“agent memory”

Open-source super agent harness that runs sub-agents, memory, sandboxes and skills for research, coding and content tasks lasting minutes to hours.

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

Stateful agent harness whose agents keep memory across sessions and run on schedules through a CLI, browser and chat apps.

Open-source computer use agent from Simular that operates desktop and web apps by clicking, typing and scrolling.

Self-hosted agent from Nous Research that builds skills from experience and is reachable from the terminal and chat apps

Open-source AI code review agent for pull requests on GitHub, GitLab, Bitbucket, Azure DevOps and Gitea.

Native macOS AI agent that connects many LLM providers to a task loop that drives apps through Accessibility and builds in Xcode.

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

Minimal software engineering agent built around bash only, scoring above 74% on SWE-bench Verified.

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

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

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

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

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

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 agentic SAST scanner: AI agents follow imports and call graphs to confirm findings in a repo or PR diff.

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

Desktop harness that coordinates several terminal coding agents as one team on your own machine.

Lightweight self-hosted personal agent framework in Python with a WebUI, chat-app channels, memory and MCP

Open-source, self-hosted AI agent platform for persistent bots with their own computers and memory.

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

Notion's built-in agent that completes multi-step tasks using workspace content, connected apps and the web

Replit's chat-driven agent that builds, tests and deploys apps and can create other agents and automations

Personal AI assistant with eight memory types, hourly proactive check-ins and channels from macOS and iOS to Slack and Telegram.