Deep dive
The full breakdown - performance, comparisons, and setup
pi
pi is an agent framework - AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI.
Overview
This is the home of the Pi agent harness project including our self extensible coding agent.
- Visit pi.dev, the project website with demos * Read the documentation, but you can also ask the agent to explain itself
For Slack/chat automation and workflows see earendil-works/pi-chat.
Pi does not include a built-in permission system for restricting filesystem, process, network, or credential access. By default, it runs with the permissions of the user and process that launched it.
If you need stronger boundaries, containerize or sandbox Pi. See packages/coding-agent/docs/containerization.md for three patterns:
- Gondolin extension: keep 'pi' and provider auth on the host while routing built-in tools and '!' commands into a local Linux micro-VM. - Plain Docker: run the whole 'pi' process in a local container for simple isolation. - OpenShell: run the whole 'pi' process in a policy-controlled sandbox.
See CONTRIBUTING.md for contribution guidelines and AGENTS.md for project-specific rules (for both humans and agents). Longer term plans for Pi can also be found in RFCs.
GitHub releases include a versioned source archive covered by the release's 'SHA256SUMS' file. Extract it and run the same build script used for the official standalone binaries:
pi is open-source, written primarily in TypeScript, with 109,797 GitHub stars under the MIT license. The latest release is v0.87.1 (2026-09-22).
Key capabilities
From the project's documentation:
- @earendil-works/pi-coding-agent: Interactive coding agent CLI
- @earendil-works/pi-agent-core: Agent runtime with tool calling and state management
- @earendil-works/pi-ai: Unified multi-provider LLM API (OpenAI, Anthropic, Google, …)
- Visit pi.dev, the project website with demos
- Read the documentation, but you can also ask the agent to explain itself
- Plain Docker: run the whole pi process in a local container for simple isolation.
How it fits a local-AI stack
pi runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:
Sources
- Source code & docs: earendil-works/pi
Stats from GitHub, 2026-09-28.
Frequently asked
Quick answers to common questions
What is pi?
pi is a agent-framework tool for local AI workloads. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Is pi free and open source?
Yes, pi has 109,797 GitHub stars and is licensed under MIT. You can self-host it for free on linux, docker.
What platforms does pi support?
pi runs on linux, docker.
What hardware do I need for pi?
The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. pi has 109,797 GitHub stars and an active community.
Does pi support GPU acceleration?
pi supports GPU acceleration via CUDA, Metal, or Vulkan depending on your platform. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.
What are the best alternatives to pi?
Popular alternatives include other agent-framework tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.
How much does pi cost?
pi is free-open-source. It is completely free and open source to self-host.
Pairs well with
Complementary tools, models, and hardware