agentboards.org
Compare/99 vs claudecode.nvim

99vsclaudecode.nvim

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

99
ThePrimeagen · IDE extension
#219OSS
Panel
5.6
3 spec wins
Reliability
4.8
Usefulness
5.5
Cost
7.5
Longevity
4.7

“It ships for macOS and Linux only, which is one way to make sure Windows developers keep hand-coding.”

claudecode.nvim
Coder · IDE extension
#196OSSMCP
Panel
6.0
1 spec wins
Reliability
5.8
Usefulness
5.7
Cost
7.5
Longevity
5.0

“The interface is ClaudeCodeSend and ClaudeCodeAdd, because in Neovim even the agent gets a colon command.”

Spec by spec

Spec99claudecode.nvim
Architecture
CategoryIDE extensionIDE extension
Runslocallocal
Platformsmacos, linuxmacos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientNoNo
MCP serverNoYes
Capabilities
Runs terminal commandsNoNo
Multi-file editsYesNo
Git operationsNoNo
Browser controlNoNo
Sandboxed executionNoNo
Multi-agent orchestrationNoNo
Headless / CI modeNoNo
Models
BackboneClaude Sonnet via OpenCode, Claude CodeClaude
Bring your own modelYesModel choice is delegated to the configured provider CLI; if no model is set the provider's default is used. No
Local modelsNoNo
Cost
Pricing modelbyokbyok
Starts atn/a$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseunspecifiedMIT
GitHub stars4,7443,091

Which one would each critic pick

Critic99claudecode.nvimPick
El Juez——not enough reviews
El Amigo6.36.3no preference
El Crítico5.55.5no preference
El Profesor5.56.5claudecode.nvim — The direction is inverted: the editor runs the server and the agent is the client, so context is pushed by the human rather than retrieved by the model.
La Inversora5.05.8claudecode.nvim — Owned by a company whose actual product is self-hosted development infrastructure, which makes this developer marketing rather than a line of business.
La Jefa4.54.5no preference
El Hacker7.07.5claudecode.nvim — MIT, pure Lua on the editor's own event loop with one plugin dependency, and no model choice at all because the backbone is fixed to one vendor.

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.