FauxPilot

Self-hosted Copilot-API server on your own GPU — now dormant

Code & Dev Tools Open Source Open Source
Researched · Published · Reviewed
RECATOOLS Score
4.2 / 10
Capability
4
Value for money
7
Ease of use
3
ASEAN readiness
6
API quality
5
Founded
2022
HQ
Remote
Users
20000+ GitHub stars
Launched
Jul 2026
Developer
FauxPilot Community

Overview

Open-source, self-hosted server that mimics GitHub Copilot's API, serving completions from Salesforce CodeGen models on NVIDIA Triton. Code never leaves your hardware, but development has been dormant since 2024 and the base models are dated.

Advertisement

Pricing

Pricing shown for reference only. These figures reflect RECATOOLS research as of 11 Jul 2026 and may be out of date or incomplete. This is not financial or purchasing advice — always confirm the current price on the provider’s official website before making any decision.

Free
Free
Fully free

Use cases

Running AI code completion on an air-gapped development network Complete privacy for commercial codebase development without cloud API exposure Research into self-hosted AI coding assistance infrastructure
Advertisement

ASEAN Perspective

FauxPilot in Southeast Asia

ASEAN-region availability and pricing notes coming soon. Drop the editorial team a note via /contact/ if you can supply local context (Singapore/Malaysia/Indonesia/Thailand/Vietnam).

RECATOOLS Verdict

FauxPilot proved in 2022 that you could run a Copilot-style completion server on your own hardware — Salesforce CodeGen models on NVIDIA Triton, speaking GitHub Copilot's own API — which made it the reference point for teams that wouldn't send code to the cloud. That concept won; this implementation didn't. The repo has been dormant since around April 2024 with no releases ever published, and its CodeGen base models are generations behind current open code models. For real self-hosted coding assistance now, Tabby, Continue, or an Ollama-backed setup is more current, easier to run, and actually maintained. FauxPilot is worth knowing as the category's proof of concept — not the tool to standardise on in 2026.

Independent AI-assisted assessment by RECATOOLS.

What people say

Don't build on this in 2026. FauxPilot's GitHub repo is still up — 14.7k stars, zero published releases — but the commit history goes quiet around April 2024, and the README's support policy is literally the word "lmao." Community round-ups of self-hosted coding assistants stopped recommending it back in early 2024 for exactly this reason.

Which is a shame, because the idea was ahead of its time. In 2022, FauxPilot proved you could stand up a server that speaks GitHub Copilot's own API, point your VS Code or JetBrains plugin at it, and get completions from Salesforce CodeGen models running on NVIDIA's Triton Inference Server with the FasterTransformer backend — without a single line of code leaving your network. For banks, defence contractors and NDA-bound teams, that was the whole pitch, and it worked.

The problems are the base models and the plumbing. CodeGen was respectable in 2022 and is nowhere near current open code models like Qwen2.5-Coder or DeepSeek-Coder. Triton plus FasterTransformer is a heavyweight, fiddly stack that demands a serious NVIDIA GPU and real Docker patience, and nobody is fixing its rough edges anymore. For the same privacy guarantee today, Tabby gives you a maintained self-hosted assistant, Continue plus an Ollama backend takes twenty minutes to set up, and both serve models years ahead of anything FauxPilot ships.

Credit where due: it demonstrated the self-hosted Copilot category before almost anyone else. But a dormant repo serving 2022-era models is a reference, not a tool.

Summary of public user & expert reviews, compiled by RECATOOLS.

Notable facts

  • FauxPilot was created within weeks of GitHub Copilot's general availability, demonstrating how quickly the open-source community reacts to commercial AI tool launches.
  • The project was named as a deliberate pun — 'faux' (fake in French) + 'Pilot', reflecting its nature as an open-source alternative to GitHub's Copilot.
  • FauxPilot's architecture works by intercepting Copilot API requests in the IDE and redirecting them to a local server — no IDE modification required.

Frequently asked questions

Is FauxPilot free?
Yes. Open source, you only pay for your GPU hardware or cloud compute.
Does FauxPilot send code to the cloud?
No. All inference runs on your own hardware with no external API calls.
How does FauxPilot compare to GitHub Copilot quality?
Quality depends on the model used. SantaCoder-based completions are good but not at GPT-4 level used by Copilot.
What hardware is needed?
An NVIDIA GPU with at least 8GB VRAM for smaller models; 24GB+ for SantaCoder 1.1B.
Does FauxPilot work with VS Code?
Yes. Configure the Copilot extension to point to your local FauxPilot server.

About this listing

Researched on
Published on
Last reviewed

This entry was compiled from publicly available data including FauxPilot's official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with FauxPilot unless explicitly stated.

Data accuracy

Third-party AI tools update their pricing, features, availability, and policies frequently. Information here may be outdated by the time you read this — we make reasonable efforts to keep listings current, but cannot guarantee absolute accuracy.

For the latest details, please refer to FauxPilot directly →

Spotted something out of date? Suggest an update →

Advertisement