Agenta-AI /agenta
Agenta is a workspace where you and your team build agents and automations.
★ 4,912⑂ 732👁 29⑃ 6,183● 1,933▤ 512
+1
日增长
4,912
stars
732
forks
29
watchers
6,183
prs
1,933
issues
512
releases
README
The open-source workspace for your agents and your team
Build AI coworkers by chatting. Share them with your team. Talk to them in Slack, WhatsApp or Telegram.
---
---
Documentation •
Website •
Agenta Cloud
---
---
What is Agenta?
Agenta is an open-source workspace where you build specialized agents that automate and augment your work.
You build agents by chatting with them. You describe the work, connect the apps they need, and improve them through feedback.
You can work with your agents in the web app, or talk to them where you already are: Slack, Telegram or WhatsApp Business.
For recurring work, you can create automations. Your agents run on a schedule or when an event occurs in a connected app, and you can see what every run did.
Tutorials
Step-by-step videos. Each one builds a real agent from scratch, by chatting.
Build your first AI coworker · 10 min
Connect your tools, give the agent a role, save a skill, and automate sales-call prep.
Track your competitors while you sleep · 7 min
Give an agent web search, schedule it for every Monday, and get the digest in Gmail.
Build an inbound outreach agent with no code · 17 min
Research every new lead, qualify it, and send a personalized reply.
More tutorials on our YouTube channel.
Why use Agenta?
Agenta is the wrong tool if you are looking for:
- an agentic development environment for writing code, like ocra, Claude Code or OpenCode.
Agenta is built for the work around and beyond code: IT ops, GTM, HR, legal, finance, support...
- a single-user personal assistant, like openclaw or Hermes.
Agenta is built for teams: agents are shared, multi-user, and run where the team works (e.g. Slack).
- a low-code workflow builder, like n8n or Zapier.
In Agenta you do not draw workflows. You build autonomous agents that figure out the steps and solve problems on their own.
Agenta is built for work, with professionals in mind from day one. That means:
1. Multiplayer by default. Give your team (or customers) access, set roles, and share agents and chat sessions.
2. Transparent. You see each agent's configuration, its versions, and every change.
3. Controllable, with you in the loop. You set exact permissions per agent: which tools it can use, and whether it can read or write with them. You decide what it does on its own and what goes through you first.
4. Secure. Each session runs in its own sandbox, isolated from every other. Model credentials are never seen by the agent.
5. Auditable. Every run is traced. Every cost is tracked.
6. Yours. Open source, self-hostable, on your models, with your data on your servers.
7. For technical and non-technical teammates. You build agentsTop issues
#6443(bug) The provider drawer lists 34 models for a key that OpenAI just rejected7 comments · 2026-09-01#7225[Feature] Trajectory evaluator: score tool-call sequences, not just final outputs5 comments · 2026-09-28#6283Do not rename the agent after the first rename4 comments · 2026-08-25#5620(bug) A plain .zip attachment is stored with the Word-document media type4 comments · 2026-08-01#4911(feat) Harden user-MCP http SSRF guard (DNS rebinding + redirects) for OSS default-on4 comments · 2026-06-28#8265fix(frontend): a new sign-up can stay on "Loading home" until a reload3 comments · 2026-11-11#8243Helm: cron jobs call http://api:8000, which does not resolve in the cluster3 comments · 2026-11-09#7951(bug) Approving multiple calls to the same tool leaves most calls unexecuted3 comments · 2026-10-31
Discussions
#7601Multilingual numeric evaluator without a judge model (Custom Code Evaluator, standard library only)0 comments · 2026-10-14#4134Disable 0.0.0.0 listening1 comments · 2026-04-11#4123LLM-as-a-judge available models1 comments · 2026-04-08#4011Updates to the Evaluator Playground — Evaluate LLM-as-a-Judge and Other Evaluators0 comments · 2026-03-16#4010Annotation Queue to Label Test Sets0 comments · 2026-03-16#4009Annotation Queues for Traces0 comments · 2026-03-16#3784Add usage limits for traces (hard and soft caps)0 comments · 2026-02-19#3706Webhooks for Deployment Linked to CI1 comments · 2026-02-10
Latest release
v0.128.13 v0.128.13 2026-11-13What's Changed [docs] Update API reference docs by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/8248 fix(frontend): Show agent-created automations without a reload by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/8267 fix(api): give workflow reference tools a long time limit by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/8271 fix(runner): let a tool's own time budget extend the tool-call watchdog by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/8277 [release] v0.128.13 by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/8