Agents

Visual workbench for AI coding agents that shows every model call, with sessions run locally or on a server

Microsoft AI Frontiers experimental agent for browser and local file tasks, built to run on small models.

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

Multi-device terminal server for running Claude Code, opencode, Codex and OpenClaw with sessions that survive disconnects.

Open-source coding agent in the browser that edits frontend source files from clicks and plain-English descriptions.

Local-first desktop agent workspace for DeepSeek Harness, with conversations, files, terminals and a shared browser.

Outbound sales agent for early founders: finds prospects, drafts messages for your approval, then sends them.

Local-first agent OS that runs Claude Code, Codex and OpenCode on your machine and lets you drive them from a browser or chat apps.

Open-source, local-first desktop app where a team of AI coding agents shares one session, a visible plan and an issue list.

Self-hosted AI investment research assistant for A-shares, Hong Kong and US stocks, with data and chats kept on your own machine.

Self-hosted open-source AI coding assistant with a CLI and web UI, multi-agent collaboration and Docker deployment.

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

Multi-agent platform that audits source code for vulnerabilities, verifies findings and drafts CVE reports

Local-first inbox for long-running AI agent work, built on DeepAgents and LangGraph with approvals and scheduled runs.

Self-hosted personal assistant you text over iMessage; it can drive a cloud browser for tasks such as bookings and purchases.

Open-source AI agent that investigates cloud and Kubernetes incidents, writes root-cause analyses and drafts fix pull requests.

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

Self-hosted workspace where people and coding agents share projects, live sessions and persistent Mates across providers.

Self-hosted personal AI agent with a desktop app and web dashboard that talks over Telegram, Slack, Discord, WhatsApp or the browser

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

Open-source Devin alternative that runs Claude Code, Codex, OpenCode or Pi in isolated workspaces you can self-host.

Self-learning data agent that answers English questions with read-only SQL over a database, grounded in six context layers.

Experimental Python framework for a self-building autonomous agent, centered on stored functions and a dashboard

Open-source agentic language model (30.5B parameters, 3.3B active per token) trained for long, multi-step web information seeking.