Chat library for the fiddlesticks agent harness framework
Tiny global registry of per-request CancellationToken handles, keyed by string id. Pair with tokio_util::sync::CancellationToken for request-id-based cancellation in async LLM agents and web servers.
HTTP inbound/outbound adapters for Allora integration flows (request/reply & fire-and-forget).
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.
sid is a UNIX-inspired coding agent for Anthropic-compatible APIs
Local LLM inference MCP server powered by llama.cpp
High-performance AI coding agent CLI - Rust port of Pi Agent
Use ngrok traces to drive your development process.
Utility functions
Primary library for the fiddlesticks agent harness framework
Generic OpenAI-compatible MCP server
REST server module for Caryatid