A self-evolving multi-agent framework. The system composes agent orgs that produce patches, grades them against a real test suite, gates them through a circuit-breaker, and merges them — without a human in the inner loop. It runs three task streams in parallel (self-modification,
How to install liquid-org?
u0001f3a2/liquid-org
$claude plugin marketplace add u0001f3a2/liquid-orgInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install liquid-org by running `claude plugin marketplace add u0001f3a2/liquid-org`, then use it for the current task and follow its documentation at https://github.com/u0001f3a2/liquid-org.
.claude-plugin/plugin.json
| 1 | # .claude-plugin/plugin.json |
| 2 | claude plugin marketplace add u0001f3a2/liquid-org |
Related
6 picksType
- cavemanUltra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.Jul 2026
- claude-memMemory compression system for Claude Code - persist context across sessionsJul 2026
- mem0Universal memory layer for AI AgentsJul 2026
- mempalaceGive your AI a memory — mine projects and conversations into a searchable palace. 36 MCP tools, auto-save hooks, and guided setup.Jul 2026
- harnessThe team-architecture factory for Claude Code — a meta-skill that turns a domain description into an agent team and the skills they use, with six pre-defined team-architecture patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical…Jul 2026
- council-of-high-intelligence18 AI personas deliberate your hardest decisions — structured multi-round deliberation (blind analysis, anonymized cross-examination, weighted verdict) with genuine model diversity across providers.Jul 2026
