“Source is public: you can read it before you run it.”

An open-source Python agent runtime, installed with one pip command, with a local cache that skips repeat LLM calls — pitched as a lighter alternative to LangGraph for developers.

“Open source, stated by the project itself.”

An open-source workspace for building and connecting AI agent workflows to 1,000+ integrations and LLMs; a developer/maker tool rather than a no-code product.

“You can see how it works, not just what it promises.”

The Control Plane and Network Layer For AI Agents

“Source is public: you can read it before you run it.”

An open-source agent platform where a lead AI agent takes tasks from WhatsApp, Slack, GitHub, MCP and more, then delegates to worker agents - built for technical teams running agents across their stack.

“Open source, stated by the project itself.”

A local control layer that lets you set permissions and approve or audit the actions of AI agents across connected apps, aimed at developers running autonomous agents.

“You can see how it works, not just what it promises.”

An open-source Chrome extension that lets an AI agent read and act on the page you're viewing, using whatever model you plug in, with API keys kept local and no telemetry.

“Source is public: you can read it before you run it.”

An open-source, local-first memory and task layer for AI coding agents, built around MCP. Developer infrastructure, not a consumer product.

“Open source, stated by the project itself.”

An open-source platform for running full teams of autonomous AI agents, each with its own context, tools, memory and role, rather than a single copilot — aimed at developers building multi-agent systems.

“You can see how it works, not just what it promises.”

An open-source Android AI agent that runs entirely on-device with MCP support and persistent memory. A technical, open-source project more than a polished consumer assistant app.