AutoGPT 是面向自主智能体的开源平台,支持用自然语言或可视化流程创建、运行和管理能够持续执行任务的智能体。
关于 Backmesh
backmesh: Self-hosted GitHub Actions runners for up to 10× less Cost Pricing FAQ Docs Self-hosted GitHub Actions runners for up to 10× less. AWS GCP Azure Each job runs on its own spot VM in your AWS, GCP or Azure account. Your cloud bills you, so your cloud credits apply. # Paste into Claude Code, Codex, or another coding agent set up https://backmesh.com/SKILL.md Copy Core features free, no credit card. Install manually See the costs No cloud keys stored A role from your cloud CLI connects each cloud. Your code never reaches us Code, secrets, caches and logs stay between GitHub and your runners. One small event per job It never names the repo, workflow, job or branch. What's sent 150,000 minutes a month: $1,800 on GitHub, $191–$365 on backmesh. 4-vCPU Linux jobs; the range spans AWS, Azure and GCP and the VM types a job may get. Compute cost a month GitHub-hosted $1,800 $1,800 backmesh on AWS $210–$261 $210–$261 + $0.41–$0.58 per 1,000 jobs to boot their VMs, about 30 s each backmesh on Azure $191–$206 $191–$206 + $0.53–$0.74 per 1,000 jobs to boot their VMs, about 60–70 s each backmesh on GCP $299–$365 $299–$365 + $1.50–$2.27 per 1,000 jobs to boot their VMs, about 60–70 s each $0 $500 $1,000 $1,500 $1,800 Spot VMs (range across VM types) Control plane, fixed Control plane: about $86 on AWS, $111 on Azure, $74 on GCP. GitHub's list price against spot prices on 2026-11-13, without disks, VM boots or runners no job takes, so it's a floor; see What does backmesh cost? Compute, one month GitHub-hosted linux_4_core 150,000 min × $0.012 $1,800.00 Total $1,800 backmesh in your AWS account Spot VMs, one per job $124–$175 150,000 min, us-east-2 Control plane, fixed $86 backmesh Free $0 Total $210–$261 Spot prices on 2026-11-13, without disks or boots. Pricing backmesh's core features are free; you pay your clouds for the VMs. Free $0 Unlimited jobs Cache included No credit card required Install Premium Let's talk Slack monitoring Logs Runtime history Talk to us Pick the cloud per workflow. Each label runs in one cloud. Out of spot capacity, the next VM type launches, never the next cloud. Use backmesh-od-* (on-demand) for jobs that shouldn't be interrupted. Learn more strategy: matrix: cloud: [aws, gcp, azure] runs-on: backmesh-${{ matrix.cloud }}-4 backmesh-aws-4 test · aws backmesh-gcp-4 test · gcp backmesh-azure-4 test · azure Every job log ends with what it used. Learn more Job log backmesh: resources over 312 s, sampled every 5 s Memory peak 9.8 GiB
访问提示
本站仅提供官网信息与访问导航,不代表对该网站的产品、服务或交易作出担保。访问外部网站时,请核对网址,注意账号和财产安全。
同类型网站
查看分类百川智能发布的金融大模型,金融场景能力领先GPT-4o近20%
Build a Large Language Model (From Scratch) 是一款AI 大模型方向的 AI 工具,适合主流大语言模型与开源模型。
支持多 AI Agent 框架的可视化管理面板,支持 OpenClaw 和 Hermes Agent 双引擎,内置智能助手一键安装诊断