Pi-Mojo – A Mojo Port of Pi AI Agent Toolkit

Notifications You must be signed in to change notification settings

Fork 0

Star 1

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

1 Commit

1 Commit

examples

examples

src

src

tests

tests

.gitattributes

.gitattributes

.gitignore

.gitignore

ARCHITECTURE.md

ARCHITECTURE.md

LICENSE

LICENSE

README.md

README.md

pixi.toml

pixi.toml

Repository files navigation

pi-mojo is a native Mojo port of Pi—a popular, tool-efficient agentic AI platform (utilizing only 4 core tools) prominent in open-source systems like OpenClaw. It provides the Mojo community with a compiled, self-contained reference implementation to explore systems-level agent architectures, type-safe structures, and native C integrations.

🚀 Getting Started

Prerequisites

Ensure you have the Modular Mojo compiler installed:

mojo --version

Running Examples

The repository features progressive, systems-level agentic AI examples demonstrating the spectrum of agent architectures and compiled system execution capabilities:

🤖 Example 1: Progressive AI Completions & Chat (Sample Run)

A progressive exploration of text completions, starting from zero dependencies, local llm and live cloud LLMs.

mojo -I src examples/example_1_basic_ai/example_basic_ai.mojo

💻 Example 2: Systems Coding Agent (Sample Run)

A systems agent that translates high-level task descriptions into shell commands and executes them natively via system process spawning.

mojo -I src examples/example_2_coding_agent/example_coding_agent.mojo

🔧 Example 3: Native AI Tool Calling (Sample Run)

A cloud-only agent demonstrating how to expose native Mojo functions as tools (Function Calling) to a live LLM.

mojo -I src examples/example_3_tool_calling/example_tool_calling.mojo

🌊 Example 4: Real-Time AI Event Streaming (Sample Run)

A cloud-only completions stream demonstrating real-time SSE token parsing and flushed printing.

mojo -I src examples/example_4_event_stream/example_event_stream.mojo

⚡ Example 5: GPU-Accelerated Hardware Analytics (Sample Run)

A local performance benchmark executing parallel token classification on a hardware-accelerated GPU pipeline.

mojo -I src examples/example_5_gpu_analytics/example_gpu_analytics.mojo

🌐 Example 6: Concurrent Multi-URL Web Research Agent (Sample Run)

A concurrent web agent spawning parallel thread pools to fetch and sanitize multiple websites concurrently, then synthesizing research reports via Gemini 3.5 Flash.

mojo -I src examples/example_6_web_researcher/example_web_researcher.mojo

🔍 Example 7: Codebase Semantic Auditor & Refactoring Agent (Sample Run)

A systems security auditor agent crawling files dynamically and extracting zero-copy StringView lifetimes slices to synthesize refactoring proposals.

mojo -I src examples/example_7_codebase_auditor/example_codebase_auditor.mojo

🔁 Example 8: Long-Running Coder Agent (Sample Run)

An autonomous systems-level coding agent running in a persistent loop (Plan -> Act -> Observe -> Repeat) that maintains session state history, executes system commands, and solves multi-step engineering tasks.

mojo -I src examples/example_8_long_running_coder/example_long_running_coder.mojo --interactive

💓 Example 9: Local LLM Service Heartbeat Check (Sample Run)

A diagnostics checker that executes health queries and round-trip timing checks to verify the state of local LLM models on port 1234.

mojo -I src examples/example_9_local_heartbeat/example_local_heartbeat.mojo

🔄 Example 10: Towards Full-Fledged Agentic Loops (Sample Run)

An autonomous background-ticking daemon agent driven by a heartbeat clock that polls workspace states, monitors compilation status, patches error logs, and drives tasks to completion.

mojo -I src examples/example_10_full_fledged_agent/example_full_fledged_agent.mojo --interactive

🏗️ High-Level System Architecture

pi-mojo unifies compiled, high-performance systems logic with dynamic agent loops. High-level agent packages leverage low-level subprocess utilities and filesystem caching tools to achieve zero-overhead execution.

For complete technical implementation details, sequence diagrams of the execution, and the repository directory layout, refer to ARCHITECTURE.md.

🛡️ License

Licensed under the MIT License (refer to the LICENSE file for details). All attributions belong to the original upstream Pi development team.

About

A mojo port of the PI AI Agent Toolkit

Resources

Readme

License

MIT license

Uh oh!

There was an error while loading. Please reload this page.

Activity

Stars

1 star

Watchers

1 watching

Forks

0 forks

Report repository

Releases

1 tags

Packages 0

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

Languages

Mojo 97.9%

Python 2.1%