“Agent memory”

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

Web automation agent built on AG2 that fills forms, searches sites and operates web apps from plain-language instructions.

Open-source coding agent for the terminal, editor, desktop, browser and chat apps that works with Qwen, OpenAI, Anthropic and Gemini APIs

Desktop and terminal AI coding workspace with persistent sessions, project memory, subagents and a managed browser.

Open-source personal AI assistant that runs on your own hardware and answers in the chat apps you already use

Terminal-native AI coding assistant that reads and writes code, runs commands, manages Git and keeps persistent project memory.

Small assistant that runs each agent in its own Linux container and connects to Slack, Telegram, WhatsApp and other chat apps

Cursor's coding agent that you run from the terminal or editor, with a choice of frontier models and support for scripts and automations

Local-first desktop and terminal workspace where AI agents work on code, documents and research.

Token-efficient agent with a local router that picks the cheapest capable model for each turn.

MIT-licensed AI coding agent with terminal, TUI and browser interfaces, durable project memory and specialist subagents.

Desktop workspace that runs several existing CLI coding agents in parallel with shared workflows.

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 with a Kali Docker sandbox, a Textual TUI and any OpenAI-compatible model gateway

Go terminal coding agent with cost-aware routing across LLM providers, shipped as one binary.

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

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

Brief-driven runner that keeps coding agents working across sessions and asks only for decisions that are yours.

Open-source terminal coding agent for DeepSeek V4 that keeps prompt prefixes byte-stable for cache-friendly, low-cost sessions

The Pi coding agent compiled ahead of time into one native executable for Linux, macOS, Windows and Android (Termux).

Cognition's desktop IDE and command center for managing local and cloud coding agents and models in one place