agentboards.org
Compare/Claudine vs SLICC

ClaudinevsSLICC

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

Claudine
Xemantic · Agent harness
OSS
Panel
4.7
2 spec wins
Reliability
3.8
Usefulness
4.2
Cost
6.7
Longevity
4.2

“The Windows native build is still in progress, which is also a fair status report for an agent that keeps rewriting itself.”

SLICC
AI Ecoverse · Agent harness
OSS
Panel
4.7
1 spec wins
Reliability
3.7
Usefulness
5.2
Cost
6.5
Longevity
3.5

“It is named the Self-Licking Ice Cream Cone, which is the first product on this board to review itself in the title.”

Spec by spec

SpecClaudineSLICC
Architecture
CategoryAgent harnessAgent harness
Runslocallocal
Platformsmacos, linuxmacos, linux, windows, web
Context windownot documentednot documented
Protocols
MCP clientNoNo
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesNo
Browser controlYesClaudine has internet access through its tools; the README does not describe browser automation. Yes
Sandboxed executionNoNo
Multi-agent orchestrationNoYesThe README lists multi-agent delegation and says SLICC can orchestrate several browsers at once.
Headless / CI modeNoNo
Models
BackboneAnthropicany configured provider
Bring your own modelYesYes
Local modelsNoNo
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseGPL-3.0Apache-2.0
GitHub stars17932

Which one would each critic pick

CriticClaudineSLICCPick
El Juez——not enough reviews
El Amigo5.55.0Claudine — Pick this if you want to understand how a harness works from the inside; pick a maintained terminal agent if you want to finish a ticket this afternoon.
El Crítico4.34.3no preference
El Profesor4.85.0SLICC — The agent runs inside the browser tab it automates rather than driving it from an external process, which removes the driver boundary and with it the usual separation of concerns.
La Inversora4.84.5Claudine — Xemantic sells workshops and research, so the code is the syllabus rather than the asset, and a hundred and seventy-seven stars is the marketing return on it.
La Jefa3.53.3Claudine — It is documented as taking full access to the machine and the internet, which is the single sentence that ends a security review before anyone asks about seats.
El Hacker5.56.3SLICC — Apache-2.0, and npx launches Chrome against a workspace on my own disk, with a headless Go follower binary for the machines that have no display. No MCP client anywhere.

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.