OpenHands

OpenHands

Open Source(MIT)
Verified
AI-Native
Most customizable

The open platform for cloud coding agents

Dedicated tenancy
Open Weights
Works offline
Global
Agent-Ready
+10
Autonomous
Last updated: Oct 27, 2026
Open Source
Visit Site84.5k
More
openhands.dev

Quick Answer

OpenHands is an open-source, MIT-licensed platform for running coding agents locally, in its own cloud, or self-hosted inside your VPC. It is model-agnostic: bring your own LLM key and use Anthropic, OpenAI, Bedrock or another provider, with MCP support for connecting internal tools. Enterprise deployments add RBAC, per-project budget limits, containerized sandboxes, prompt-injection detection and full audit logs. The SaaS Individual tier is free, using your own key or providers at cost.

About OpenHands

OpenHands is an open-source, LLM-powered software agent platform for developers that executes real engineering work, not just code suggestions. It runs autonomous agents that plan, write, and apply changes across your codebase, helping teams complete complex tasks end-to-end. Designed for enterprise software development at scale, it offers flexible deployment options and robust governance.

AI-extracted from public sources. May contain errors. Methodology · Report an error
What Makes OpenHands UniqueAI

OpenHands provides a control plane for every layer of the agent stack, offering fine-grained access control, LLM gateway, budgeting, and prompt injection detection within containerized sandbox runtimes, which is unique for an open-source coding agent platform.

Decision Intelligence

Best For

AI
Platform teams automating engineering workflows at scale
Teams building internal developer platforms or AI-powered tooling
Enterprises managing large or legacy codebases and mission-critical software systems
Developers building agents that work with code for one-off or routine maintenance tasks
Organizations with strict data security, compliance, and governance requirements
Pricing Overview

Type

Open Source

Starting Price

$0/mo

Free Trial

No

Credit Card

Not Required

Free Plan

Yes

Dimension Scores

· 6.4 avg

How good it is, across universal quality axes

Ease of Use3/10
Customization10/10
Support7/10
Integration9/10
Compliance & Data Protection3/10
Performance5/10
Planning Quality8/10
AI-scored from up to 37 public sources, reviewed by a person·High confidenceHow we score

Task Scores

· 7.2 avg

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

Task Decomposition8/10
State Management8/10
Observability8/10
Scalability Throughput8/10
Role Definition7/10
Agent Coordination7/10
Workflow Orchestration7/10
Tool Use Delegation7/10
Inter Agent Communication6/10
Error Recovery6/10

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

Capabilities
Code
Code Review
Automation
Agent
Memory
Search
Browsing
Categories
Code Assistant
Automation Agents
Developer Platform
Orchestration Agents
Fit Score

Complexity

Advanced

Company Size

Solo
Small
Medium
Enterprise

Team Size

Individual
Large Team

Skill Level

Expert
Features
Autonomous agent execution for engineering tasks
Containerized sandbox runtime for safe autonomy
Prompt injection detection with automatic halt
Full audit logs for every agent action
Model-agnostic architecture with BYOK support
Large Codebase SDK for complex codebases
RBAC and budget controls for enterprise governance
Integrations with GitHub, GitLab, Slack, Jira, Linear, and more
Technical Capabilities
SDK Available
MCP Compatible
Multi-Agent
Human-in-Loop
Team Features
Webhook Support
Has Demo
Function Calling
Sandbox Mode
Audit Logs
No Signup (unknown)
Works Offline
Requires Host App
Framework
MCP Server
Digital Employee

Deployment

Hybrid
A2A Protocol:
MCP
Authentication
Single Sign-On
SAML
Okta
Microsoft Entra ID
Google Workspace
OAuth
GitHub
Developer Access
Webhooks
Sandbox
Login required
HITL mode:
Approve
Compliance, Privacy & Trust
GDPR: No info available
SOC 2: No info available
HIPAA: No info available
Trains on user data: Yes
Free tier
Opt-out available
Data deletion: 30 Days
Model isolation: Dedicated
Copyright policy: User Owns Output
Human review:
Recommended
Tech Specs
Response time (est.):
Moderate
MCP Servers:
Fetch
Filesystem
Notion

The Model(s) Behind It

Model details — extracted from public vendor sources by our pipeline (AI extraction plus a source check) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

Uses Models

Underlying Model Benchmarks

Third-party leaderboard scores for the AI model(s) powering this — including price & speed. These describe the underlying model, not the product's own metrics.

llm-coding

SWE-bench Verified
Princeton + OpenAI 2024 · SWE-bench
71.8
72th pct

Best submission: "OpenHands + GPT-5" (2025-08-07)

11/1/2026·source

Scores from official leaderboards or vendor-reported. Percentile is cross-benchmark normalized when populated by an aggregator. See methodology.

Model Weight Availability
Fully open (Apache/MIT)
Training Data Provenance
Not disclosed
Relevant to EU AI Act Art. 53 / Annex XI (GPAI)
Supported Tools
Web Browser
Code Interpreter
Terminal
File System
Web Search
Pricing Plans
Free
Free

Pricing verified from the vendor pricing page.

Looking for more OpenHands alternatives?

Explore our complete list of alternatives with filters for free, cheaper, and higher-rated options.

View All Alternatives

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
2 content types
9 languages
CodeTextEnglishSpanish+13 more

Content Types

Code
Text

Accepts

Text
Code
API

Produces

Code
Text
API
Languages: English, Spanish, French, Japanese, Korean, Portuguese, Russian, Chinese, German

Frequently Asked Questions

What can OpenHands do?

OpenHands can: Autonomous agent execution for engineering tasks, Containerized sandbox runtime for safe autonomy, Prompt injection detection with automatic halt, Full audit logs for every agent action. Best for: Platform teams automating engineering workflows at scale.

How much does OpenHands cost?

OpenHands is open source and free to self-host. Cloud hosting options may have separate pricing.

Is OpenHands free?

Yes, OpenHands is open source and free to self-host. Managed hosting may carry separate costs.

What makes OpenHands unique?

OpenHands provides a control plane for every layer of the agent stack, offering fine-grained access control, LLM gateway, budgeting, and prompt injection detection within containerized sandbox runtimes, which is unique for an open-source coding agent platform.

Does OpenHands have an API?

Yes, OpenHands offers a public API for developers to integrate its capabilities into custom applications and workflows.

What platforms does OpenHands support?

OpenHands is available on web, CLI, and API.

What languages does OpenHands support?

OpenHands supports 9 languages including English, Spanish, French, Japanese, Korean, and more.

Does OpenHands work offline?

Yes, OpenHands supports offline use — you can run it without an active internet connection.

Who is OpenHands for?

OpenHands is designed for Platform teams automating engineering workflows at scale; Teams building internal developer platforms or AI-powered tooling; Enterprises managing large or legacy codebases and mission-critical software systems.

Trust Score

75/100

Very Good

Based on 11 data signals

Confidence: High

Reflects publicly available data, not an independent audit

Compliance & Verified38/38
VerifiedYes
Open-source licenseMIT
Human ReviewYes
Human-in-the-loopYes
HITL TypeYes
Operational25/25
Data ResidencyUS
Reliability0/10

No published data

Market Proof10/10
Notable CustomersTikTok, VMware, Roche
Company17/17
Company ListedYes
Team Size11-50
User Base1M-10M
FundingSeries A
Health—

Not yet checked

AI-Assisted Data

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

AI-generated estimate: Best For, What Makes Unique

How we source data

AI Governance & Regulatory Disclosures

Legally-sensitive fields — extracted from public vendor sources by our pipeline (AI extraction plus a source check) 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
Quick Stats
Agent TypeAutonomous
MemoryLong Term
PlanningAdvanced
PlatformsWeb, CLI, API
User Base1M-10M
LaunchedMar 2024
VerifiedOct 2026
Company & Links
Company NameAll Hands AI
Founded2024
Based inUnited States
Last major updateAug 2026
FundingSeries A · $24M
Funding rounds
1 round
Valuation
Estimate · dealroom.co
DocumentationChangelog