{"data":{"slug":"fauxpilot-fauxpilot","name":"fauxpilot","tagline":"Open-source alternative to GitHub Copilot server","github_url":"https://github.com/fauxpilot/fauxpilot","owner":"fauxpilot","repo":"fauxpilot","owner_avatar_url":"https://avatars.githubusercontent.com/u/120729571?v=4","primary_language":"Python","stars":14681,"forks":638,"topics":[],"archived":false,"github_pushed_at":"2024-04-09T08:42:23+00:00","maintenance_label":"Dormant","stars_delta_30d":-32,"url":"https://www.graphcanon.com/tools/fauxpilot-fauxpilot","markdown_url":"https://www.graphcanon.com/tools/fauxpilot-fauxpilot.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fauxpilot-fauxpilot","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fauxpilot-fauxpilot","description":"FauxPilot - an open-source alternative to GitHub Copilot server","homepage_url":null,"license":"MIT","open_issues":63,"watchers":120,"ai_summary":"FauxPilot is an open-source project aiming to create a locally hosted alternative to GitHub Copilot. It leverages the SalesForce CodeGen models within NVIDIA's Triton Inference Server using the FasterTransformer backend.","readme_excerpt":"# FauxPilot\n\nThis is an attempt to build a locally hosted alternative to [GitHub Copilot](https://copilot.github.com/). It uses the [SalesForce CodeGen](https://github.com/salesforce/CodeGen) models inside of NVIDIA's [Triton Inference Server](https://developer.nvidia.com/nvidia-triton-inference-server) with the [FasterTransformer backend](https://github.com/triton-inference-server/fastertransformer_backend/).\n\n

\n \n

\n\n## Prerequisites\n\nYou'll need:\n\n* Docker\n* `docker compose` >= 1.28\n* An NVIDIA GPU with Compute Capability >= 6.0 and enough VRAM to run the model you want.\n* [`nvidia-docker`](https://github.com/NVIDIA/nvidia-docker)\n* `curl` and `zstd` for downloading and unpacking the models.\n\nNote that the VRAM requirements listed by `setup.sh` are *total* -- if you have multiple GPUs, you can split the model across them. So, if you have two NVIDIA RTX 3080 GPUs, you *should* be able to run the 6B model by putting half on each GPU.\n\n\n## Support and Warranty\n\nlmao\n\nOkay, fine, we now have some minimal information on [the wiki](https://github.com/moyix/fauxpilot/wiki) and a [discussion forum](https://github.com/moyix/fauxpilot/discussions) where you can ask questions. Still no formal support or warranty though!\n\n\n\n## Setup\n\nThis section describes how to install a Fauxpilot server and clients.\n\n### Setting up a FauxPilot Server\n\nRun the setup script to choose a model to use. This will download the model from [Huggingface/Moyix](https://huggingface.co/Moyix) in GPT-J format and then convert it for use with FasterTransformer.\n\nPlease refer to [How to set-up a FauxPilot server](documentation/server.md).\n\n\n### Client configuration for FauxPilot\n\nWe offer some ways to connect to FauxPilot Server. For example, you can create a client by how to open the Openai API, Copilot Plugin, REST API.\n\nPlease refer to [How to set-up a client](documentation/client.md).\n\n\n## Terminology\n * API: Application Programming Interface\n * CC: Compute Capability\n * CUDA: Compute Unified Device Architecture\n * FT: Faster Transformer\n * JSON: JavaScript Object Notation \n * gRPC: Remote Procedure call by Google\n * GPT-J: A transformer model trained using Ben Wang's Mesh Transformer JAX \n * REST: REpresentational State Transfer","github_created_at":"2022-08-03T02:14:22+00:00","created_at":"2026-07-11T23:20:24.4249+00:00","updated_at":"2026-09-20T04:31:36.737454+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"ai-assisted-coding","name":"ai-assisted coding"},{"slug":"code-generation","name":"code-generation"},{"slug":"docker","name":"docker"},{"slug":"fastertransformer","name":"fastertransformer"},{"slug":"github-copilot-alternative","name":"github copilot alternative"},{"slug":"local-hosting","name":"local hosting"},{"slug":"nvidia-triton-inference-server","name":"nvidia triton inference server"},{"slug":"salesforce-codegen","name":"salesforce codegen"}],"trust":{"provenance":{"is_fork":false,"github_id":520708737,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:33:03.201Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":891,"last_release_at":null,"stars_delta_30d":-32,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:33:05.431Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:33:02.093Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:33:02.093Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:33:02.093Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"FauxPilot is open-source under the MIT license, free to use, but users must provide their own hardware and manage the setup."},"requirements":{"notes":["Requires Docker and `docker compose` version 1.28 or higher.","An NVIDIA GPU with Compute Capability >= 6.0 and enough VRAM to run the chosen model is required.","The setup script downloads models from Huggingface/Moyix in GPT-J format and converts them for use with FasterTransformer."],"min_ram_gb":null,"requires_docker":true},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":true},"when_to_use":["When you need an open-source alternative to GitHub Copilot that can be hosted locally.","If you have access to an NVIDIA GPU with Compute Capability >= 6.0 and sufficient VRAM to run the desired model.","For developers who prefer to use open-source tools and have control over the AI models used in their development environment."],"when_not_to_use":["If you do not have access to an NVIDIA GPU with the required Compute Capability and VRAM.","When formal support and warranty are necessary, as FauxPilot does not offer these.","For users who prefer a fully managed service without the need to set up and maintain a local server."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:43:18.859Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":true},"decision_summary":[{"label":"Pricing","value":"freemium - FauxPilot is open-source under the MIT license, free to use, but users must provide their own hardware and manage the setup."},{"label":"Requirements","value":"Requires Docker; Requires Docker and `docker compose` version 1.28 or higher.; An NVIDIA GPU with Compute Capability >= 6.0 and enough VRAM to run the chosen model is required.; The setup script downloads models from Huggingface/Moyix in GPT-J format and converts them for use with FasterTransformer."},{"label":"Adopt for","value":"FauxPilot is an open-source alternative to GitHub Copilot, designed for local hosting and leveraging SalesForce CodeGen models with NVIDIA's Triton Inference Server and FasterTransformer backend."}]}}