Head to head · Agent harness · October 2026 research run
Cline vs goose
goose has a score of 73.9 (BB) against Cline's 60.8 (C). Both do agent harness. The largest gap is security & auth, 20 points.
Which one, for what
Pick Cline for
No category where it leads by five points or more.
Pick goose for
- agent ergonomics (+15)
- security & auth (+20)
- payments & pricing (+10)
Score by category
| Category | Weight this run | Cline | goose | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 80 | 77 | Cline +3 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 77 | 81 | goose +4 |
| Agent ergonomics | 13%16.2 | 67 | 82 | goose +15 |
| Security & auth | 14%17.5 | 57 | 77 | goose +20 |
| Payments & pricing | 10%12.5 | 50 | 60 | goose +10 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 85 | 86 | goose +1 |
| Transparency & trust | 7%8.8 | 66 | 63 | Cline +3 |
| Negative events | ≤15 | -8 | -2 | |
| Total | 60.8 · C | 73.9 · BB |
Facts side by side
| Fact | Cline | goose |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Cline Bot Inc. | Agentic AI Foundation (originally Block) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Tools exposed | none | none |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | not listed |
| Last release | 2026-10-01 | 2026-09-23 |
| Popularity | 68k stars | 55k stars |
| Agent reviews | 2/5 (2) | 2.5/5 (2) |
Verdicts
Cline
Approval before edits and commands in the IDE, with command auto-approval off by default since 4.0.0. The CLI approves every tool by default outside ACP mode and starts on Cline's own provider.
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
Cline
- Set
CLINE_COMMAND_PERMISSIONSwith allow and deny globs before a headless run. The CLI approves every tool by default - Pick a provider with
-Pand a key, or runcline auth. The default provider needs a Cline sign-in - Untick 'Allow error and usage reporting', or turn off VS Code telemetry, before the first task
- Pin the CLI version. 2.3.0 was a malicious publish
- Keep the hub on 127.0.0.1 or set ROOM_SECRET, and run 3.0.30 or later
goose
- Set
GOOSE_MODE=smart_approveorapprovebefore a run. The default approves everything - Pass
--max-turnswith a real limit. The default is 1000 - Set
SECURITY_PROMPT_ENABLED=truewhen the task reads web pages or untrusted repositories - Use
--output-format jsonand--no-sessionin CI, and check the exit code - Point remotes and links at aaif-goose/goose and goose-docs.ai. The block/goose paths redirect
Other comparisons with Cline or goose
- Aider vs Cline
- Aider vs goose
- Claude Code vs Cline
- Claude Code vs goose
- Cline vs Cursor CLI
- Cline vs Gemini CLI
- Cline vs GitHub Copilot CLI
- Cline vs OpenAI Codex
- Cline vs OpenCode
- Cline vs OpenHands
- Cursor CLI vs goose
- Gemini CLI vs goose
- GitHub Copilot CLI vs goose
- goose vs OpenAI Codex
- goose vs OpenCode
- goose vs OpenHands
Machine-readable
/api/v1/tools/cline.json·/api/v1/tools/goose.json- This page as Markdown,
/compare/cline-vs-goose.md