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.
AI/Human task management system with file-based storage
A highly parallel Perl 5 interpreter written in Rust
Rust bindings for the Listen Notes Podcast API
Multi-provider LLM client for Rust — streaming, non-streaming, tool calls, MCP, DeepSeek, OpenAI, Anthropic, Gemini, Codex
Multi-provider LLM abstraction library with caching, rate limiting, and cost tracking
llm_prompt: Low Level Prompt System for API LLMs and local LLMs
A library and REST API for translating natural language text to Cypher queries using AI models
Discord voice and text host for Gemini Live
Stateful graph runtime for LLM workflows in Rust (community project; not affiliated with LangChain). Pregel-style execution: nodes, conditional edges, checkpoints, streaming. Optional adapters for Ollama, OpenAI, OpenRouter (OpenAI-compatible), and Anthropic; optional ReAct agent + tools. Crate import: rust_langgraph (underscore). Default features include in-memory checkpoints. Enable Cargo features explicitly for LLM modules (e.g. ollama, openai, openrouter, anthropic, prebuilt). See README.md on crates.io for copy-paste Cargo.toml, env vars, and common mistakes.
Formal symbolic AI implementation with OpenAI-compatible APIs