Every account and every tool, in every agent.
Sign in to each Codex and Claude account once. When one reaches its limit, your next request goes to the next account in line, and you keep using Codex and Claude Code as usual.
3 of 3 accounts readyNext Personal
- 1PersonalNext5-hourResets in 2h61% usedWeeklyResets in 4d44% used
- 2WorkNext5-hourResets in 4h18% usedWeeklyResets in 1d63% used
- 3BackupNext5-hourResets in 5h6% usedWeeklyResets in 6d12% used
Use a tool from any agent
Each agent keeps its own MCP servers, skills, and plugins. Hansard serves them to every agent session through its own MCP entry, so Claude Code can call Codex’s Computer Use, and Codex can load a skill you wrote for Claude Code.
Share skills and MCP serversOpen the app in the iOS Simulator, turn on dark mode, relaunch it, and check that the switch stays on.
I’ll drive the Simulator with Computer Use.
Dark in Simulatorfrom CodexWaiting for approvalDark mode stays on after the relaunch. The switch reads On and the settings screen is dark.Computer Use was denied, so I stopped before touching the Simulator.
Allow Computer Use to use Simulator?
Choose what each agent can reach
Turn sharing off for one item, or for one conversation from its Actions menu. Tools that run code, control your computer, or change cloud services ask before each use until you allow them.
Skills, plugins, and MCP servers- Computer UseRecommended offMCP server for Codex
- release-notesSkill for Claude Code, in this project
- postgresMCP server for Cursor and Claude Code
- playwrightMCP server for Claude Code
- deploy-checkSkill for Codex
- Between usage checks
- 2 min
- While it runs, the router reads each account’s usage about every two minutes.
- Prompts spent on checks
- 0
- Checking usage never sends a model prompt and never redeems a reset.
- Until an idle server stops
- 15 min
- A server another agent installed starts on first use and stops after 15 minutes without a call.
Smaller time savers
Continue after a limit
When a limit stops a turn running in Hansard, Continue sends one new turn with the same model and settings, and the router picks an account with allowance left.
Continue after a usage limitSee when you’ll run out
Each plan limit shows where your pace leads, and an alert warns when every account of a provider is about to reach its limit.
Track plan usageChange routing for a while
Use only one account, skip one to save it, or try one first, for a few hours or until its next reset. The override ends on its own.
Temporary overridesStop idle agents
Running lists every agent conversation on your computer with what it is doing now, and the process monitor shows the memory of everything each agent started, so you can stop the ones left idle.
Running agentsMore of Hansard
Personal Sync
Keep your whole archive in storage you own, with every computer you use in step with the others.
Teams
Share whole conversations from the repositories you choose with your team, under rules every member can read.
Sharing
Send one conversation as a web page anyone can open, a PDF, Markdown, or a trajectory file.
Insights
Rank models on your own work with your own Pareto frontier, and see what you pay against list price and how the work turns out.
Running and Review
Run each project's agents from one place, with tabs, changes, and terminals, and answer everything that waits on you in one queue.
Reading a run
Follow any agent run step by step: a trace of its calls, the agents it started, its context and cost, and Create PR.
Graph
See how your projects, conversations, files, commits, and decisions connect, and the evidence behind each link.
Slack bot
Start Claude Code and Codex runs on your Mac from Slack, approve each one in its thread, and get digests where you choose.
AI assistants
Let Claude.ai, ChatGPT, and other assistants search your agent conversations and memories, with your approval on your Mac.
Phone companion
Follow your agents from your phone, answer what they ask, and revive or start them while they run on your computer.
Accounts
Keep every Claude and Codex account in one place with its limits, route each conversation to one with allowance left, and cap API key spend.
Put it on the record.
