A private reasoner for your terminal. Direct conversation or grounded multi-agent research, GPU-native and fully local. No API keys, no inference servers.
Guardrails for AI agents, with a receipt. Blocks destructive tool calls before they run and signs every decision into a hash-chained record anyone can verify with an open-source tool.
Host-agnostic LLM agent execution on the OpenAI Agents SDK: model fallback, streaming, structured-output extraction, self-correction, and tracing — behind a small injected provider seam.
Unified LLM client library for Go - one API, 36 providers (Anthropic, OpenAI, Google Gemini, AWS Bedrock, Mistral, Groq, DeepSeek, +29 more), zero external dependencies.
Go-native, zero-dependency LLM command-output compressor — an embeddable take on rtk (the Rust 'token killer') with lossless-by-default compression and credential redaction.