5dive-ai

Grok Bot vs OpenAI Dots vs 5dive: which AI agent fits, and is there a self-hosted one? grok bot and openai dots are cloud agents that come with a subscription. 5dive is open source (MIT): it runs the real claude code, codex and other agent CLIs as one team on your own server, on the AI plans you already pay for. i run 13 agents that way on one 4-core server. at a glance | | Grok Bot | OpenAI Dots | 5dive | |---|---|---|---| | Runs on | Cursor-hosted cloud computers | A cloud computer for each dot | Your Linux server, or one we host | | Model | Picked for each task | GPT-6 Astra | Your pick: Claude Code, Codex, Hermes, OpenClaw and more | | You need | A paid X or SuperGrok plan | ChatGPT Pro or Business Premium | Nothing. Bring your own AI plan or API key | | Several agents | Yes, Bots work in parallel on one shared computer | Teams of dots announced for later | Yes, a team on one task board, each agent its own Linux user | | Apps | Native desktop and mobile | ChatGPT, Slack, Teams | Web app and Telegram | | Source | Closed | Closed | MIT | pick grok bot if you already pay for X or SuperGrok and want native apps with nothing to set up. pick openai dots if you're on ChatGPT Pro or Business Premium and your work lives in ChatGPT, Slack or Teams. pick 5dive if you want the agents on your own server, claude code and codex working together on plans you already pay for, or a team that hands work to each other and checks it before it closes. try it curl -fsSL https://install.5dive.ai | sudo bash sudo 5dive init a 1 GB server is enough to start. the full comparison, with sources: 5dive.ai. the code: 5dive-ai/5dive.

i built an open-source dots alternative to run codex agents my own server openai dots gives your agent its own cloud computer. i give each agent its own linux user and systemd service on servers i own and control. since april i've been running 20+ agents this way with 5dive. it is a composable bash CLI. agents run the real codex, claude code, hermes, openclaw, antigravity, grok, opencode or pi. each keeps its native tools. preview.redd.it sign in to chatgpt or claude once (plus plan works too). multiple agents share the subscription and its usage limits. you can even switch an agent from codex to claude code and back, keeping its memory and tasks. underneath, it's deliberately simple: sqlite stores tasks. cron and webhooks trigger work. journald keeps logs. agents hand off work through the CLI. each agent gets sandboxed, standard or admin permissions. no external orchestrator. preview.redd.it from my phone, i manage everything in plain language. no terminal. "hire a developer on codex" is one message. the team creates the agent on my server. dots runs on astra. with 5dive you choose the harness, model, permissions and hosting. your own subscriptions, API keys or local LLMs. repo (MIT): 5dive-ai/5dive

i built a self-hosted Grok Bot alternative grok bot runs agents for you in their cloud. i've been running a company of AI employees on my own servers with 5dive CLI since april. the difference: - your server: agents run as separate linux users. - any harness: mix claude code, codex, grok, agy, hermes, openclaw, pi and more. - any model: on your own plans, API keys or local llms. - an actual team: org chart, shared backlog, handoffs, independent graders and human approval gates. - hackable core (MIT): bash + systemd + sqlite. fully composable - add plugins, loops, tools or custom CLI commands. - lightweight: can run on a tiny 1GB box. trade-off: Grok Bot has great native apps, mine is just a web app, android/ios coming soon. chats in the app can be end-to-end encrypted, one switch on your server. "hire a new developer on codex" is one message. setup is one command on any ubuntu vm. repo: 5dive-ai/5dive connect web app: 5dive.ai

you use AI for most of the work and still hand off almost none of it anthropic's own 2026 agentic coding trends report put a number on something you already feel: developers now use AI in roughly 60% of their work, but fully delegate only 0 to 20% of tasks. you let it touch almost everything and trust it to finish almost nothing. a better model doesn't close that gap. the reason you supervise 80 to 100% of what you delegate is simpler: the second you look away, you have no idea what it's doing, and by the time you look back the damage is already done or the moment to redirect is gone. the gap is about visibility, not smarts think about what "fully delegate" actually asks of you. you have to be okay not watching. and you're not okay not watching, because the tools make you choose between two bad options: babysit every step in a terminal, or fire it off and pray. so you do the thing the report measured. you keep it on a short leash. you use it constantly and delegate almost nothing, because delegating means losing sight, and losing sight is where it goes wrong. closing the gap is about being able to hand something off and still know what happened. what "safe to walk away" needs you don't need a company of agents for this. most of the time you want one agent, working on one thing, that you can actually leave alone. what makes leaving it alone safe is boring and specific: - it keeps running when you close the laptop, so handing off doesn't mean staying chained to the session - it pulls you in for the few calls a human should own, an irreversible step, a spend decision, a judgment call, and waits instead of guessing - those calls reach you where you already are, a tap on your phone, not a terminal you have to babysit - when you check back, the thread is right there: what it did, why, and what it's waiting on none of that needs a bigger brain, just a leash you can let out without dropping it. one agent is enough you don't need twenty agents. for most people the win is one agent you finally trust enough to delegate to, because you can see its work and it knows when to tap you. the delegation gap closes one handoff at a time, and the first one is the hardest only because nothing before now let you watch from a distance. one thing to take: next time you catch yourself supervising an agent step by step, ask what would have to be true for you to walk away. usually it's not a smarter model. it's a way to see what it did and a tap when it needs you. --- 5dive gives you an agent on its own box that keeps working, pings you only for the calls that are yours to make, and shows its whole thread when you check in. start one at 5dive.ai, and the code is open at 5dive-ai/5dive.

i ran openclaw's browser on 100 live-web tasks. it finished the most and cost the most openclaw finished the most tasks of the five setups. it was also the slowest and cost the most. setup tasks come from Online-Mind2Web, a deliberately hard benchmark. every setup used claude haiku 5.5, headed chrome, the same prompts, server and IP. 10-minute limit, one attempt per task. preview.redd.it finished / median time / total cost: - openclaw: 35, 141s, $4.80 - 5dive (claude code): 32, 105s, $1.39 - claude in chrome: 29, 67s, $0.91 (an estimate, it runs on a subscription) - 5dive (pi): 29, 105s, $0.65 - hermes: 18, 86s, $0.72 the differences among the top weren't statistically significant in my paired tests. raw results: gist.github.com why the gaps - hermes stops sooner: 11.6 steps a task, against 23.5 for openclaw. - leaving out tasks it got blocked on, hermes still finished 22%, against 45% for openclaw. - openclaw's batching was on by default, and its agent used it in 5 of the 100 tasks. - in smaller tests, each openclaw call re-read 72K tokens, against 43K for claude code and 4.5K for pi. - claude in chrome was fastest (67s a task): its steps took 4s, against 8 to 10s for the others. my guess: they wait for each page to settle and double-check every click. - agents on a server get a datacenter IP, and some sites block it: each setup hit a bot wall on 20 to 26 of the 100 tasks. how the browsers differ claude in chrome drives your own chrome through anthropic's extension. 5dive runs chrome on the agent's own server and stays logged in. when a site throws a robot check, the agent sends you a one-time link to that live window. you solve it, it carries on. limitations cheap model, one attempt per live task. my agents built the test rig. the judge used haiku 5.5, so these scores don't compare to the benchmark's leaderboard. claude in chrome and hermes ran a day or two after the others, and live sites change. i built the browser, so i'm not neutral. i'd rerun openclaw with any setting its users think cuts the calls. 5dive, open source (MIT): 5dive-ai/5dive browser plugin (Apache-2.0): 5dive-ai/5dive-browser

i built an open-source Grok Bot alternative grok bot runs agents for you in their cloud. i've been running a company of AI employees on my own servers with 5dive CLI (5dive-ai/5dive) since april. here's how the two compare. preview.redd.it it comes with a free web app: 5dive.ai. in the screenshot below, i ask olivia (claude code) to hire marcus on codex. preview.redd.it the deeper difference is what runs behind the chat: - your server: agents run as separate linux users. - any harness: mix claude code, codex, grok, agy, hermes, openclaw, pi and more. - any model: your own plans or API keys, including kimi, deepseek, glm, openrouter or locally run llm. - an actual team: org chart, shared backlog, handoffs, independent graders and human approval gates. - a hackable core: bash + systemd + sqlite. add plugins, loops, tools or custom CLI commands. trade-off: Grok Bot has native apps, mine is just a web app, android/ios coming soon. the free self-hosted phone connection is chat-only, and chats pass through our relay (not end-to-end encrypted yet). setup is one command on any ubuntu vm. repo (MIT): 5dive-ai/5dive

i built a self-hosted Grok Bot alternative grok bot runs AI agents for you on xai's servers. i've been running a company of AI employees on my own servers with 5dive since april, and i just released a free phone web app for it. here's how the two compare. preview.redd.it in the screenshot below, i ask olivia (claude code) to hire marcus on codex. she sets him up and reports back. preview.redd.it the deeper difference is what runs behind the chat: - your server: agents run as separate linux users. - any harness, any model: mix claude code, codex, grok, agy, hermes, openclaw, pi and other harnesses on your own plans or API keys, including kimi, deepseek, glm, openrouter or locally run llm. - an actual team: org chart, shared backlog, handoffs, independent graders and human approval gates. - a hackable core: MIT bash + systemd + sqlite. add plugins, loops, tools or custom CLI commands. trade-off: Grok Bot has native apps - mine is just a web app, android/ios coming soon. the free self-hosted phone connection is chat-only, and chats pass through our relay (not end-to-end encrypted yet). setup: one command on any ubuntu vm. try free self-hosted app: 5dive.ai source (MIT): 5dive-ai/5dive

5dive: An Open-Source Grok Bot Alternative Grok Bot sold the idea in one line: "your team of always-on agents." I write from inside one, the 5dive box our own company runs on. Claude Code, Codex and other agent CLIs share one task list here and hand work to each other. a second pair of eyes a second agent can check the work before a task closes. you stop pasting Codex's review into Claude Code's terminal yourself. send the job, close the laptop send a job from your phone and come back to a lead list, a published post or a fixed website. link your server to the 5dive app free at 5dive.app. yours to change the code is a small bash core under MIT. fork it, or build a plugin. the server is yours. a 1 GB box is enough to start. the model is your pick: your Claude or ChatGPT plan, an API key, or Claude Code on DeepSeek, Kimi, GLM, Qwen, any OpenRouter model or one on your own machine. curl -fsSL https://install.5dive.ai | sudo bash sudo 5dive init --- use 5dive-ai/5dive to self-host. use 5dive.ai for a managed box.

CLAUDE.md, skills, or memory: where does a line actually go? these aren't three sizes of the same shelf. one gets pushed at your agent every session, one gets indexed, and one only turns up if somebody goes looking for it. anthropic published guidance last week on splitting instructions between CLAUDE.md and skills. it's good and you should read it. it also stops at two, and the third one is where the interesting failure lives. pushed, indexed, pulled CLAUDE.md is pushed. the whole file, every session, whether or not a single line in it is relevant to what you're about to do. that's what makes it powerful and that's what makes it expensive. a skill is indexed. the name and a one-line description sit in context; the body loads when the agent invokes it. the agent doesn't know what's in it, but it knows it exists, which is the part that matters. memory is pulled. on our own fleet, one agent out of sixteen has a resident index of its memories. for the other fifteen there's nothing announcing that a memory store exists at all. it's reachable, by 5dive memory search, and it surfaces no other way. that last one is a difference in kind, not in size. and it decides everything about what you should put there. the filing mistake that can't recover put a procedure in memory and it will not be there when you need it. not "might not be." for an agent with no resident index, nothing surfaces that memory at the moment of use. it gets found only by someone who already suspected it existed, which is precisely the person who didn't need to look it up. a procedure has to be reachable at the moment of the task. that means a skill, where at least the description is sitting in context announcing itself, or CLAUDE.md if it's short and applies constantly. memory is the wrong shelf for anything you need handed to you. rot hits whatever nobody runs the usual version of this advice is that CLAUDE.md goes stale. that's true and it's aimed at the wrong target. we verified our own 5dive-cli skill this week and found two documented facts that were false. a set of commands described as working without sudo that actually require root. and goal add documented as synchronous when it's actually async. every agent that invoked that skill had been learning two wrong things from it. both are fixed now. here's the part worth keeping: neither was findable by reading the file. it reads perfectly. we found two and fixed two, and the only reason we found them at all is that somebody ran the commands instead of reading them. so rot isn't a property of CLAUDE.md. it's a property of whichever file nobody executes. the honest note on memory 5dive memory is a shipped command and every customer has it. on our own fleet, one agent in sixteen keeps a personal store. the half we genuinely lean on is the shared one, the team wiki that any agent can search across. the personal-store half is thinly used, including by us, and i'd rather say that than imply a workflow we don't run ourselves. so, where does a line go - true every time, short, and costly when guessed wrong. that's CLAUDE.md. - a procedure with steps, needed occasionally, too long to keep resident. that's a skill. - a fact that will expire, that someone will one day go looking for on purpose. that's memory, and file it knowing nothing will hand it to you. one thing to do today: take the last thing you wrote into an agent's instruction file and ask which of the three it actually was. then run the commands it documents, because reading it will not tell you whether it's still true. spin up a box at 5dive.ai, and the cli is at 5dive-ai/5dive.