Skip to main content
Glama

Infinite Flight Agent

Infinite Flight Agent is an open-source AI dispatcher for Infinite Flight pilots. It turns a plain-language idea like "Dulles to Denver tomorrow evening in the A321neo" into a briefing ready to fly. It runs on your own keys and your own ChatGPT plan, from the terminal or any MCP client.

**SPAWN:** Gate C28 — used by the most recent completed UA599 (2026-10-30, FlightAware); today's gate is not assigned yet
**TAKEOFF THRUST (simulation-grade estimate):** FLEX, LEAP-1A32: set N1 0.911 x full-thrust N1 (range 0.865-0.948)

**Flight:** UA599 KIAD → KDEN · real aircraft A21N
**Departure:** sched out 2026-11-01 17:20 EST (2026-11-01T22:20:00Z)
**SimBrief plan confirmed:** KIAD 01R -> KDEN 16R · A21N LEAP-1A32 · FL360 · 1259 nm · ETE 03:27:38 · block fuel 11872 kgs
**Takeoff:** rwy 01R · flaps 1 · V1/VR/V2 155/159/161 · bleeds ON

A briefing from a live end-to-end run on October 31, 2026 (registration and codeshares removed).

Why pilots use it

  • Fly real flights. It searches live and recent schedules through FlightAware AeroAPI, so it never invents a flight number. If today's gate isn't assigned yet, it gives the gate from the most recent operation and labels it historical.

  • Generate your SimBrief plan for you. Once you approve, it fills SimBrief's dispatch form in a cloud browser, reads every field back, and generates exactly one plan per leg.

  • Lead with what you set first. Every briefing opens with where to spawn and what N1 to set, before the details.

  • Know where the thrust number comes from. Takeoff N1 is estimated from SimBrief's own takeoff solution (thrust mode, FLEX temperature, runway conditions), using the lapse shape of FlyByWire's open A32NX thrust model. It covers the A320neo, A321neo, and 737 MAX 8, each labeled as an estimate with a range. Other aircraft get a clear "unavailable" instead of a guess.

  • You approve before anything happens. Nothing is generated until you approve the exact flight, airports, aircraft, and thrust status shown back to you.

  • Use it where you already chat. Use the terminal chat, or connect ChatGPT, Claude, or Codex to the MCP server.

Related MCP server: SimBrief Flight Planning MCP Server

How it works

flowchart LR
  you([You]) -->|"flight idea"| agent["Dispatcher agent<br/>(Deep Agents + your ChatGPT plan)"]
  agent -->|"real flights, gates"| fa[(FlightAware AeroAPI)]
  agent -->|"approval"| you
  agent -->|"fill and generate"| bb["Browserbase cloud browser"] --> sb[(SimBrief)]
  sb -->|"OFP + takeoff performance"| agent
  agent -->|"spawn + N1 briefing"| you

One agent handles the conversation and judgment calls. Fixed tools handle the parts that must be exact: flight lookup, approval, plan generation, matching the generated plan to the leg, and the thrust estimate. Details are in the agent guide and the technical design.

Quick start

You need uv, a ChatGPT plan, a FlightAware AeroAPI key (the Personal tier is enough), a SimBrief account, and a Browserbase API key.

git clone https://github.com/IntelIP/InfiniteFlightAgent.git
cd InfiniteFlightAgent
uv sync --locked
cp .env.example .env        # add AEROAPI_KEY, SIMBRIEF_USERID, BROWSERBASE_API_KEY
uv run ifd-login            # Sign in with ChatGPT and approve plan usage
uv run ifd-simbrief         # log in to SimBrief once in the cloud browser it opens
uv run ifd-chat             # describe your flight

Approval prompts appear in the terminal. See the agent guide for all settings, resuming conversations, and MCP client setup.

Choose how to run it

Path

Best for

Start

Terminal chat

Trying it out, single machine

uv run ifd-chat

Local MCP server

Claude Desktop, Codex, or other MCP clients on your machine

MCP setup

Self-hosted remote MCP

Using it from ChatGPT or your phone, behind Cloudflare Access

Cloudflare deployment

The self-hosted path runs a Cloudflare Worker and container, with Neon Postgres for conversation state, R2 for screenshots, and Doppler for secrets. It is built for one owner and is not a shared or resold service.

Quality

The agent is checked against 100 scripted first messages across 11 categories: vague requests, multi-leg trips, private flights, unsupported aircraft, and more. On October 31, 2026, two consecutive full runs on the same code passed every safety check 100% of the time, and fully passed 92 and 91 of the 100 cases. The safety checks are: no invented flight numbers, no assumed dates, correct airports, and unsupported thrust disclosed before approval. A separate live end-to-end set exercises approval, real SimBrief generation, and the final briefing. See evaluation results.

Status and limits

  • Early, personal-use software. It works end to end locally. The remote deployment is built but not yet live.

  • Thrust targets are simulation-grade estimates, shown with a range. No aircraft is yet marked as verified against reference data; see aircraft coverage.

  • FlightAware only sees about two days ahead. Flights further out have no live schedule or gate.

  • It does not control the simulator. It never claims your plan was imported, your aircraft spawned, or your thrust was set.

For flight simulation only. Never use any output of this project for real-world flight planning or aircraft operation.

Contributing

Issues and pull requests are welcome. Read CONTRIBUTING.md for setup, tests, and the evaluation rules, and SECURITY.md to report a vulnerability privately. The roadmap and backlog show what's next.

License

GPL-3.0-only. The takeoff N1 estimator ports the thrust-limit lapse shape of FlyByWire A32NX ThrustLimits_A32NX.hpp (GPL-3.0, commit 66021c2), so the whole project is distributed under the GPL. Bring your own keys and compute: no credentials, hosted service, or ChatGPT plan access are included.

Infinite Flight Agent is an independent project. It is not affiliated with or endorsed by Infinite Flight LLC, FlightAware, SimBrief or Navigraph, Browserbase, OpenAI, or FlyByWire Simulations. All trademarks belong to their owners.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    B
    quality
    A
    maintenance
    Enables flight planning and aviation operations through intelligent airport resolution, great-circle route calculation, and aircraft performance estimation. Supports 28,000+ airports worldwide and 190+ aircraft types for comprehensive flight planning via natural language.
    46
    4
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    SimBrief MCP Server brings flight planning data directly into your AI workspace. Access your SimBrief flight plans (OFP), retrieve real-time METAR weather reports for any airport, and fetch pilot information - all through natural conversation. Built for virtual pilots who want to streamline their pre-flight briefing workflow in Microsoft Flight Simulator, X-Plane, and other flight simulation platf
    14
    2
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to access and manage your Flighty flight data directly from the local macOS app database, supporting flight lists, status, searches, additions, and more.
    22
    MIT