LLM agents

1,995 tagged LLM, measured the same way as everything else here.

Browse within: Multi-Agent 218prompt-engineering 145Autonomous Agents 129Science 100agents-md 100claude-code-plugin 67code 67human-in-the-loop 65agentic 58drone 58gazebo 58multi-agent-systems 58ai-security-tool 48local-first 48

code-deduplicator

265

rben01/agentic-coder-config

Agent

Use this agent when you want to eliminate code duplication across your codebase. Examples: Context: User has just written several similar functions and wants to clean up duplication. user: 'I just added these three validation functions that seem really similar' assistant: 'Let me use the code-deduplicator agent to…

not rated 1 3mo ago A 0 tokens

advisor

266

DENGYUFAN0/guashuai-junshi

Agent

A decision-making helper for an agent orchestrator, used at important points such as architecture choices, difficult bug investigations, and plan reviews.

not rated 1 1mo ago A 76 tokens original MIT

toon-evidence

267

w0wl0lxd/tooned

Agent

This document records actual test results from running tooned commands on real fixtures, streaming scenarios, index/metrics surfaces, and model comprehension validation. All results come from the current binary (tooned CLI) and agent CLI tests with swe-1.7-max, glm-5.2 (high), not simulated or estimated.

not rated 1 5d ago A 0 tokens AGPL-3.0

reference-repos

268

SimonGino/portage

Agent

An agent with access to a specified set of local GitHub repositories and a file-by-file path guide. The description is partly in Chinese and gives repository-reference rules.

not rated 1 changed today A 0 tokens

jdwp-investigator

271

dronsv/jdwp-mcp

Agent Claude Code

You are a Java debugging investigator. Your job is to autonomously diagnose runtime issues in a live JVM using JDWP debug tools.

not rated 1 4mo ago A 0 tokens fork MIT

francescofioredev/accreta

Agent Claude Code

MCP and agent-interface engineer for accreta. Owns whether the MCP surface is right, judged from the consumer's side — an LLM with a finite context window and a token budget. Measures response sizes rather than asserting them. Read-only; returns graded findings, never edits.

not rated 1 +1 10d ago A 65 tokens original MIT

mediiiiium/mcp-jp

Agent

A reusable prompt for checking whether an API connector actually covers the features documented by its service. It tells an agent to use official documentation as evidence before adding tools.

not rated 0 5d ago A 0 tokens original MIT

ders-notu

274

merlhn/ehliyet

Agent Claude Code

Ehliyet ders konularını (transkript ya da konu adı) siteye uygun ders notuna çevirir ve yayına ekler. Kullanıcı bir konu + video transkripti verdiğinde, ya da "şu konunun ders notunu üret ve siteye ekle" dediğinde bu agent kullanılır. Konu adı verilip kaynak verilmezse içeriği standart MTSK müfredatından üretir. Örnek…

not rated 0 12d ago A 140 tokens original MIT

llm-offloader

275

seaosinc/mcp-llm-offload

Agent

A routing agent that sends lightweight text tasks to cheaper models, such as local language models, to save the main model’s usage budget.

not rated 0 2mo ago A 153 tokens original MIT

linguist

276

ihwooMil/long-term-memory

Agent Claude Code

A Korean-language analysis specialist for pragmatics, discourse, word-form patterns, and text-based reward signals. Pragmatics studies how meaning depends on context and intent.

not rated 0 6mo ago A 0 tokens original MIT

mdan master

277

khalilbenaz/MDAN

Agent

Orchestrateur Principal, Gardien du Contexte, Directeur des Wizards.

not rated 0 5mo ago A 18 tokens original MIT

perniemann/pnCore

Agent

Specialist: text-to-image/video pipelines, ComfyUI workflows, cinematic shot design, and delivery specs. Invoke for generative media production beyond UI placeholders.

not rated 0 2d ago A 39 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: