agentboards.org
Compare/AgentDock vs eve

AgentDockvseve

Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.

AgentDock
AgentDock · Agent framework
OSS
Panel
5.8
0 spec wins
Reliability
5.0
Usefulness
5.2
Cost
8.0
Longevity
4.8

“The install instructions are a git clone, which is the most honest version number a beta has ever published.”

eve
Vercel · Agent framework
OSS
Panel
5.8
1 spec wins
Reliability
5.2
Usefulness
4.8
Cost
7.0
Longevity
6.0

“An agent whose entire configuration is a directory, from a company whose entire product is a directory.”

Spec by spec

SpecAgentDockeve
Architecture
CategoryAgent frameworkAgent framework
Runslocal, cloudlocal
Platformsmacos, linux, windows, webmacos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientNoNo
MCP serverNoNo
Capabilities
Runs terminal commandsNoNo
Multi-file editsNoNo
Git operationsNoNo
Browser controlNoNo
Sandboxed executionNoNo
Multi-agent orchestrationNoNo
Headless / CI modeNoNo
Models
BackboneAnthropic, OpenAI, other providers via the provider registryany AI Gateway model
Bring your own modelYesYes
Local modelsNoNo
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITApache-2.0
GitHub stars1,7635,443

Which one would each critic pick

CriticAgentDockevePick
El Juez——not enough reviews
El Amigo5.86.0eve — Pick it if you want an assistant that lives in a repository and answers in Slack; pick Mastra when you need a framework that will actually reach into your codebase.
El Crítico5.54.8AgentDock — The core is not published as a versioned package, so installing it means cloning a repository and pinning a commit, and the README carries a beta badge.
El Profesor6.56.0AgentDock — The orchestration layer varies which tools are exposed as the conversation progresses, which treats the tool set as state rather than as a fixed constant.
La Inversora5.36.0eve — 4,971 stars in three months from a company whose inference routing service supplies the model identifiers, which makes the open framework a very well-built funnel.
La Jefa4.85.5eve — Nothing to buy for sixty engineers, and the spend arrives metered through a routing service, while messaging channels and schedules make this an internal bot platform.
El Hacker6.86.3AgentDock — MIT and provider-independent through a registry I can extend, but MCP is on the roadmap rather than in the code, so my existing servers stay outside.

Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.

Want a third column? The compare tool handles any two agents. Three-way comparisons are on the roadmap once the spec rows are all verified.