agentboards.org
Compare/Aide vs Void

AidevsVoid

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

Aide
CodeStory · AI-native IDE
#275OSS
Panel
3.0
0 spec wins
Reliability
3.0
Usefulness
3.0
Cost
4.3
Longevity
1.7

“An IDE built around a proactive agent, now proactively doing nothing.”

Void
Void · AI-native IDE
#213OSSMCP
Panel
3.7
3 spec wins
Reliability
2.8
Usefulness
3.3
Cost
7.0
Longevity
1.5

“Archived in June 2026, which makes it the only IDE on this board whose roadmap is guaranteed not to change.”

Spec by spec

SpecAideVoid
Architecture
CategoryAI-native IDEAI-native IDE
Runslocallocal
Platformsmacos, linux, windowsmacos, windows, linux
Context windownot documentednot documented
Protocols
MCP clientNoYes
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsNoNo
Browser controlNoNo
Sandboxed executionNoNo
Multi-agent orchestrationNoNo
Headless / CI modeNoNo
Models
BackboneClaude, GPTClaude, GPT, Gemini, Grok, DeepSeek, Qwen, Llama, Mistral, Gemma
Bring your own modelYesYes
Local modelsNoYes
Cost
Pricing modelbyokbyok
Starts atn/a$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseAGPL-3.0Apache-2.0
GitHub stars2,19228,781

Which one would each critic pick

CriticAideVoidPick
El Juez——not enough reviews
El Amigo3.04.0Void — Nobody should adopt Void now; if you want an open editor agent with your own models, run Cline or Kilo Code inside stock VS Code.
El Crítico2.83.3Void — An agent mode with terminal execution and no sandbox, inside an editor that will never be patched again, is the failure mode and it is permanent.
El Profesor3.33.8Void — Two sound design decisions, a VS Code fork and direct provider connections, and one structural weakness: a fork inherits its upstream's cadence only while someone merges it.
La Inversora2.82.5Aide — CodeStory intended to sell hosted inference on a subscription, that did not hold, and the company now presents itself as a research lab, which is the pivot in its purest form.
La Jefa2.52.5no preference
El Hacker3.86.0Void — Apache-2.0, direct to Ollama and vLLM with no vendor relay, MCP client, and archived, so I could fork it and be the sole maintainer of a VS Code fork, which is a job.

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.