Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

TRACER: replace 90%+ of your LLM classification calls with a traditional ML model. Formal parity guarantees. Self-improving.

Self-hosted AI workspace.

pool is Poolside’s coding agent that runs in your terminal or integrates with any ACP-compatible editor

Claude Code for your Inbox

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

AI gateway written in Go. Lightweight unified OpenAI-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI & Ollama. LiteLLM alternative with observability, guardrails, streaming, costs and usage…

Coordinator for stateful sharded services

The agent that grows with you

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

Autonomous experiment loop extension for pi

Open-source local-first AI agent for desktop work. No account, no telemetry: use local models with Ollama/Rapid-MLX or bring your own provider key.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Terminal-native AI coding agent running in containers.

OpenShell is the safe, private runtime for autonomous AI agents.

Framework for evaluating and improving agents

Personal AI, On Personal Devices

Sandbox your local AI agents so they can read/write only what they need

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faste…

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

A native macOS AI chat client built with SwiftUI

Natural language to bash commands. Run, understand, copy bash commands generated by an LLM

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…

Talk to your shell in natural language. Locally.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞