pi-go MCP Server
dimetron/pi-go
[](https://agentrank-ai.com/tool/dimetron--pi-go/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Are you the maintainer of dimetron/pi-go? Claim this listing →
Go implementation of AI coding agent
Add AgentRank to Claude Code Discover and compare tools like dimetron/pi-go — your AI finds the right one automatically
Get API Access → claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
dimetron/pi-go is a Go tool licensed under MIT. Go implementation of AI coding agent Topics: acp, ai-agent, cli, coding-agent, go, golang, llm, mcp, terminal, tui, pi.
Ranked #2996 out of 24846 indexed tools.
Ecosystem
Go MIT
acpai-agentclicoding-agentgogolangllmmcpterminaltuipi
Score Breakdown
Stars 15% 210
210 stars → growing community
Freshness 25% 1mo ago
Last commit 1mo ago → moderate activity
Issue Health 25% 56%
15/27 issues closed → decent issue management
Contributors 10% 9
9 contributors → small team
Dependents 25% 0
No dependents → no downstream usage
npm Downloads N/A
PyPI Downloads N/A
Forks 29
Description Brief
License MIT
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Description low impact
Freshness high impact
Dependents medium impact
Matched Queries
From the README
# pi-go A terminal-based coding agent built on [Google ADK Go](https://adk.dev/). It connects to multiple LLM providers, runs sandboxed tools, integrates LSP, and ships with a process-based subagent system. ## Features - **Multi-provider LLM** — Claude (Anthropic), GPT/O-series (OpenAI), Gemini (Google), Mistral, Grok (xAI), Azure OpenAI, OpenRouter, OpenCode, and Ollama (local or cloud) for models - **Sandboxed tools** — read, write, edit, shell, grep, find, tree, and git operations. All tools are restricted to the project directory via `os.Root`. - **Interactive TUI** — Bubble Tea v2 with Markdown rendering (Glamour), slash commands, and theming - **Session persistence** — JSONL append-only event logs with branching, compaction, and resume - **Model roles** — Named configurations (default, smol, slow, plan, commit) selectable via CLI flags - **Subagents** — Process-based multi-agent system with types: explore, plan, designer, reviewer, task, quick_task - **LSP** — JSON-RPC clientRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.