NeoSignal
← Back to agents
O

OpenHands

Agents
84

Open-source platform for AI software developers with sandbox execution environment

Leading open-source software development agent platform

Metrics

licenseMIT
providerAll Hands AI
agent typecoding
github stars42,000
base model requirementsclaude-3.5-sonnet, gpt-4, llama-3
tool integrations count18

Score Breakdown

adoption85
tool use85
memory context82
self reflection80
planning reasoning86

Compatibility

1111111190111111118811111111851111111182

Scoring Methodology

planning_reasoning25% weight

Task decomposition and strategic execution capabilities

Source: AgentBench, WebArena, SWE-bench Verified

tool_use25% weight

Intent recognition, function selection, and execution accuracy

Source: ToolBench, API-Bank, Berkeley Function Calling Leaderboard

memory_context20% weight

Long-context handling and information retention

Source: LongBench, RULER, InfiniteBench

self_reflection15% weight

Error recognition and behavior adjustment

Source: ReAct benchmark, Reflexion evaluation

adoption15% weight

GitHub stars, community usage, ecosystem maturity

Source: GitHub API, PyPI downloads, Stack Overflow activity

Related Signals

Multi-Agent Frameworks See Enterprise Adoption

Agents1d ago

Enterprise teams are increasingly adopting multi-agent frameworks like CrewAI and AutoGen for complex workflows, moving beyond single-agent implementations to orchestrated agent teams.

87

Data Sources

github.comdocs.all-hands.dev
Last updated: December 24, 2025