Agent harnessAI and agent development
pi
Build extensible coding agents with a unified model API
- Stars
- 69,444
- Forks
- 8,532
- Updated
- Updated Jul 10, 2026
MIT
Build extensible coding agents with a unified model API
Pi Agent Harness packages a unified multi-provider LLM API, a tool-calling runtime with state management, an interactive coding CLI, and a terminal UI as composable modules. It gives developers separate extension points for models, tools, and interfaces. Pi has no built-in permission system and inherits the launching process’s filesystem, network, and credential access, so stronger boundaries require a container or sandbox.
Resource types
Use cases
Runtime
Build extensible agents for long-running, multi-step work
Build and run open agents with tools, memory, permissions, and multi-agent coordination.
Protocols & integrations
Capabilities
Audience
Public GitHub facts last synced Jul 10, 2026.
Run long-lived business workflows as recoverable multi-agent execution graphs.
Build and self-host LLM agent backends behind a unified API.