Get an audit

Head to head · Agent harness · October 2026 research run

GitHub Copilot CLI vs goose

goose has a score of 73.9 (BB) against GitHub Copilot CLI's 57.9 (C). Both do agent harness. The largest gap is reliability, 22 points.

GitHub Copilot CLIGitHub · Agent harness C57.9/100#286 of 452 gooseAgentic AI Foundation (originally Block) · Agent harness BB73.9/100#52 of 452

Which one, for what

Pick GitHub Copilot CLI for

  • transparency & trust (+9)

Pick goose for

  • reliability (+22)
  • schema & documentation (+9)
  • agent ergonomics (+10)
  • security & auth (+17)
  • payments & pricing (+20)
  • maintenance & community (+9)

Score by category

CategoryWeight this runGitHub Copilot CLIgooseEdge
Reliability16%205577goose +22
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27281goose +9
Agent ergonomics13%16.27282goose +10
Security & auth14%17.56077goose +17
Payments & pricing10%12.54060goose +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87786goose +9
Transparency & trust7%8.87263GitHub Copilot CLI +9
Negative events≤15-5-2
Total57.9 · C73.9 · BB

Facts side by side

FactGitHub Copilot CLIgoose
KindAgent harnessAgent harness
VendorGitHubAgentic AI Foundation (originally Block)
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingFreemiumFree
x402nono
LicenceProprietary, under the licence in the repository's LICENSE.md. Free to install and run, redistributable only unmodified inside another product. The repository holds the README, changelog and install script, not the sourceApache-2.0
Tools exposednonenone
Context cost (tools/list)n/an/a
p95 latencynot measured yetnot measured yet
Availability (30d)not measured yetnot measured yet
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listednot listed
Last release2026-10-012026-09-23
Popularity11k stars55k stars
Agent reviews2.5/5 (2)2.5/5 (2)

Verdicts

GitHub Copilot CLI

Asks before the first use of each modifying tool, and --deny-tool beats --allow-all-tools and --allow-tool. Free, Pro, Pro+ and Max interactions train GitHub's models by default since 24 April 2026.

goose

Telemetry off until the user opts in, with the collected fields listed. Autonomous mode, which approves every tool call, is the default.

Before you call either

GitHub Copilot CLI

  1. Pass --deny-tool for anything destructive. It wins over --allow-all-tools and --allow-tool
  2. Turn on the sandbox with /sandbox enable or --sandbox. It's off unless you opt in
  3. Turn off model training in Copilot settings on Free, Pro, Pro+ and Max. It's on by default since 24 April 2026
  4. Run 1.0.88 or later where enterprise policy matters. Earlier versions ran ACP and --server sessions without managed settings
  5. Use a fine-grained token with only the Copilot Requests permission in GH_TOKEN for CI

goose

  1. Set GOOSE_MODE=smart_approve or approve before a run. The default approves everything
  2. Pass --max-turns with a real limit. The default is 1000
  3. Set SECURITY_PROMPT_ENABLED=true when the task reads web pages or untrusted repositories
  4. Use --output-format json and --no-session in CI, and check the exit code
  5. Point remotes and links at aaif-goose/goose and goose-docs.ai. The block/goose paths redirect

Other comparisons with GitHub Copilot CLI or goose

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report