agentboards.org
Compare/Augment Code vs ACP Client for VS Code

Augment CodevsACP 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.

Augment Code
Augment Code · IDE extension
#32MCP
Panel
6.3
6 spec wins
Reliability
6.3
Usefulness
7.0
Cost
5.2
Longevity
6.5

“Charges the model's list price plus a 40 percent service fee, which is at least a markup you can read without a lawyer.”

ACP Client for VS Code
Jun Han · IDE extension
#41OSS
Panel
7.3
6 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

SpecAugment CodeACP Client for VS Code
Architecture
CategoryIDE extensionIDE extension
Runslocal, cloudlocal
Platformsmacos, linux, windowsmacos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientYesNo
MCP serverYesNo
Capabilities
Runs terminal commandsYesYesThe extension runs the commands the agent requests and displays their output; the agent loop itself lives in the ACP agent.
Multi-file editsYesYes
Git operationsYesNo
Browser controlNoAuggie ships web-search and web-fetch tools only, so it can read pages but cannot drive a browser; browser automation requires adding a third-party MCP server. No
Sandboxed executionYesCosmos cloud environments are built from a Docker base image you pick from any public registry and each session starts from a fresh isolated snapshot; the local Auggie CLI has no sandbox, and self-hosted daemons isolate only via per-session Git worktrees. No
Multi-agent orchestrationYesNoEleven agents are pre-configured but only one is active at a time, with quick switching between them.
Headless / CI modeYes`auggie --print` runs non-interactively for scripts and CI, and Augment publishes GitHub Actions wrappers for PR descriptions and reviews. No
Models
BackboneClaude, GPT, Gemini, GLM, KimiGitHub Copilot, Claude Code, Gemini CLI, Qwen Code, Auggie CLI, Qoder CLI, Codex CLI, OpenCode, OpenClaw, Kiro CLI, Hermes Agent
Bring your own modelNoModel choice is limited to Augment's curated list via /model or --model; no custom base URL, LLM gateway, or Bedrock/Vertex/Azure deployment is documented. Yes
Local modelsNoNo local or OpenAI-compatible endpoint is documented; inference always runs through Augment. No
Cost
Pricing modelmixedbyok
Starts at$20/mo$0/mo
Free tierNoYes
Bring your own keyNoLLM usage is billed by Augment as provider cost plus a 40% service fee; supplying your own provider key or cloud account is not documented. Yes
Openness
Open sourceNoYes
LicenseproprietaryMIT
GitHub stars283391

Which one would each critic pick

CriticAugment CodeACP Client for VS CodePick
El Juez——not enough reviews
El Amigo7.07.5ACP 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 Crítico6.07.0ACP 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 Profesor6.57.8ACP 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 Inversora7.06.8Augment Code — Publishing a 40 percent service fee is either transparency or a confession, and exposing the index over MCP is a hedge toward becoming a component in other people's agents.
La Jefa6.87.3ACP 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 Hacker4.37.3ACP Client for VS Code — MIT, and the agent list is not a list: anything speaking the protocol can be configured by hand, with no plugin API to learn and no review to pass.

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.