No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by edgehero · Agent Tool · ★ 181
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is pi-dispatch safe to install? View the security audit →
pi-dispatch Let a coding agent work on your repositories while you are not watching, without surprise bills and without giving it the keys to your machine. pi-dispatch runs the pi coding agent as a self hosted background service: on a schedule, or when an issue, comment or pull request arrives from GitHub, GitLab, Forgejo or Azure DevOps, it opens a locked down container, lets the agent do one job against the repo, records what it did and what it spent, and shuts the container down. A durable queue absorbs bursts, spend caps are checked before a single token is spent, and a live admin panel shows everything and can turn the whole thing off. This is not another agent to weigh against the one you already use; it is the queue, the budget and the box for the pi you already run, steered by the setup your repo already has. ![Transcript of /dispatch status, runs, and triggers: queue counts, the run-
| Stars | 181 |
| Forks | 10 |
| Language | JavaScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 60.6131239144903/100 |
| Last Updated | 2026-10-13 |
| Created | 2026-07-15 |
| Platforms | claude-code, cli, docker, node |
| Est. Tokens | ~25k |
These tools work well together with pi-dispatch for enhanced workflows:
Looking for a pi-dispatch alternative? If you're comparing pi-dispatch with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi, Codex, and Antigravity & Gemi
Persistent Linux workspaces for agentic development.
Run Cursor's agent loop inside the pi coding agent via local Cursor SDK agents, with native model selection, t
Unified LLM gateway with weighted load balancing, observability & cost tracking. 统一的 LLM 网关，提供权重负载均衡、可观测性与费用追踪
Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.
开源OpenClaw中文文档站，OpenClaw中文指南，支持小龙虾 AI 智能体安装部署、消息渠道接入、Agent 架构、Skills 技能配置、模型提供商、CLI 命令参考、网关运维、安全沙箱等全方位文档。覆盖 Wh
Explore other popular agent tool tools:
pi-dispatch is Run the pi coding agent as a self-hosted service: jobs from cron, the CLI, or GitHub, GitLab, Forgejo and Azure DevOps events, each in a locked down Docker or Podman container, with a durable queue, s. It is categorized as a Agent Tool with 181 GitHub stars.
pi-dispatch is primarily written in JavaScript. It covers topics such as ai, ai-tools, azure-devops.
You can find installation instructions and usage details in the pi-dispatch GitHub repository at github.com/edgehero/pi-dispatch. The project has 181 stars and 10 forks, indicating an active community.
pi-dispatch is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to pi-dispatch on Agent Skills Hub include Codeman, container, pi-cursor-sdk. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: