multi agent system agents

EvoScientist/EvoScientist

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

EvoScientist/EvoScientist

Agent

Compare two outputs WITHOUT knowing which skill produced them.

EvoScientist/EvoScientist

Agent

Evaluate expectations against an execution transcript and outputs.

DemonDamon/AgenticX

Agent

A planned agent for improving user questions before retrieval-augmented generation (RAG), a method that searches a knowledge base before generating an answer.

DemonDamon/AgenticX

Agent

A code-analysis agent that documents the structure, files, statistics, and implementation details of an agents directory in a Python project.

alfredolopez80/multi-agent-ralph-loop

Agent Claude Code

Agent "ai-output-code-review-super-auditor" from alfredolopez80/multi-agent-ralph-loop, covering the vision, your work, step by step, ultrathink principles in practice, 0. role & mission and 1. scope of work.

alfredolopez80/multi-agent-ralph-loop

Agent Claude Code

Agente que transforma prompts ordinarios en prompts profesionales para IA usando arquitectura en 5 capas.

alfredolopez80/multi-agent-ralph-loop

Agent Claude Code

Agent "software-architech" from alfredolopez80/multi-agent-ralph-loop, covering the vision, your work, step by step, ultrathink principles in practice, key principles and python sdk (instead of “python/fastapi”).

MANOJ21K/agentic-code-review

Agent

Hunts correctness bugs that are provable from the code as written — logic errors, off-by-one, null/undefined dereferences, unresolved references, inverted conditions, wrong operators, unreachable code. Requires a concrete failure scenario for every finding. Refuses style, performance speculation, and…

MANOJ21K/agentic-code-review

Agent

Reviews a diff against the git history of the files it touches. Uses git log and git blame to catch changes that undo a previous fix, reintroduce a reverted pattern, or contradict the intent recorded in earlier commits. Adds the dimension a code-only reviewer misses — the past. Use when the changed files have…

MANOJ21K/agentic-code-review

Agent

Reviews changed code for security defects introduced or touched by the diff — injection (SQL, shell, path), hardcoded secrets, missing authorization on new endpoints, unsafe deserialization/eval, and sensitive data written to logs. Only flags issues in the changed surface, with a concrete exploit scenario. Use on any…