Agenta: a self-hosted workspace for building agents that run on a schedule
Agenta is a workspace where you and your team build agents and automations.
At a glance
- What is it?
- Agenta packages an agent builder, a shared workspace, background scheduling and run tracing into one self-hosted TypeScript application. It is aimed at teams that want to keep using a Claude or ChatGPT subscription instead of metered API billing, and the trade-off is that you own the runtime.
- Who is it for?
- Adopt Agenta if you already pay for a Claude or ChatGPT subscription, want agents that run on a schedule against Gmail, Slack, Notion or GitHub, and are willing to operate the runtime yourself. Do not adopt it if you need a permissively licensed codebase you can fork without reading a lawyer's summary, or if you have no capacity to run and upgrade a self-hosted service.
- Can I use it commercially?
- Check first. The repository uses a licence we do not classify automatically, so read its LICENSE file before any commercial use.
- Is it still maintained?
- Yes. The repository last received commits 2 days ago.
- What is it written in?
- Mainly TypeScript, according to GitHub's language statistics.
Answers come from the project's GitHub data, last synced on November 13, 2026, and from our analysis. They are not legal advice.
Star history
- Agenta-AI/agenta4,906 ★ · +162
| Repository | 2026-09-11 | 2026-11-13 |
|---|---|---|
| Agenta-AI/agenta | 4.7k | 4.9k |
162 Stars in the last 63 days, measured from the daily GitHub snapshot. Compare with other projects
Editorial analysis
The problem Agenta targets: agents that live in one person's terminal
Most agent tooling today produces something that only its author can run. The agent is a folder of prompts and scripts on one laptop, tied to one model, invoked by hand. Agenta's pitch is that the agent becomes a shared artifact: you build it by chatting with it, you connect the apps it needs, and you share it with your team. The second half of the pitch is recurrence. For recurring work, Agenta offers automations, where agents run on a schedule or when an event occurs in a connected app. That is a different product category from a chat client. It is closer to a job runner whose jobs happen to be language-model agents, with every run traced and every cost tracked. The audience is a small team that has already decided agents are useful and now needs them to survive past the demo, without standing up a bespoke orchestration layer around a CLI.
How an agent is defined: AGENTS.md, skills and MCP servers
The README says you build agents by chatting with them: you describe the work, connect the apps they need and improve them through feedback, and agents keep memory, create and refine their own skills and update their own instructions. Model choice is broad: hosted models through an API, or self-hosted models with Ollama, and agents can run on a Claude or ChatGPT subscription you already pay for. The repository is primarily TypeScript, with a Python package published on PyPI under the name agenta, which suggests the server side and the SDK do not share a language.
Background agents and the permission model that makes them tolerable
An agent that runs on a schedule without a human watching is an agent that can send the wrong email at 3am. Agenta's answer is per-tool permissions. The README states that you set exact permissions per agent: which tools it can use, and whether it can read or write with them, and you decide what it does on its own and what goes through you first. That is more than a binary allow or deny, and the interesting part is the work that goes through you first. How long an approval can pend, what happens if nobody responds, and how approvals are delivered are the questions that decide whether the model works in practice. Integrations arrive two ways: directly through MCP, or through Composio, which the README describes as covering more than 1,000 apps including Gmail, Slack, Notion and GitHub. Composio is a third-party dependency, so the reach of your integrations is bounded by someone else's catalogue and pricing, not by Agenta alone.
Getting it running: cloud first, self-hosting for the subscription trick
The README offers two paths. One is Agenta Cloud, linked at cloud.agenta.ai. The other is self-hosting: the README calls Agenta open source and self-hostable, and separately says you can run agents on the Claude or ChatGPT subscription you already pay for instead of metered API billing. That is the single most concrete reason to pick Agenta over a hosted alternative, and it is also the reason the self-hosted path carries the operational burden. The honest position is that the setup instructions live in the documentation at agenta.ai/docs, and the repository also publishes a Python package on PyPI, which is the likely entry point for programmatic use. Treat the docs, not this article, as the source for exact commands. The project ships frequently: three releases, v0.128.0 through v0.128.2, landed between 30 October and 2 November 2026, with the latest push to main on 2 November 2026.
The licence is the first thing to check, not the last
The repository metadata reports the licence as NOASSERTION, which means GitHub's classifier could not map the LICENSE file to a known identifier. The README, meanwhile, calls Agenta open source and self-hostable, which is not a licence identifier. Until you open the LICENSE file in the repository and read it, you do not know the terms. This is not a hypothetical concern for a product whose selling point is self-hosting. If your organisation's policy requires an OSI-approved permissive licence, or if you intend to embed Agenta in something you distribute, the classifier result is a stop sign until resolved. I am not giving legal advice here; the point is narrower. The licence is not classified, and the only way to settle it is to read the file. Do that before you spend a sprint integrating MCP servers against it.
Where Agenta is the wrong tool
The failure mode that the README implies but does not dwell on is operational. Agenta is a self-hosted service, and the team-access feature, role-based access control and run tracing all live inside that service. If nobody on your team will own upgrades, you will be running an old build. The release cadence gives a sense of the surface area: releases on 30 October and twice on 2 November 2026, with a version number already past 0.128. That is a lot of version churn for a system you are expected to keep available for scheduled jobs. Second, the approval workflow for background agents is only as good as its notification path. If your scheduled agents touch production systems, verify that path before you let one run unattended.
How it differs from wiring agents together yourself
The obvious alternative is composition: take an agent CLI you already use, wrap it in a scheduler such as cron or a workflow engine, and store prompts in a git repository. That approach gives you total control and no new dependency, and for a single developer running two jobs it is probably the right answer. The difference in approach is what Agenta adds on top of the runtime. A scheduler runs a command; Agenta shows each agent's configuration, its versions and every change, and traces every run. A scheduler has no concept of per-tool permissions or human approval; Agenta does. A scheduler gives you no shared workspace where a teammate can open the same agent and continue the work. You can build all of that yourself, and teams do, but you are then maintaining an orchestration layer whose only user is your own company. Agenta's bet is that this layer is generic enough to share. The counter-bet is that a general layer will not fit your specific approval rules, and you will end up forking it. Which bet wins depends on how unusual your workflow is.
Maintenance cost and what to verify before you commit
Two cost centres are visible. The first is upgrades. Between 30 October and 2 November 2026 the project published three releases, and the version number sits above 0.128, which tells you the API and configuration surface are still moving. Plan for a regular upgrade cycle rather than a set-and-forget deployment, and read the release notes for each bump before applying it. The second is integration dependency. Composio provides the 1,000-plus app catalogue, so your Gmail, Slack, Notion and GitHub connections route through a third party even when Agenta itself runs on your hardware. That is a supply chain you should name explicitly in any internal review. Before adopting, verify three things: the actual licence text in the repository, since the metadata does not identify it; the behaviour of a pending human approval when a scheduled agent blocks on it; and the upgrade procedure, because you will be using it often. If those three checks come back clean for your team, Agenta is a reasonable way to keep agent work on a subscription you already pay for instead of a meter that runs while you sleep.
Editorial conclusion
Adopt Agenta if you already pay for a Claude or ChatGPT subscription, want agents that run on a schedule against Gmail, Slack, Notion or GitHub, and are willing to operate the runtime yourself. Do not adopt it if you need a permissively licensed codebase you can fork without reading a lawyer's summary, or if you have no capacity to run and upgrade a self-hosted service. Before committing, open the LICENSE file and confirm the actual terms.
Frequently asked questions
What is agenta?
An open-source workspace for building and running agents. You build agents by chatting with them, describing the work, connecting the apps they need and improving them through feedback, then share them with your team or run them in the background on a schedule or on an event from a connected app. Every run is traced, and you can see each agent's configuration, its versions and every change.
what is agenta ai
It is the hosted and self-hostable form of that workspace. Agenta Cloud is linked at cloud.agenta.ai, the README calls the project self-hostable, and agents can run on an existing Claude or ChatGPT subscription instead of metered API billing. Models can be hosted through an API or self-hosted with Ollama.
How do I self-host Agenta?
The README describes Agenta as open source and self-hostable, on your models with your data on your servers; setup instructions are in the documentation at agenta.ai/docs.
Can Agenta background agents act without approval?
Yes, within limits you set. You set exact permissions per agent, including which tools it can use and whether it can read or write with them, and you decide what it does on its own and what goes through you first. Automations run agents on a schedule or when an event occurs in a connected app.
Official sources
Add this badge to your README
If you maintain this project, the badge below links readers to this analysis and shows its maintenance status from the daily GitHub snapshot. Paste the markdown into your README; add ?metric=license or ?metric=stars to the image URL for a different field.
[](https://hysenlabs.com/projects/agenta-ai-agenta)Star history chart for your README
[](https://hysenlabs.com/projects/agenta-ai-agenta)Was this useful?