gotempsh/temps

AI-native open-source alternative to Vercel + Sentry + PostHog + Pingdom + Resend + E2B. 440+ CLI operations with drop-in skills for Claude Code, Codex & OpenCode — deployments, analytics, session replay, error tracking, OpenTelemetry, email, sandboxes & AI gateway in one self-hosted Rust binary.

What it solves

Temps is a self-hosted, all-in-one platform that replaces multiple expensive SaaS tools for developers. It consolidates deployment, monitoring, analytics, and AI infrastructure into a single binary, eliminating the need for separate subscriptions to services like Vercel, Sentry, PostHog, and Datadog.

How it works

Temps operates as a self-hosted PaaS (Platform as a Service) that manages your applications and infrastructure. It uses a Rust-based backend with a PostgreSQL/TimescaleDB database and Cloudflare's Pingora engine for proxying. It provides a unified dashboard for managing Git-push-to-deploy workflows, managed databases (Postgres, Redis, MongoDB), and S3-compatible storage.

For AI-specific capabilities, it includes an AI Gateway to unify various LLM providers under one OpenAI-compatible endpoint, and AI Sandboxes based on Firecracker microVMs for secure, hardware-isolated code execution.

Who it’s for

Developers and teams who want to own their data and infrastructure, reduce SaaS spend, and simplify their observability stack by moving away from managed hosted platforms to a self-hosted alternative.

Highlights

  • AI-Native Operations: Over 440 CLI commands that can be driven by AI agents (e.g., Claude Code) via provided skills.
  • AI Gateway: A single endpoint for multiple LLM providers (OpenAI, Anthropic, Google, etc.) with built-in usage and cost tracking.
  • AI Sandboxes: Hardware-isolated code execution environments using Firecracker microVMs, compatible with the Vercel Sandbox SDK.
  • Integrated Observability: Built-in Sentry-compatible error tracking, OpenTelemetry traces/metrics/logs, and uptime monitoring.
  • Full-Stack Tooling: Includes web analytics with session replay, transactional email with DKIM, and managed database provisioning.

Related

  • Project
    jaylfc/taOS

    A self-hosted AI agent platform that turns spare hardware into a distributed compute cluster, providing a framework-agnostic memory system and a full web-based desktop interface.

  • Project
    octos-org/octos

    An embeddable AI agent harness kernel written in Rust that provides the execution loop, memory, and coordination infrastructure for agent-powered applications.

  • Project
    johnson7788/MultiUserClaw

    MultiUserClaw is a Docker‑based SaaS framework that lets you run isolated AI assistants (Hermes agents) for many users. It includes a React front‑end, a FastAPI gateway for auth, container management and LLM proxying, per‑user Hermes containers, PostgreSQL storage, and features like knowledge bases, skill store, cron jobs, multi‑channel bots, and multi‑model support.

  • Project
    NVIDIA/OpenShell

    A secure, sandboxed runtime for autonomous AI agents that uses declarative YAML policies to prevent unauthorized data access and network activity.

  • Project
    KevRojo/Dulus

    An open-source agent runtime that enables keyless access to frontier AI models via web sessions and provides a token-efficient environment for building and managing AI agents.