piboxpi-coding-agent (earendil-works) running on the network inside an aicodebox container. Exposes seven programmatic surfaces on one image — interactive shell, one-shot exec (`-p "..."`), an HTTP REST API (run/async/cancel, workspace file ops), an OpenAI-compatible `/openai/v1/chat/completions` endpoint (streaming, client-executed tool calling, response_format/JSON-schema), an MCP server at `/mcp` (mounted in API mode or as a sidecar), a Telegram bot, and a cron scheduler that fires pi on a schedule. Foreground modes (API/Telegram/Cron) are mutually exclusive except Telegram+Cron; MCP coexists with any of them. Bearer-token auth per surface (`PIBOX_API_MODE_TOKEN`, `PIBOX_MCP_MODE_TOKEN`), empty = no auth. Use when the user wants to drive pi-coding-agent programmatically over HTTP/MCP/Telegram/cron instead of a local terminal session, or needs to reason about which pibox mode/endpoint fits a given integration.
Install via ClawdBot CLI:
clawdbot install psyb0t/piboxGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec (Calls external URL not in known-safe list
https://github.com/psyb0t/docker-piboxUses known external API (expected, informational)
api.anthropic.comAudited Sep 10, 2026 · audit v1.0
Generated Sep 10, 2026
Integrate pibox into a CI/CD pipeline to automatically review pull requests or generate code changes. A CI step triggers one-shot exec mode with a specific prompt, and the agent analyzes the repository and posts results or commits changes, all without an interactive terminal.
Use cron mode to fire pi-coding-agent on a recurring schedule to produce daily standups, release notes, or repository health digests. Results can be pushed to a workspace file or Telegram channel for team consumption.
Deploy pibox in Telegram mode so engineers can chat with pi-coding-agent from their phones, using per-chat model and effort overrides. File transfer support lets users send snippets in and receive generated files back.
Point LangChain, openai-python, or any OpenAI-compatible client at the /openai/v1/chat/completions endpoint to give those frameworks a remote pi-driven coding agent. Supports streaming, client-executed tool calling, and JSON-schema response formatting for structured outputs.
Mount pibox's MCP server so agents in Claude, Cursor, or OpenClaw get remote tool access to a pi-driven workspace. The MCP surface exposes run_prompt and file tools, letting IDE agents delegate heavy coding tasks to the containerized pi agent.
Offer pibox as a managed multi-tenant service where customers get authenticated API keys to drive pi-coding-agent over REST or MCP. Provide tiered plans based on run volume, concurrency, and workspace storage.
License the pibox container and configuration tooling to enterprises that need to run AI coding agents inside their own infrastructure for compliance and data-residency reasons. Includes support, security hardening, and integration services.
Monetize by selling pre-built integrations and plugins (CI providers, IDE extensions, chat platforms) that connect to the pibox REST, MCP, or Telegram surfaces. Sell individually or as a bundle to engineering teams.
💬 Integration Tip
Always set PIBOX_API_MODE_TOKEN and PIBOX_MCP_MODE_TOKEN even on internal networks — empty tokens leave the agent-execution and file APIs completely unauthenticated; bind to loopback or behind an authenticating proxy. Remember PIBOX_AVAILABLE_MODELS is required for API mode, foreground modes are mutually exclusive (except Telegram+Cron), and only one run can occupy a workspace at a time.
Scored Sep 10, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...