Nori

Orca is a free, open-source agent development environment for running multiple coding agents in parallel on desktop, mobile, or a VPS. It runs CLI agents such as Codex, Claude Code, OpenCode, and Pi side by side, placing each agent in an isolated Git worktree so results can be compared and merged. The environment provides split terminals, a VS Code editor, diff annotation and review, browser-based Design Mode that sends selected HTML, CSS, and screenshots to an agent, native GitHub and Linear views, SSH worktrees with port forwarding, and a mobile companion for monitoring agents and sending follow-ups. Its CLI can script workflows such as creating worktrees, taking snapshots, clicking, and filling fields. Orca is designed to work with any coding agent that runs in a terminal and uses the user's own agent subscriptions.

Nori Agentic is a company building cloud agents for managing and auditing asset managers' security master databases. Its agent starts when a data cell changes, investigates the change with sources such as Box, Bloomberg APIs, and email, assembles a cited explanation with a recommendation to keep or discard the change, and notifies the cell owner in Slack. The videos describe a deployment for a large asset manager in which this process reduced manual review from about an hour per change to approximately five minutes.

Noop is an AI team that runs Claude Code and Codex agents on the user's own computers, coordinated through the user's free Cloudflare account. It accepts a goal in one sentence, breaks it into tasks, runs tasks in parallel, and returns results while asking the user to choose among short options when human input is needed. Its decision-making starts cautiously and adapts to the user's previous choices; the project describes this as learning how the user decides. Noop can be accessed through a browser or optional desktop and mobile apps, and supports adding additional macOS, Linux, and Windows machines. It is distributed under the MIT license.

nono is an open-source agent runtime security tool from the team behind Sigstore. It uses kernel-enforced sandboxing with zero setup and low latency to protect AI agents, their tools, credentials, skills, and instruction files; it supports macOS, Linux, and Windows through WSL2 and runs as an unprivileged single binary. On Linux it uses Landlock and on macOS Seatbelt, while delegated tools can run in separate ephemeral child sandboxes with explicit filesystem, network, environment-variable, and credential permissions. Its policy system controls tool commands, domain and HTTP access, and credential use through proxy-based injection and phantom tokens. It also provides Sigstore-based supply-chain and skill attestation, cryptographic audit records, file-change snapshots and rollback, agent profiles, a registry of packaged agents, and Rust and Python FFI bindings. The project is distributed under the Apache-2.0 license.

Munder Difflin is a free, open-source desktop multi-agent harness that runs multiple terminal-based AI coding agents as coordinated local agents. It wraps agents including Claude Code, OpenAI Codex, Gemini CLI, Qwen, OpenCode, GitHub Copilot CLI, and custom commands, working with users' existing subscriptions and hourly usage limits. Each agent runs as a real node-pty process and is rendered through xterm.js, while an Electron and React interface displays sessions as avatars on a Pixi.js office floor. A GOD orchestrator called Michael assigns and routes work, adjudicates agent messages, and escalates spending, destructive operations, scope changes, and other configured approvals. Agents coordinate through a local Git-backed hive of plain-file memory, atomic mailboxes, a shared blackboard, and an append-only event log; a markdown-first semantic memory layer supports recall across sessions. Optional Git worktrees isolate parallel agents.