“Go”

Go port of the Pi coding agent, shipped as one native binary that can still run Pi's TypeScript extensions.

Self-hosted Go workspace where AI agents run security tools through MCP for authorized testing.

Go reimplementation of the pi coding agent with headless and REPL modes, skills, plugins and multi-provider support.

Open-source durable execution platform for building reliable applications and AI agents.

Open-source observability for LLM applications, built on OpenTelemetry

Locally run, multi-provider AI coding workspace for the desktop, with sessions you can continue from a phone on the same LAN.

Open-source SDK for browser agents that combines natural-language act, extract and observe with Playwright-style control.

Terminal coding agent written in Go, with sub-agents, MCP support, a permission gate and native diff review.

Terminal coding agent that routes each development task to Claude, GPT or Gemini based on configurable rules.

Open-source sandbox platform that runs AI agent workloads in isolated environments on your own infrastructure.

Orchestration platform for AI agents, background tasks and durable workflows.

Open-source, local microVM sandboxes for untrusted workloads, with an embeddable SDK and an MCP server.

Fully local, voice-enabled assistant that browses the web, writes code and plans tasks without cloud services

Open durable execution: write async await code that runs on the database or queue you choose.

Open-source, Apache-2.0 visual tool for building AI agents, apps and workflows with plugins, knowledge bases and an API and chat SDK

Terminal coding agent that edits files and runs commands, lets you pick the model and permission level, and runs on your machine.

Kanban workspace for running several coding agents in parallel, reviewing their changes and opening pull requests

Self-hosted browser workspace built on the Pi Coding Agent, with chat, file editing, command runs and scheduled tasks

Personal desktop AI agent for files, writing, planning and daily tasks, with companions, plugins, scheduled runs and MCP.

Runs a Claude Code dev team on your server and drives it from Telegram, VK or LO chats, opening a PR per request.

Open-source, high-performance vector database for large-scale search, with a managed option on Zilliz Cloud.

Self-hosted workspace where people and coding agents share projects, live sessions and persistent Mates across providers.

Local-first MIT coding agent with DeepSeek defaults, provider switching, OS sandboxing and a checkpoint for every patch.

Tracing, evaluation and monitoring for LLM apps and agents, with SDKs for several languages