Skip to content
Download
Nib 0.1 preview is hereRead the post

Where thought
becomes work.

Ask, build and hand off work. Nib works with Claude, GPT, Gemini, GLM, Kimi, Qwen, DeepSeek or your own gateway. Your projects, history and settings stay with you whichever model you pick, and your crew keeps to its schedule and its budget.

Download Nib

Free account: 2,500 agent actions a month on your own keys · macOS

A Nib desktop window. A user asks Nib to fix a flaky checkout test; the agent reads the test, searches for fixed sleeps, edits the file and reruns the tests until they pass. The session repeats with Claude Opus 5.5, GPT-6.1 Sol, GLM-5.3, Gemini 4 Argon and Qwen3.8 Flash.

One place for all of it.

  • Work

    Ask, and an agent does it on any model. Parallel sessions, any turn undone.

  • Nib Crew

    Roles, schedules and budgets. Reports land in your inbox.

  • Make

    Ask for a dashboard or an app. Share it by link.

  • Browser

    You and the agent see and drive the same page.

Any model, tuned to each one. Your request and the model you chose meet here. The agent fits its tools to that model, then does the work.

Bring any model

Paste a key. Pick any model.

Nib detects the protocol, lists your models and picks a sensible default. Switch models mid-session and your context comes with you.

  • Claude Opus 5.5
  • GPT-6 Astra
  • Gemini 4 Argon
  • GLM-5.3
  • DeepSeek V4 Pro
  • Qwen3.8 Max
  • Grok 4.7
  • MiMo V2.6 Pro
  • MiniMax M3
  • Kimi K3
  • Mistral Medium 3.5
  • Claude Sonnet 5.5
  • GPT-6.1 Sol
  • Gemini 3.8 Flash
  • Claude Fable 5.1
  • OpenRouter
  • Vercel AI Gateway
  • Ollama
  • Cerebras
  • DeepInfra
  • Fireworks AI
  • Groq
  • Novita AI
  • SiliconFlow
  • Together AI
  • LM Studio
  • vLLM
  • LiteLLM
  • Any OpenAI-compatible URL

The product

The full agent toolkit, for any model.

The same tools, permissions, checkpoints and extensions, whichever model you choose.

A harness tuned per model

On Terminal-Bench, the same model scores up to ~30 points apart in different agents. Nib gives each model the edit format chosen for it, passes reasoning back between turns, and checks diagnostics on the files it touched before it stops.

Model familyGets
ClaudeEdit
GPTApplyPatch
GeminiEdit
Qwen · MiniMax FlashEditLines
DeepSeek · MiniMaxReasoning

Zero configuration

Paste a key or a gateway URL. Nib detects the protocol and lists your models.

sk-••••••••••••2c91
  • Detected OpenRouter · Anthropic-compatible
  • Listed the models that can call tools
  • Default: Claude Sonnet 5.5

Brings your existing setup

Your instructions, skills, subagents, hooks and MCP servers work as they are. AGENTS.md, CLAUDE.md and GEMINI.md are read in place; the rest imports in one step.

AGENTS.mdCLAUDE.mdGEMINI.md.agents/skills.claude/skills.mcp.json

Read 23 items in place. Nothing to rewrite.

Permissions you can read

Permission rules in the familiar Tool(specifier) syntax, an OS sandbox for shell commands on macOS and Linux, and an audit log of every decision.

  • allowBash(git status)
  • allowEdit(src/**)
  • askBash(git push *)
  • denyRead(./.env)

Rewind to any turn

Each turn is checkpointed. Fork a session, or roll code and conversation back to an earlier turn.

  1. Read 4 files
  2. Edit api/limits.ts
  3. Bash bun testRestore here
  4. Edit README.md

Parallel sessions, isolated worktrees

Run several agents at once, each on its own branch and worktree. Review the diff, merge when it’s ready.

Rate-limit the public API

nib/rate-limit

+214 −38Running

Fix flaky checkout test

nib/flaky-checkout

+3 −1Ready to merge

Upgrade to React 19.3

nib/react-19-3

+96 −112Needs you

Synced between your computers

Sessions follow you from desktop to browser. Steer a local run from the web app. Phones and cloud sandboxes are coming soon.

  • MacBook ProRunning locally
  • Mac miniFollowing along
  • app.nib.ggApprove git push?

MCP, skills and subagents

Connect any MCP server, package know-how as skills, and delegate to subagents that run in parallel with their own context.

githublinearpostgresplaywrightsentryfigmaslack+ any server

Diffs worth reading

Word-level diffs, inline review comments and LSP diagnostics after each edit, so problems show up while you review.

− const limit = 100;

+ const limit = config.rateLimit ?? 100;

export function guard(req: Request) {

One system

Every agent, in one place.

Sessions, subagents, races, reviews and crew members aren’t separate features. They’re runs of one system, so they share one set of rules, one ledger and one inbox, and you can steer any of them while they work.

Mission control6 runs · $1.56 today
  • Rate-limit the public APISession · local$0.42Working
  • Find every public routeSubagent · read-only · local$0.03Done
  • Write the limiter testsSubagent · worktree$0.11Working
  • Fix the flaky checkout testRace · 3 models · worktree$0.57Winner picked
  • Review PR #482Crew · Kai, Engineer · local$0.19Needs you
  • Deep review of the diffReview · 4 findings · worktree$0.24Done
An example run tree: a session with two subagents, a three-model race, a crew member waiting for approval and a review agent, each with its place, status and cost.

  • One gate

    Every tool call from every agent goes through the same permission rules and audit log. Shell commands run in the OS sandbox on macOS and Linux.

  • One inbox

    Permission requests, questions and finished work from every session, in one queue.

  • One ledger

    A cost receipt for every turn, and usage by day, model and workspace.

  • One supervisor

    Shared provider rate limits and priorities across runs, so parallel agents wait their turn instead of hitting a provider’s limits.

  • One board

    Tasks, findings and file leases shared between agents, so two agents don’t write the same file at once.

  • Agent-operable by design. Most of what you can do in Nib, an agent can do from chat, under the same rules. Anything that spends money or acts outside the workspace waits for your approval.

Race · preview

Race any prompt across models.

Run one prompt on several models and keep the result that passes the tests.

“The checkout test is flaky on CI. Fix it.”3 lanes · one prompt

  1. Claude Opus 5.5Its own branch and worktree
    • Transcript
    • Diff
    • Test run
    • Cost
  2. GPT-6.1 SolIts own branch and worktree
    • Transcript
    • Diff
    • Test run
    • Cost
  3. GLM-5.3Its own branch and worktree
    • Transcript
    • Diff
    • Test run
    • Cost

  • Same prompt, isolated worktrees

    Each model works on its own branch and worktree, so lanes don’t touch each other’s files.

  • Compare side by side

    Each lane’s transcript, diff and cost receipt next to the others, so you pick on evidence.

  • Judge and merge

    A judge that doesn’t see model names recommends a lane; you adopt it or merge it.

Nib Crew · preview

A crew that works on a schedule.

Nib Crew members are agents with a role, goals and a schedule. They run on your machine while the app is open; a cloud mode is coming. Spending is capped per member, and anything public waits for you.

Ava · CEO

Wrote the Q4 plan

Kai · Engineer

Reviewing PR #482

Sage · SEO

4 pages ready to publish

Milo · Marketer

Drafting the launch post

Iris · Designer

Pricing mockups ready

Theo · Analyst

Weekly retention report

Noor · Support

5 replies to review

Remy · Researcher

Competitor teardown

Schedules and triggers

Daily, weekly or on a GitHub mention, while Nib is running.

Approvals where it matters

Anything public or irreversible waits for you.

Budgets per member

Limits on spend and tokens, per run, per day and per month.

Reports in your inbox

Standups and results arrive in your Inbox. Slack and email are coming.

One runtime

Desktop, web and terminal. Same agent.

One runtime powers every surface, so sessions, settings and history are the same wherever you pick them up.

Desktop

A native app for macOS. Parallel sessions, diffs, terminal and keychain-stored keys.

Download the app

Web

The same workspace in your browser, synced with your computers. Phones and cloud sandboxes are coming soon.

How sync works

CLI

A terminal UI, and a headless mode that speaks JSON for scripts and CI.

CLI reference

And where you already work

Under the hood

Same model. Up to 30 points apart.

On Terminal-Bench, the same model scores up to ~30 points apart in different agents, per the published results below. The harness is the part Nib works on, and these are the techniques it uses.

GPT-5.4 on Terminal-Bench 2.0 · pass rate by agent

+29.8 points

between the lowest and highest scoring agent, same model.

Agent A
47.2%
Terminus-2
62.9%
Agent B
71.9%
Agent C
77.0%

Source: arXiv 2604.25850. Same model and task set; only the agent differs. Scores as published by the source. Agents are labelled with letters, and the same letter is the same agent across models; the source names them. Terminus-2 is Terminal-Bench’s reference agent. Nib is not in this chart: we haven’t published a Terminal-Bench score.

Native edit formats

The edit format alone moves scores on public editing benchmarks. Each model gets the format chosen for it: str_replace, V4A patches or hash-anchored lines.

Reasoning that round-trips

Some providers refuse a turn whose earlier reasoning is missing. Nib passes each provider’s reasoning back on the next turn, in the form that provider expects.

A shell that works like a terminal

Non-interactive defaults, a real PTY for interactive programs, background jobs instead of timeouts, and bounded output.

Checks before it stops

When the agent thinks it’s done, Nib checks diagnostics on the files it touched and sends failures back into the loop. A Stop hook can run your tests; a built-in test gate is coming soon.

Cache-stable context

Stable prefixes, observation masking before summaries, and big outputs spilled to files, so more of each turn hits the provider’s cache.

Tolerance for open models

JSON repair, schema coercion and text tool-call parsing, so a malformed tool call from GLM, Kimi, Qwen or DeepSeek is repaired instead of ending the turn.

provider and gateway presets, including local models
202
API protocols: Anthropic, OpenAI Chat and Responses, Gemini
4
edit formats, chosen per model
3
runtime behind the desktop app, CLI and web app
1

Pricing

Start free. Upgrade when you need more.

Free includes 2,500 agent actions a month on your own keys and a small monthly allowance of Nib models. Paid plans lift the limit on your keys and add more Nib models, sync and Nib Crew automation; cloud runners are coming soon.

Free

Any model on your own keys, plus a little of ours. Needs a Nib account.

$0with an account

Download
  • Desktop app and CLI
  • Your own keys: 2,500 agent actions a month
  • A monthly allowance on efficient Nib models + $3 welcome credit
  • 2 synced devices, 30 days of cloud history
  • 3 crew members, manual runs
  • 2 hours to try Nib in the cloud, once (coming soon)
  • Self-hosted runners, free

ProPopular

Unlimited use of your own keys, with Nib models included.

$16.67/ month

$200 billed yearly

Get Pro
  • Everything in Free
  • Nib models for everyday work, any model; resets weekly
  • Your own keys: unlimited
  • Unlimited devices and history
  • 20 cloud runner hours a month (coming soon)
  • 10 crew members, 200 automated runs a day

Max

For people who run several agents all day.

$83.33/ month

$1,000 billed yearly

Get Max
  • Everything in Pro
  • Nib models every week: 5× Pro's usage
  • 100 cloud runner hours, 8 at once (coming soon)
  • Unlimited crew members, 1,000 automated runs a day
  • Priority support

Ultra

For people whose agents work in parallel all day, every day.

$166.67/ month

$2,000 billed yearly

Get Ultra
  • Everything in Max
  • Nib models every week: 10× Pro's usage
  • 200 cloud runner hours, 16 at once (coming soon)
  • Unlimited crew members, 2,000 automated runs a day
  • Priority support

Team

Shared agents and guardrails for the whole team.

$25/ month per seat

2-seat minimum

Start with Team
  • Pro's features, per seat
  • Nib models every week, pooled: each seat adds about 30 small coding tasks a week
  • 10 crew members per seat, pooled; 2,000 automated runs a day
  • Sign in with GitHub or Apple
  • Google and OIDC SSO: coming Q1 2027
  • Priority support

Prices in USD, plus applicable taxes.

Enterprise

Enterprise is open to design partners. Talk to us.

From $60 / seat / month · Annual, 25-seat minimum

  • Provider allowlists
  • Unlimited crew
  • Priority support
  • On the roadmap: SAML and SCIM (2027)
  • On the roadmap: streaming the audit log to a SIEM
  • On the roadmap: runners in your VPC
Talk to us

How we price

  • Your plan's usage at provider prices

    Nib models are counted at the model provider's published price for the tokens you use, cache discounts passed through. Usage beyond your plan is charged at list price × 1.05, which includes a disclosed 5% fee.

  • Your keys, no meter

    Bring your own keys on every paid plan, unlimited. Free includes 2,500 agent actions a month on them.

  • A percentage in the plan, dollars for money

    Your plan shows how much of this week you've used and when it resets. Credits, estimates on your own keys and invoices are always in dollars.

  • Receipts per task

    Every Nib-model request is metered by user and model, and you can see it.

  • No 5-hour windows

    One weekly allowance, with no rolling lockouts. In a new account's first 30 days, Nib models have a daily safety cap: $3 on Free, $25 on Pro, $100 on Max, $200 on Ultra and $25 per seat on Team. Credit you've bought isn't capped. Rate limits are only there to stop abuse.

Compare every feature

Questions

Answers, plainly.

Something else on your mind? Read the docs or write to support@nib.gg.

Try it on a real task.

Download Nib, sign in, paste a key, and ask for something you’ve been putting off.

Download Nib