Agents

Sakana AI framework for automated research where LLMs generate ideas, run experiments and write papers.

Self-hosted AI agent built on n8n, PostgreSQL and Claude that runs over Telegram or a webhook API.

Python command-line pairing agent for ML engineers that builds baselines, works Kaggle-style tasks and writes weekly reports.

Modular LLM software engineering agent from ByteDance with a CLI, interactive mode and several model providers.

Open-source end-to-end general multi-agent product that answers queries and produces reports, slides and code.

Claude Code agent on a VPS you own, with a real Chromium browser and a Telegram bot to message it.

Open-source deep research agent for multi-step web research, with models published on Hugging Face.

Always-on personal agent that turns Telegram voice notes into linked markdown notes in your Obsidian vault on a VPS.

Agent that runs deep learning experiments around the clock on local, SSH or Slurm backends and records each outcome

Open-source Android app that runs Gemma 4 on the phone to read the screen and operate apps, with optional cloud models

Microsoft agent framework for automating Windows desktop apps, with a multi-device Galaxy orchestrator.

Open-source autonomous work engine that plans and runs tasks across files, terminal, browser and APIs, then checks the result

Open-source Mac personal AI that works through your Claude Code or Codex CLI session, with voice, screen awareness and phone calls.

Open-source agentic software engineer that plans, researches the web and writes code from a high-level task

General-purpose biomedical AI agent that autonomously runs research tasks by combining LLM reasoning with code execution.

Multi-agent LLM framework for web search that runs several queries at once, with React, Gradio or Streamlit front ends.

LLM-driven trading agent for Hyperliquid that reads technical indicators and places trades with take-profit and stop-loss rules.

Autonomous research system that runs literature review, idea generation, experiments and manuscript writing.

Deep research agent that gives large reasoning models autonomous search, web browsing and report drafting.

In-cluster Kubernetes SRE agent that investigates pods and logs from Slack and can report only or remediate, with a SQLite dashboard.

Research system that searches the web, writes an outline and drafts a Wikipedia-style article with citations; Co-STORM adds human collaboration.

Sourcegraph's coding agent and dev environment that runs agents in cloud machines called orbs that keep working after you close your laptop

Python performance optimizer that uses LLMs to generate, test and benchmark optimizations and opens pull requests.

General-purpose agent that builds apps, writes reports, creates presentations and connects to your other systems.