Launching soon — get early access:
Agenta

Agenta

Open Source(NOASSERTION)
Verified
AI-Native

The open-source workspace for your agents

SOC 2 Type II
GDPR
Public status page
No training on your data
Global
+7
Last updated: Oct 12, 2026
Open Source
57 views
Visit Site4.5k
More

Quick Answer

Agenta is an open-source workspace for building, evaluating, and deploying AI agents and automations. Agents are built through chat, with version control and human-in-the-loop approvals. The Hobby plan is $0 forever.

About Agenta

Agenta is an open-source workspace for teams to build, evaluate, and deploy AI agents and automations. It lets teams build agents through chat, with versioned agent configuration, tracing, evaluations and human-in-the-loop approval for consequential actions. Agenta is MIT-licensed and self-hostable with Docker Compose or Helm charts, using your own models and credentials with no lock-in.

What Makes It UniqueAI

Agenta uniquely combines an open-source, self-hostable agent workspace with built-in version control for prompts and skills, and human-in-the-loop approval for agent actions. This allows teams to build, test, and deploy AI agents with full transparency and control over their infrastructure and data.

AI-extracted from public sources. May contain errors. Methodology · Report an error

Decision Intelligence

Best For

Engineering teams building code review or operations agents with full control over their stack
Product teams automating research and reporting workflows with human oversight
Teams running AI agents on their own infrastructure
Organizations requiring robust governance and compliance for AI automation
Teams building custom agents through chat
Pricing Overview

Type

Open Source

Billing Cycle

Monthly

Free Trial

No

Credit Card

Not Required

Free Plan

Yes

Dimension Scores

· 7.7 avg

How good it is, across universal quality axes

Ease of Use4/10
Customization10/10
Support8/10
Integration9/10
Compliance & Data Protection7/10
Performance8/10
AI-analyzed from product data·High confidenceHow we score

Task Scores

· 6.7 avg

What it can do, per category it works in · showing 8 of 10 tasks scoring 5+

Monitoring Logging9/10
Workflow Building8/10
Trigger Variety8/10
Scheduling Capability8/10
Api Connectivity8/10
Action Library7/10
Autonomous Execution6/10
Multi Step Chains5/10

Scores are AI-estimated from publicly available data — not an independent test or a verified user rating. How we rank →

Capabilities
Agent
Automation
Code
Data Analysis
Fine-Tuning
Memory
Model Evaluation
RAG
Limitations
  • -Cloud Hobby plan limits team members to two and trace data retention to one week
Fit Score

Complexity

Intermediate

Company Size

Small
Medium
Enterprise

Target Team Size

Small Team
Large Team

Target Skill Level

Intermediate
Expert
Technical Specifications
SDK Available
MCP Compatible
Team Features
Webhook Support
Has Demo
Function Calling
Sandbox Mode
Audit Logs
No Signup (unknown)
Works Offline (unknown)
Requires Host App
Framework
MCP Server
Inference API
Authentication
Single Sign-On
OIDC
Okta
Auth0
Microsoft Entra ID
Google Workspace
OneLogin
Developer Access
API
Public
REST
SDK
agenta
Python
Webhooks→ Docs
Max team seats:2
Deployment:
Self Hosted
Max upload:8MB (PDF), 5MB (Image)
Response time (est.):
Fast
MCP Servers:
Notion
GitHub
HubSpot
Slack
Linear
Google Drive
Compliance, Privacy & Trust
GDPR: Stated by vendor
DPA
SOC 2: Stated by vendor
Type II
HIPAA: No info available
Privacy & data handling
Trains on user data: No
Data retention: Until Deleted
Data deletion: Upon Request
Model isolation: Shared
Copyright policy: User Owns Output
Human review:
Recommended

Compliance audit trail

3 events
  1. GDPR

    Privacy Policy last updated

    8mo ago · 2026-02-05 · source

  2. GDPR

    Data Processing Agreement last updated

    8mo ago · 2026-02-04 · source

  3. Subprocessors

    Sub-processors list last updated

    8mo ago · 2026-02-04 · source

The Model(s) Behind It

Model details — extracted from public vendor sources by our pipeline (Smart Generator + A3 cross-referencing) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

Uses Models
Training Data Provenance
Not disclosed
Relevant to EU AI Act Art. 53 / Annex XI (GPAI)
Integrations & Connections
13 connections
GI
GitHubNative

Trigger agents on pull requests and manage code

LI
LinearNative

Link issues and manage project tasks

PO
PosthogNative

Query funnels and analyze product performance

DO
DockerNative

Deploy and run agents on local machines

DA
DaytonaNative

Run code execution sandboxes for agents

AN
AnthropicAPI

Connect for Claude models via API keys

OP
OpenAIAPI

Connect for ChatGPT models via API keys

OL
OllamaAPI

Connect for local LLM inference

Auto-updated

Trust Score

89/100

Very Good

Based on 10 data signals

Confidence: High

Reflects publicly available data, not an independent audit

Compliance & Verified38/38
VerifiedYes
GDPRYes
SOC 2 reportYes
SOC 2 Type IIYes
Human ReviewYes
Operational25/25
Status PageYes
Data ResidencyEU, US
Reliability0/10

No published data

Company17/17
Company ListedYes
Team Size1-10
FundingSeed
Health—

Not yet checked

AI-Assisted Data

Some details are AI-generated estimates — verify with the vendor.

AI-generated estimate: What Makes Unique

How we source data

AI Governance & Regulatory Disclosures

Legally-sensitive fields — extracted from public vendor sources by our pipeline (Smart Generator + A3 cross-referencing) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

EU AI Act Risk Tier
Unclassified

Switching & Migration

Migration Difficulty
Moderate Effort
Data portable as:
CSV
Support:
Slack
GitHub
Enterprise
Quick Stats
PlatformsWeb, CLI, API
Integrations13+
Launched2023
VerifiedOct 2026
Company & Links
CompanyAgentatech UG
Founded2023
Based inGermany
Last major updateAug 2026
FundingSeed
DocumentationChangelog
All Features
Chat-based agent building
Version control for agents and prompts
Human-in-the-loop approval workflows
Role-based access control (RBAC)
Integrations via built-in tools and MCP servers
Scheduled and event-triggered automations
Trace and monitor agent runs
Self-hosting with Docker Compose or Helm charts
Pricing Plans
Hobby
Free/month
  • 2 team members
  • Unlimited projects
  • Unlimited agents and workflows
  • 5,000 agent runs / month
  • 1-week trace data retention
  • Community support through GitHub Issues
  • Pro
    $29/month
  • Unlimited team members
  • Unlimited schedules and event triggers
  • 10,000 agent runs / month included
  • Additional runs $5 per 10,000
  • Unlimited evaluations
  • 1-month trace data retention
  • Business
    $299/month
  • 10,000 agent runs / month included
  • Additional runs $5 per 10,000
  • Team roles and role-based access control
  • SSO
  • SOC 2 Type II report
  • 3-month trace data retention
  • Enterprise
    Custom
  • Custom usage and trace data retention
  • Audit logs
  • Custom domains
  • Custom security and legal terms
  • Deployment and onboarding support
  • Dedicated support
  • Open source
    Free
  • Unlimited users and projects
  • Unlimited agents and workflows
  • Unlimited schedules and event triggers
  • Build and use agents through chat
  • Bring your own models and credentials
  • Instructions, skills, tools, integrations, and MCP servers
  • Pricing verified from the vendor pricing page.

    User Reviews

    No reviews yet. Be the first to review!

    Who It's For
    4 roles
    Software DevelopersComputer ProgrammersWeb Developers+1 more
    Platform, Content & Languages
    3 content types
    1 languages
    CodeTextDocumentEnglish+7 more

    Content Types

    Code
    Text
    Document

    Accepts

    Text
    Code
    URL
    Document

    Produces

    Text
    Code
    Document
    Languages: English

    Frequently Asked Questions