Auto-discover and register Ollama models in pi. No more manual models.json editing.

NexusAI Local Proxy — Ollama + OpenRouter + Device API Manager

GoNext CLI — the gonext terminal plus the local worker that runs agent / OCR / PDF / embedding jobs on your Mac (Ollama / MLX / OpenAI-compatible).

Qwen Code - AI-powered coding assistant

OGPT - AI coding assistant for the terminal with a built-in local engine

Local-first AI workforce operating system for your machine. Hire crew, assign missions, and supervise from the CLI or a local dashboard while models run on this computer — thinking, tool calls, and an audit trail, on loopback.

ai-fly — peer-to-peer HTTP/WebSocket bridge with AI-ready presets, over OpenDWeb fabric

Ollama provider — local LLM text completion, embeddings, and image description via Ollama API

Native Ollama provider for the pi coding agent - per-request context size, overflow compaction, model thinking levels, prompt warm-up

MCP control plane for local cognitive labor — job-shaped tools with tiered Ollama models (instant/workhorse/deep/embed), server-enforced guardrails, and measured economics so Claude can delegate bulk work without losing control.

Install alias for vermastaff — local-first AI workforce OS. Same CLI as @verma-consulting/vermastaff: hire crew, run missions, supervise from a local dashboard while models run on this machine.

Ollama adapter for [Obyflow](https://github.com/Obyflow/obyflow)'s AI-assisted investigation features, implementing the `LLMAdapter` interface from [`@obyflow/llm-core`](https://www.npmjs.com/package/@obyflow/llm-core). Use this to run investigations agai

A typed local-LLM provider for the @orkestrel line — a ProviderInterface over a local Ollama daemon's /api/chat with NDJSON streaming and guard-narrowed wire boundaries. Part of the @orkestrel line.

Evaluation framework and CLI for WebMCP tools and agentic workflows

A local terminal coding assistant powered by Ollama

Bandit — a local-first AI coding agent for your terminal. Unscoped alias for @burtson-labs/bandit-stealth-cli.

Multi-Provider Ollama Proxy Server for Node.js (OpenAI + Gemini + Openrouter). Free tier usage available.

Writes your git commit messages for you with AI

Ollama embedding provider and OllamaRag convenience class for @mcp-abap-adt/llm-agent.

Production-grade TypeScript SDK for Ollama with native fetch, high availability failover, multi-turn tool calling, structured outputs, reasoning stream tokens, OpenAI/Anthropic bridges, MCP, and Web Stream adapters.