RepoAlerts

15838328874/pi

Can I trust it?

No red flags in our checks.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 6 days ago.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A self-hostable, multi-tenant AI agent platform in Python, reimplementing the pi coding agent harness as an HTTP service. Includes streaming LLM adapters, an asyncio agent loop, sandboxed tool execution, JWT auth with quotas and audit, a trajectory log, an eval harness, and MCP…

Who it's for

Python developers and teams building self-hosted, multi-user AI agent services with sandboxed tool use

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up 15838328874/pi in my project. Follow its README: https://github.com/15838328874/pi. Explain each step and check it is safe before running anything.

Read the README

Star curve

264From 0 to 264 stars between 6 Sept 2026 and 20 Oct 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

18,263 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![15838328874/pi on RepoAlerts](https://repoalerts.com/badge/15838328874/pi.svg)](https://repoalerts.com/repo/15838328874/pi?ref=badge)
Share on X

  • wangmiaozero/pi-harness

    A desktop workspace built on Pi Coding Agent for macOS, Windows and Linux. It adds run tracing, replay, budgets, tool policies, checkpoints, recovery, evaluation, and multi-agent task orchestration wi

    Apps & desktopTypeScript · 1,000 stars · +813 this week · 61 days old

  • disler/durable-pi

    Durable agent network in TypeScript. Each device runs a backend that owns its agents, SQLite storage and tools, persisting runs so they resume after restarts. Clients connect via URL and bearer token

    AI agentsTypeScript · 227 stars · +123 this week · 15 days old

  • IsuruMaduranga/harness-engineering-101

    A book-length series in Markdown that explains how AI agents work by building a roughly 300-line toy agent harness in plain Python. It covers the LLM message array, tool calls, the agent loop, context

    AI agentsPython · 376 stars · +371 this week · 44 days old · HN 132 pts

  • Aoisop/mawoagent

    A local Python agent runtime with a web workbench and CLI that connects model inference, tool execution, permission checks, session resume, long-term memory and Skills. It can turn explicit user feedb

    AI agentsPython · 57 stars · +56 this week · 2 days old

  • google-research/harness2

    A Python framework for recursive harnessing of AI agents, which optimizes the prompts, tools, memory, skills and orchestration around a fixed model. It refines the harness per task through propose, pr

    AI agentsPython · 14,759 stars · +14,753 this week · 14 days old · HN 77 pts

  • togethercomputer/HybridAgent

    Research code for HybridAgent, an LLM agent that alternates between latent-space reasoning and text-based actions in one generation. It includes the hybrid generation engine with Python and search too

    AI agentsPython · 331 stars · +328 this week · 12 days old