AI research skills and agents

MiroThinker-v1.0-8B

miromind-ai · Kit

An open research agent model that reasons over long contexts and calls tools many times per task to look up information. The 8B size, built on Qwen3-8B, suits…

Tev-320B

gordonhu · Kit

A 320B mixture-of-experts agent model that works through long terminal tasks with a single bash tool. Trained with reinforcement learning on 1,170 environments…

K2-Horizon-3.7B

IFM · Kit

Handles coding, reasoning and agent-style tasks as a small open model with a 512K token context window. Built by IFM for people who want public training data,…

DialFork Leaderboard

DialFork · Kit

Lists how different methods score on DialFork, a benchmark for procedural hallucination in conversational AI agents, on one static page. It suits researchers w…

Sage-A1.5 GGUF (Q4_K_M)

InternScience · Kit

Runs Sage-A1.5, a 35B mixture-of-experts agentic model for long scientific tasks, as a 4-bit GGUF file. It can split work across subagents and check its own pr…

Sage-A1.5

InternScience · Kit

Works through long scientific tasks as an agent that delegates to subagents, checks its own progress and revises its plan. A 35B mixture-of-experts model for r…

Axion-1.0-35B

Axion1-0 · Kit

A reproduction checkpoint of Axion 1.0-35B, a 35B mixture of experts model for scientific reasoning, information seeking and tool using problem solving, served…

PAN 2

IFM · Kit

A 29B world model from IFM at MBZUAI that turns a scene and described actions into a video of up to 20 seconds, so an agent can preview outcomes. For researche…

GuardrailAgent Benign Check

Sattyam · Kit

Shows how often the GuardrailAgent input gate wrongly flags 250 harmless XSTest prompts as jailbreaks, with every prompt and decision. Useful for people who bu…

FlyHash vs SimHash Demo

pranamhan · Kit

An interactive browser demo that compares FlyHash and SimHash for retrieving items, built to accompany a paper on FlyHash for LLM agent memory. For researchers…

MedCaseAgent

PediaMedAI · Kit

A project page for research resources on rare disease clinical case reports: a 584-record benchmark, a large corpus of case-report metadata and the agent code.…

MiMo RL Environment Explorer

FineEnvs · Kit

Browses 7,780 reinforcement learning environments from XiaomiMiMo, then runs a model on a task and shows how it is graded. An unofficial explorer for people wh…

Cua Driver Bench on AgentEnv

earakely-scale · Kit

A replay viewer for computer-use agents running Cua Driver Bench tasks, with the recorded desktop, tool calls, grades and drivers side by side. These are not t…

SchemeArena

launch · Kit

Presents a research project that tests LLM agents for scheming across 400 scenarios, with a monitor called SCOUT. It is a static project page for AI safety res…

Full Duplex Leaderboard

aufklarer · Kit

Compares voice agents on when to speak, which tool to call and how well speech follows a style instruction, using three public benchmarks. For teams that build…

RL Environments on Hugging Face

FineEnvs · Kit

Lets you browse reinforcement learning environments on the Hugging Face Hub, look at their tasks and rewards, and run agent rollouts to compare results. It sui…

TabArena

TabArena · Kit

Ranks machine learning methods for tabular data with Elo ratings in a Gradio leaderboard, and serves the numbers to agents as JSON and MCP tools. For researche…

An n8n workflow that screenshots product pages listed in Google Sheets through ScrapingBee, has a Gemini agent read titles, prices, brands and promotions, and…

An n8n workflow you call with a web address that carries a topic. An AI agent has Perplexity research the topic, and the workflow answers with a finished HTML…

An n8n workflow that sends one question to Perplexity’s Agent API with web search limited to the domains you list and to the last month. It returns the answer…

An n8n workflow that runs every evening. An OpenAI agent writes a report on the top n8n creators, saves it to Google Drive and emails it, and a Gemini list of…

An n8n workflow you chat with. Give it an n8n creator’s username, and an OpenAI agent reads that creator’s public weekly and monthly numbers and writes a Markd…

An n8n chat where you name a niche. An agent searches YouTube for videos from the last two days, looks each one up for views, likes and tags, and reports what…

An n8n workflow with a chat window. An OpenAI agent answers your questions, searches Google through SerpApi for recent facts, looks topics up in Wikipedia, and…

An n8n workflow with a chat agent that can open web pages. Its tool downloads an address, strips scripts and styles, turns the page into Markdown and hands it…

bioinformatics-agent-skills

ssinder · Skill

Gives an AI coding agent expert skills for computational biology, from RNA-seq and single-cell analysis to protein structure, molecular dynamics, peptide desig…

Scientific Agent Skills

K-Dense-AI · Skill

K-Dense’s open library of more than 170 research skills for coding agents: biology, chemistry, medicine, materials, data analysis, literature search and scient…

ex-USSR Kinship Research

DenisSergeevitch · Skill

Turns an AI agent into a careful genealogist for the former USSR and the Russian Empire, with registers, evidence statuses and an HTML report. Made for family…

An n8n workflow that collects one topic’s news each morning. Apify reads the last day of posts from X handles you list, an Airtop browser reads your websites,…