AI agents

A self-hosted job board that runs coding agents in isolated Git worktrees, queues jobs, and returns pull requests or summaries for review.

Agent Argue stages structured debates between language-model agents and turns them into balanced cards; code checks quoted concessions against the transcript before publication.

Stately Agent is a software for building intelligent agents that interact via chat and events, with examples including joke generation, tic-tac-toe, and weather querying, requiring installation and an OpenAI API key

A lightweight, stateless platform for discovering and routing requests between AI agents through an HTTP and JSON API.

Agent QA is a self-improving QA harness with memory for natural-language web and mobile tests; it adapts to UI changes and provides a dashboard, CLI, MCP server, and coding-agent skills.

A set of small, single-purpose libraries that improve reliability in production LLM agents through tool validation, network controls, trace tests, context fitting, structured output checks, and usage budgets.

A desktop app for directing autonomous coding-agent teams through Kanban tasks, shared messaging, code review, and approvals.

An MCP server for AI agents providing cryptographic activity provenance, chain integrity checks, agent identity verification, and reputation tools.

agent-kit is a TypeScript toolkit for deploying multi-tenant AI agents with sandboxed execution, curated memory, and human-approved learning.

agent-manager is an open-source terminal UI that runs coding agent CLIs such as Claude Code, Codex, OpenCode and Gemini CLI unmodified, each in its own persistent tmux session, with a git worktree per session and diff review comments sent back to the agent.

agent001 is an open-source agent that uses its own wallet and credit line to borrow and repay USDG, sell an x402 API, and interact through CLI or Telegram.

Run multiple coding agents in parallel inside isolated local Docker containers or cloud virtual machines, with per-box browser and VS Code access.

An open-source control plane for building and operating AI agents as callable services, with routing, coordination, asynchronous execution, memory, and observability.

A local workspace for coordinating AI coding agents across tickets, repositories, and pull requests, with project tracking, retained context, and human approval gates.

Aider is a command-line tool for AI-assisted pair programming, allowing code editing in local git repositories with GPT-3.5/GPT-4, featuring direct file edits, automatic git commits, and support for most popular programming languages

ANUS is an open-source terminal coding agent that reads code, edits files, runs commands, routes requests to available free models, and retries when a provider is rate-limited.

A DSPy-native runtime that turns natural-language goals into inspectable agent graphs, executes independent steps in parallel, evaluates results, and can repair failed runs.

Aster is a local-first software-engineering agent that uses shared tools, permissions, memory, skills, and retrieval for chat, code review, and fixes.