agentboards.org
Compare/amux vs Netclode

amuxvsNetclode

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

amux
Mixpeek · Agent harness
Panel
5.8
3 spec wins
Reliability
5.2
Usefulness
6.0
Cost
7.5
Longevity
4.3

“You can peek into a peer's terminal before interrupting it, which is more courtesy than most colleagues extend.”

Netclode
angristan · Agent harness
Panel
5.7
2 spec wins
Reliability
5.8
Usefulness
6.7
Cost
6.3
Longevity
3.8

“The workspace lives in object storage, so a paused session costs only storage, making this the rare agent that gets cheaper when ignored.”

Spec by spec

SpecamuxNetclode
Architecture
CategoryAgent harnessAgent harness
Runslocalcloud, sandbox
Platformsmacos, linux, webmacos, linux, web
Context windownot documentednot documented
Protocols
MCP clientNoNo
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYesFiles are changed by the Claude Code, OpenCode, Copilot or Codex SDK running inside the microVM.
Git operationsNoYes
Browser controlNoNo
Sandboxed executionNoYes
Multi-agent orchestrationYesNo
Headless / CI modeYesCron-style schedules and self-pacing autonomous loops run unattended; no CI integration is documented. YesA GitHub bot spins up a sandbox on an @mention in an issue or pull request and auto-reviews Dependabot and Renovate updates.
Models
Backbonevia managed agents (Claude Code, Codex, Gemini CLI, OpenCode, Ollama)Claude Code SDK, OpenCode, Copilot, Codex SDK, Anthropic, OpenAI, Mistral, Ollama
Bring your own modelYesYes
Local modelsYesOllama is listed among the agent runtimes a worker can use. YesOllama is listed as an optional provider for running models on your own GPU.
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesNo
Bring your own keyYesYes
Openness
Open sourceNoNo
LicenseMIT with Commons Clauseunspecified
GitHub stars513257

Which one would each critic pick

CriticamuxNetclodePick
El Juez——not enough reviews
El Amigo6.36.0amux — Pick amux if you want a fleet of agents working overnight with a board to wake up to; pick Crystal if you would rather supervise a couple of them yourself.
El Crítico5.55.3amux — The watchdog restarts crashed sessions and replays the last message, so a failing agent is resurrected rather than reported and the failure never surfaces.
El Profesor6.36.5Netclode — A warm pool of pre-booted microVMs answers the latency objection to strong isolation, and an event log lets a client reconnect without losing state.
La Inversora5.05.0no preference
La Jefa5.05.3Netclode — Per-repository scoped tokens from a forge app, and a proxy that keeps provider keys out of the sandbox: two controls I usually have to ask for.
El Hacker6.56.0amux — One Rust binary with a SQLite store, model or provider swappable mid-run without losing context, and Ollama listed among the worker runtimes.

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.