Business agents

LLM cost attribution per feature — track which parts of your product are spending your AI budget

OpenAI-compatible LLM client with multi-provider fallback.

A local 'second brain': RAG over your scattered notes and docs, with an MCP server so AI agents can use it too.

Agents that read the web through Lyrenth and finish the job: one command, cited answers, and steps that can write the result to a file.

AIGP governance adapter for the Claude Agent SDK (agent-loop level: query/ClaudeSDKClient, tool use). Distinct from aigp-anthropic, which wraps raw Messages API calls.

Your computer, piloted by any LLM. A cross-platform, provider-agnostic, permission-safe computer-use agent (OpenAI, Anthropic, Gemini, NVIDIA NIM and 10+ more).

Provider-agnostic reference commerce agent — a fork of anthropics/commerce-agents that runs on any OpenAI-compatible chat-completions endpoint (OpenRouter, Chutes, LiteLLM, vLLM, self-hosted).

Typed async and synchronous Python clients for Pi's agent RPC runtime

Anthropic plugin for PolyLLM.

Govern Claude Agent SDK tool use through Primary Path (canUseTool gate)

Govern LangGraph interrupt()-based HITL through Primary Path

Govern OpenAI Agents SDK tool approvals through Primary Path

rag-aio: asynchronous, modular RAG platform — facade, CLI, and all rag-aio packages in one distribution

Python SDK for the Snowflake Cortex Agent REST API (agent:run streaming, threads, feedback)

Stock swing attribution — detects unusual moves and explains them, or abstains

LLM observability and resilience decorator — semantic prompt caching, automatic retries, rate limiting, cost tracking, and a local web dashboard for any Python LLM call.

A high-throughput and memory-efficient inference and serving engine for LLMs