Agents

Self-hosted AI assistant for multiple users and agents, reachable from a web dashboard and chat apps.

Framework that lets a multimodal model view the screen and operate a computer with mouse and keyboard actions.

Open-source CLI research agent for literature reviews, deep research and paper drafts.

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

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

Open-source CLI that scans Kubernetes clusters, diagnoses problems with built-in analyzers and explains them with an LLM.

Self-hosted Go workspace where AI agents run security tools through MCP for authorized testing.

Local-first desktop workspace for AI agents, with plugins, MCP servers and parallel sessions.

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

Terminal coding agent that sends each request to whichever free model is answering today.

Autonomous red-team agent with a Docker stack, terminal CLI, web dashboard and hosted option.

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

Open-source desktop agent that edits files and Office documents and takes tasks from chat apps.

Open-source workspace for named AI agents with memory, delegation, routines and approval controls.

Apache-licensed agent workspace that keeps an append-only event log of every model and tool action.

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

Open-source desktop app where AI agents appear as chat contacts, each running Claude or Codex locally.

Open-source command-line coding assistant from Mistral that runs on Mistral models and asks approval before tool execution.

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

Self-hosted open-source agent that produces and schedules YouTube videos after user approval.

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

Multi-agent development platform built on Kotlin Multiplatform, with IDE plugins, a CLI, desktop, mobile and web targets.

Open-source AI workbench for scientific research that runs analyses and experiments with visible steps.

Open-source desktop and mobile AI agent client that runs Claude Code and Codex on your own machine.