Open-source AI agent teams you can actually inspect. Debug every prompt, tool call, memory change, and agent interaction. Control permissions, edit context, and choose the model for each agent. Self-host for free. Stop guessing what your agents are doing.

I believe that as AI agent systems become increasingly complex, observability will become just as important as orchestration. When issues arise, being able to understand what transpired between the agents rather than simply looking at the final output can make a significant difference.

@tanjum Exactly. The final output tells you what happened, the traces tell you why. We built Guilds for the 'why' 🔍

Hey Product Hunt!

We ve been running agent workflows for years, long enough to know exactly how they break. One agent makes a wrong assumption, another takes it as fact, the notes absorb it, and the error compounds. More instructions don t fix that. Seeing what actually happened does. So we built guilds.run: agent teams you can understand, debug and control.

Get started in a few minutes

Run it on your machine: git clone <https://github.com/CigaleAI/guil...> && cd guilds && ./setup.sh && docker compose up --detach --wait
Open http://127.0.0.1:8080, connect your LLM provider, and set up a guild of agents, each with its own task and model.
Give them a real task and inspect what happens: the exact prompt, every tool call and result, every memory change, and the group chat between agents.
When something goes wrong, ask Studio why. It reads the runs, finds the cause and drafts a fix. Nothing changes until you publish.

Hey Product Hunt!

Get started in a few minutes

Run it on your machine: git clone <https://github.com/CigaleAI/guil...> && cd guilds && ./setup.sh && docker compose up --detach --wait
Open http://127.0.0.1:8080, connect your LLM provider, and set up a guild of agents, each with its own task and model.
Give them a real task and inspect what happens: the exact prompt, every tool call and result, every memory change, and the group chat between agents.
When something goes wrong, ask Studio why. It reads the runs, finds the cause and drafts a fix. Nothing changes until you publish.

@tanjum Exactly. The final output tells you what happened, the traces tell you why. We built Guilds for the 'why' 🔍

guilds.run

Create multi-agent workflows that you can trust

Create multi-agent workflows that you can trust

Forum Threads

When AI agents start drifting, how do you debug them?

Forum Threads

When AI agents start drifting, how do you debug them?