AI Agent Tools

omnigent4.9k★

Omnigent puts one layer over all your AI coding agents so you can swap between them without rewriting anything. Claude Code, Codex, Pi, your own custom agents, it runs them through a single harness with shared policy controls, so the agent choice becomes a config detail instead of a rewrite. The standout feature is a security sandbox that hides your credentials and locks down filesystem and network access while an agent runs. Setup is light for what it does: install the CLI through uv or Homebrew, and you get terminal and web UIs plus runners that execute locally or on Modal or Daytona. You bring your own model credentials. The governance and sandboxing are the real reason to look, they address the thing that makes people nervous about letting agents run loose on their machine. Developers juggling multiple coding agents, or anyone uneasy about an agent seeing their secrets, are the target. If you've settled on one agent and trust it, this is overhead you don't need. The value scales with how much you care about isolation and the ability to switch tools without lock-in. The catch: it's alpha. The README says so, and that means rough edges, breaking changes, and features still landing. It's free and Apache-licensed, but you're adopting an early project to wrap other early projects. Promising, but not something to build a team's critical workflow on yet.

MiroFish-Offline2.4k★

MiroFish-Offline runs multi-agent AI simulations and predictions completely offline using a Neo4j knowledge graph and Ollama for local LLM inference. It's a simulation engine where multiple AI agents interact, predict outcomes, and build up a knowledge base over time. This is niche but powerful for scenarios like market simulation, scenario planning, or research where you can't send data to external APIs. Everything runs locally: the database, the models, the agents. The catch: AGPL-3.0 license (if you modify it and offer it as a service, you must open source your changes). Requires Neo4j and Ollama running locally. That's a real setup commitment. And 'offline multi-agent simulation' is a small but growing niche.

claude-peers-mcp2.1k★

Claude-peers-mcp is an MCP server that lets multiple Claude Code instances message each other in real time. If you run parallel Claude sessions (one on the frontend, one on the backend, one writing tests), this creates a direct communication channel between them so they can coordinate without you copy-pasting context between terminals. The way it works: you spin up the MCP server, connect each Claude Code instance to it, and they can send and receive messages from each other ad-hoc, like a group chat between your AI assistants. One session can ask another about an API contract it just wrote, or flag a dependency change that affects the other's work. It removes you as the bottleneck in multi-agent workflows. The catch: very new and tightly coupled to Claude Code's MCP ecosystem. It does not work with other AI agents or coding assistants. Coordinating AI sessions is still experimental territory, so expect rough edges and limited documentation. If you only run one Claude session at a time, you do not need this.

AgentSpace433★

AgentSpace is a shared workspace where humans and AI agents work as one team, instead of you driving a single agent in isolation. The idea: give agents defined roles, permissions, and an audit trail, then let them coordinate in channels the way a human team would. Most agent frameworks assume one person and one agent; AgentSpace is built for a group running several agents with governance around them. Apache 2.0 licensed. The interesting piece is AgentRouter, which routes tasks across different agent runtimes, Claude Code, Codex, OpenCode, and others, through one normalized interface, so you are not locked to a single backend. There is a digital employee board that makes agents visible and shareable across an org, a permission and approval system that puts a human checkpoint in front of sensitive actions, and full logging of everything an agent does. You can self-host it or use the hosted platform. This is early, and it is aimed at founder teams and small orgs that want to put agents to work without losing track of what they are doing. The audit trail and approval gates are the real draw; running multiple agents with no oversight gets dangerous fast. Self-host it for full control of the infrastructure, or take the hosted option if you would rather not run it yourself. The catch is maturity. This is a young project moving fast, and multi-agent coordination is still proving itself across the whole industry, not just here. The governance framing is genuinely useful, but expect rough edges, and verify the hosted tier's pricing before you depend on it, since that is not clearly published yet.