden literal strings and regex patterns. Gitignore-aware, fast, dependency-light: built for CI deny-listing of leaked credentials and banned tokens.
Highly optimized IPv4 checksum calculation, no-std compatible
S4 (Squished S3) — pluggable GPU/CPU compression codec layer (nvCOMP zstd / Bitcomp, CPU zstd).
S4 (Squished S3) — config types and loader for the GPU-accelerated S3 gateway.
S4 — Squished S3 — GPU-accelerated transparent compression S3-compatible storage gateway (cargo install s4-server installs the `s4` binary).