px0 is a local, open-source agent built around the way you work. Tell it a chore in plain English and it writes, schedules, and runs the workflow itself, wired to 1,000+ apps you already use. No server. No dashboard. Nothing hosted.
curl -fsSL https://px0.ai/install.sh | shDescribe a recurring job once and it gets written as a workflow you can run, schedule, and edit, wired to 1,000+ apps you already use.
Every line below is one sentence you type into px0 workflows new. Pick one to see what px0 writes: the schedule it pulled out of your words, the tools it went looking for, and which of them can change something outside px0.
0 17 * * 5every Friday, 17:00 localgithub: list pull requestsreadgithub: list pull request reviewsslack: send message to a channelfile · output/digests/pr-{date}.mdpx0 workflows run friday-pr-digestwrite tools are stubbed under --dry-run30 7 * * 1-5weekdays, 07:30 localcalendar: list events in a windowreadgmail: search messagesfile · output/brief-{date}.mdpx0 workflows run morning-brief0 9 * * *daily, 09:00 localsentry: list recent issueslinear: create an issuefile · output/triage-{date}.mdpx0 workflows run spike-to-ticketwrite tools are stubbed under --dry-run0 10 * * 1every Monday, 10:00 localjira: search issues in a sprintslack: send message to a channelfile · output/sprint-{date}.mdpx0 workflows run sprint-statuswrite tools are stubbed under --dry-runEverything px0 knows is stored as plain Markdown in a directory you fully control. You can access all files as-is in your favorite editor, open your knowledge base in Obsidian, grep them, or back them up. Edit a workflow by hand and the next run picks it up, with no compile step in between.
px0 store export copies content and history anywhere.px0 runs why retraces a result to the guidelines, passages, and tool calls behind it, and a fire your laptop slept through still runs when it wakes.Guidelines are Markdown files describing your conventions: how you word a commit message, what your Go reviews check. A workflow that needs one inlines it verbatim, so output comes back sounding like you instead of like a model.
px0 guidelines editAdd posts, papers, docs, and video transcripts as you read them. Text is extracted locally and indexed, so you can ask questions across everything you kept, with the passages it used cited back.
px0 brain ask "…"Every version of every file is kept by px0 itself, so the store works as a bare directory. Hand-edit a workflow and the next run picks it up; the edit still shows up in the log, and still reverts.
px0 changes revert <id>A workflow that can post to Slack is a workflow that can embarrass you. px0 treats the boundary between reading and changing things as the important one, and puts you at every crossing of it.
tools selected (3) 1. read composio:GITHUB_LIST_PULL_REQUESTS 2. read composio:GITHUB_LIST_REVIEWS_FOR_A_PULL_REQUEST 3. write composio:SLACK_SEND_MESSAGE ! this workflow could change things outside px0 SLACK_SEND_MESSAGE Enter accepts all; list numbers to drop (e.g. 2,3); n aborts › keep all?
Every tool is labelled read, write, or destructive using Composio’s own metadata. px0 never infers access from a tool’s name.
The build stops and shows you what it picked. Drop anything by number. Nothing is authorized until you say keep.
px0 preparing an authorization URL grants it nothing. Access exists only after you approve it at the provider.
px0 workflows run --dry-run resolves the real inputs and calls nothing that could post, send, or change anything.
Anything under brain/work/ is excluded from every retrieval (a hard exclusion, not a ranking penalty), so it never reaches a model, a connector, or a workflow output.
One CLI, one directory, one API key for the outside world, and everything else is already on your machine.
Tools route through Composio, so there is exactly one key to set up and no per-app connect command to hunt for. Apps authorize themselves: the first time a workflow needs Gmail, px0 prepares Gmail’s authorization and hands you the URL. You never connect a service you turn out not to need.
px0 shells out to a coding agent CLI in non-interactive mode, reusing its login, its model choice, and its rate limits. There is no separate API key to add and no bill to split.
px0 config modelIt invokes the backend before saving, so a typo’d model name fails there instead of mid-workflow.
When a build leans on a convention you have not written down (a commit format, a review rubric), px0 drafts the guideline from the workflow itself and shows it to you before saving. Reword it once and every run inlines your version, verbatim.
Point Claude Code, or any MCP client, at px0 and it can ask your brain a question, list your workflows, and run one, all over stdio with no SDK involved. Running a workflow stays off until you pass --allow-runs.
SQLite FTS5 with BM25 ships built in, nothing to install. Switch the backend to qmd for hybrid vector search with reranking. It prints the model download size and waits for a yes.
px0 isn’t trying to out-orchestrate CrewAI or out-chat Hermes. It occupies a narrower spot: turn one sentence into a scheduled, editable, local Markdown workflow.
| factor | px0 | Hermes Agent | CrewAI / LangGraph | n8n / Dify | Khoj / PKM Copilot |
|---|---|---|---|---|---|
| Natural language workflow creation | |||||
| Human-editable Markdown workflows | |||||
| Zero-server, local-first operation | |||||
| Native unattended scheduler | |||||
| Local vault / second-brain ingest | |||||
| Dry-run mode for verification | |||||
| Workflow change history & rollback | |||||
| Multi-agent orchestration |
8 of 18 factors shown, against 4 of 7 tools compared.
See the full comparisonTwenty-odd commands, all shaped the same way, and --help on every one of them.
px0 workflows newTurn a sentence into a workflowpx0 workflows runRun one now, or pick from a listpx0 workflows editRevise the request and rebuild itpx0 workflows listEverything you can runpx0 brain addSave a URL, PDF, doc, or transcriptpx0 brain askAnswer a question from your librarypx0 brain searchRetrieve the matching passagespx0 brain reindexRebuild the retrieval indexpx0 guidelines listEvery convention, numberedpx0 guidelines editReword a draft into your voicepx0 guidelines showPrint one, verbatimpx0 guidelines logOne claim’s edit historypx0 runsBrowse, filter, and re-run past runspx0 runs whyHow a run reached its resultpx0 changes listWhat changed, across the storepx0 changes revertUndo a recorded changepx0 daemon installRun workflows on a schedulepx0 tools list --statusWhat can be called, and what is readypx0 statusWhether anything needs attentionpx0 doctorCheck that everything is wired upOne command to install. One sentence to your first workflow. Everything it creates stays on your machine, in files you can read.
curl -fsSL https://px0.ai/install.sh | shpx0 initscaffolds ~/.px0 and asks for your Composio keypx0 workflows newanswer "what do you want px0 to do?"; it writes the filepx0 workflows run <id> --dry-runresolve every input, call nothingpx0 daemon installlet the schedule fire on its ownWant to try it without connecting anything? The brain needs nothing beyondpx0 init. Add a post withpx0 brain add <url> and ask it a question.