“coding”

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

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

Automates browser workflows on any website with vision-based LLM agents, via no-code app, SDK or API

Windows desktop AI companion built on Electron with a Live2D character, long-term memory, voice and tool calling.

Open-source terminal agent that queries and edits codebases and automates tasks with Gemini models

Autonomous penetration testing agent that drives Claude Code or Codex through staged recon, exploit and report pipelines.

Open-source reverse-engineering agent that uses Ghidra and LLMs to rebuild and validate C/C++ functions from binaries.

Personal agent with a Bun gateway that keeps memory, skills and run history, with approval-gated tools and web, CLI and mobile clients.

Open-source DevOps agent that runs 24/7 on your own machines, works on schedules and messages you only when it needs a person.

Agent framework that gives the agent its own Dockerized Linux computer with a browser, projects, skills and plugins

Open-source persistent development workspace with unattended tasks, schedules and heartbeat monitoring.

Open-source background agent with local memory, permission rules and chat access from many apps.

Open-source terminal AI agent that runs shell, Python and web tools on any model, including local ones.

Google's agentic development platform, offered as a desktop app, a terminal CLI, an IDE and a Python SDK.

Open-source agent (MIT) that works with any OpenAI-compatible model, keeps a 16-tool core and loads skills on demand

Research agent from Princeton and Stanford that lets a language model fix GitHub issues and other tasks by using tools on its own

Open-source, local-first desktop workspace for running Claude Agent SDK, DeepSeek Harness or Codex agents with scheduled tasks.

Single-file Python agent for shell and ops work that runs against any OpenAI-compatible model, with per-directory sessions.

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

Open-source autonomous pentesting agents that run your app, find vulnerabilities and validate them with working proofs of concept.

LLM agent workflow that assists a human researcher through literature review, experiments and report writing.

AI agent that designs, documents and validates PCBs from a product brief, working on existing KiCad repositories.

Open-source generative BI engine that gives AI agents a governed semantic layer for correct SQL and shareable dashboards.

Open-source browser for AI agents that runs beside Chrome, with imported logins and live session replay.