vibecosystem

Name: vibecosystem Review
Item: vibecosystem
Rating: 3.8
Author: Aaron Matthews

Skill Development Solid

Works inClaude Code

Solid Scanned — metadata only

137 agents, 269 skills, 53 hooks with self-learning and cross-project training. A multi-agent swarm that improves over time. Built on Claude Code.

Your AI software team. 137 agents, 269 skills, 53 hooks. Self-learning, multi-agent swarm, cross-project training. Built on Claude Code.

Deploy a self-learning agent team that improves across projects
Run one hundred thirty-seven specialized agents for different tasks
Train agents on past project knowledge for better future results

515 starsMIT (commercial OK)FreeQuick setup

Why it matters

137 agents, 269 skills, 53 hooks with self-learning and cross-project training. A multi-agent swarm that improves over time. Built on Claude Code.

Best for

Advanced Claude Code users who want a self-improving agent ecosystem that learns from past projects.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/vibeeval/vibecosystem

By vibeeval

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

claude plugins install vibeeval/vibecosystem

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

After installing, paste this into Claude:

Help me deploy a self-learning agent team that improves across projects

Trust Signals Auto-scanned

Stars515Contributors2Last updated2026-07-08LicenseMIT (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-07-18 · scanner vattempted-no-data

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 514 GitHub stars; 1 contributors; last commit 12d ago; license MIT.

Things to check

137 agents and 269 skills introduce significant configuration and orchestration overhead; requires clear agent roles to avoid redundant work or conflicting outputs. Self-learning on noisy codebases can propagate bad patterns; needs human review gates for critical paths.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

4/5

Versatility

4/5

Reliability

3/5

Security

4/5

Overall score3.75 / 5.00 SolidEvaluatedJul 2026

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 514 GitHub stars; 1 contributors; last commit 12d ago; license MIT.

← Back to the Claude Observatory