A personal AI companion you host yourself.
It remembers you, shows its work, and never acts without your say.
Get started · How it works · What works today
Conker is an everyday AI chat that runs on your own server. It remembers across conversations, runs your cron jobs, and acts through tools. What it may do is your setting, per chat, agent and tool, and anything that needs you waits in one Inbox until you answer.
It is built as small services with one job each, so every boundary is a process boundary:
flowchart LR
You([You]) --> GW[Gateway] --> Pi[Pi<br/>conversations]
Pi --> MG[MemoryGate<br/>remembers]
Pi --> TG[ToolGate<br/>acts, as allowed]
Pi --> SG[SystemGate<br/>observes]
MG --> EM[Embeddings]
| Repository | Job | Release |
|---|---|---|
| conker | The app, installer, deployment and docs. Start here. | |
| pi | Conversations, model roles, the gateway and a record of every turn |  |
| toolgate | The only way to act: typed tools, exact approvals, spending limits, the sandbox |  |
| memorygate | Memory with sources: evidence in, bounded context out |  |
| systemgate | A read-only view of the machine |  |
| embeddings | Text to vectors, and nothing else |  |
Each service is licensed under AGPL-3.0 and usable on its own. Conker is early: see status for what is proven and what is still missing.