Agents

Minimal Python autonomous agent for GPT-3.5 and GPT-4 with web search, memory and a critic option.

Command-line multi-agent tool that writes a full-length novel from a one-line brief and resumes from saved checkpoints.

Open-source experimental LLM agent that plans tasks and runs tools in a Docker ToolServer.

Open-source desktop and CLI agent that keeps its identity, memory and history across tasks and can modify the code it runs on.

Open-source AI code review for pull requests that you can self-host, with the LLM you choose.

CLI-first penetration-testing agent in Rust that runs recon, testing and validation, with a second model checking each finding.

macOS computer-use agent that reads the screen with OCR, uses a small classifier to choose each click and a writer only for text.

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

Autonomous research agent that reads papers, runs experiments and compiles a LaTeX report with no human in the loop

Autonomous coding agent that turns a task or GitHub issue into a verified pull request with a signed receipt

Open-source desktop computer-use agent that operates apps from natural-language requests.

Autonomous penetration testing agent with a Kali Docker sandbox, a Textual TUI and any OpenAI-compatible model gateway

Single Rust binary for an autonomous, self-improving agent with TUI, CLI and daemon modes and connections to many chat channels

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

AI penetration testing agent for authorized assessments, with scope enforcement and a cloud module covering major providers

Terminal pentesting agent that runs specialist subagents over a shared engagement state and supports 20+ LLM providers

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

Open-source agent harness from MindsHub that runs as the default agent in its Cowork app and standalone in a terminal.

Takes tickets from GitHub, Linear, Jira or Asana, writes the code with Claude Code and opens a pull request for review.

Self-hosted autonomous pentesting agent that finds and exploits vulnerabilities and logs the command and output for each one

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

AI agent that holds a USDC wallet, pays for each model call and paid API, and runs tasks within a budget.

Iterative search agent that keeps searching, reading web pages and reasoning until it finds an answer or runs out of budget.

DeepSeek-native coding agent for the terminal, written in Rust, with a TUI and a headless exec mode for scripts and CI.