agentboards.org
Compare/Notebook Intelligence vs ACP Client for VS Code

Notebook IntelligencevsACP Client for VS Code

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

Notebook Intelligence
plmbr · IDE extension
#76OSSMCP
Panel
6.9
2 spec wins
Reliability
6.2
Usefulness
7.0
Cost
8.7
Longevity
5.7

“It adds autocomplete to notebooks, so cell forty-seven can now be wrong considerably faster.”

ACP Client for VS Code
Jun Han · IDE extension
#41OSS
Panel
7.3
1 spec wins
Reliability
7.0
Usefulness
6.8
Cost
8.2
Longevity
7.0

“It supports eleven coding agents, one at a time, which is a fair summary of the last two years.”

Spec by spec

SpecNotebook IntelligenceACP Client for VS Code
Architecture
CategoryIDE extensionIDE extension
Runslocallocal
Platformsmacos, linux, windowsmacos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientYesNo
MCP serverNoNo
Capabilities
Runs terminal commandsYesThe nbi-command-execute tool runs shell commands in the Agent UI or JupyterLab terminal, and is documented as arbitrary code execution as the user. YesThe extension runs the commands the agent requests and displays their output; the agent loop itself lives in the ACP agent.
Multi-file editsYesFiles are limited to the Jupyter root directory, through the notebook, Python file and file editors. Yes
Git operationsNoNo
Browser controlNoNo
Sandboxed executionNoNo
Multi-agent orchestrationNoNoEleven agents are pre-configured but only one is active at a time, with quick switching between them.
Headless / CI modeNoNo
Models
BackboneGitHub Copilot, OpenAI-compatible, LiteLLM, Ollama, Anthropic ClaudeGitHub Copilot, Claude Code, Gemini CLI, Qwen Code, Auggie CLI, Qoder CLI, Codex CLI, OpenCode, OpenClaw, Kiro CLI, Hermes Agent
Bring your own modelYesYes
Local modelsYesOllama is a first-class provider adapter alongside Copilot and OpenAI- or LiteLLM-compatible endpoints. No
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseGPL-3.0MIT
GitHub stars347391

Which one would each critic pick

CriticNotebook IntelligenceACP Client for VS CodePick
El Juez——not enough reviews
El Amigo7.37.5ACP Client for VS Code — Pick it if you keep wanting to try the new thing; pick a vendor's own extension if you have already decided and you like their panel.
El Crítico6.57.0ACP Client for VS Code — It serves the agent's file writes against your workspace and runs the commands it asks for under a configurable auto-approve policy.
El Profesor7.07.8ACP Client for VS Code — Every ACP JSON-RPC message can be inspected in a traffic log, which makes a disagreement about whose fault a failure is answerable rather than rhetorical.
La Inversora6.56.8ACP Client for VS Code — The value here is borrowed: it is worth exactly as much as the protocol is adopted, and 372 stars for a free extension is respectable and unmonetisable.
La Jefa6.07.3ACP Client for VS Code — One marketplace identifier in the extension allowlist we already maintain and sixty engineers have it when the editor restarts; that is a memo, not a project.
El Hacker8.07.3Notebook Intelligence — GPL-3.0, Ollama as a first-class adapter, and a mode that shells out to the Claude Code CLI so its tools, skills and MCP servers arrive inside JupyterLab.

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.