Tabby replaces 4 paid apps
One open-source tool, 4 subscriptions it can stand in for. Each pairing below is curated and verified by hand, with the honest catch spelled out. No votes, no pay-to-list.
licenseApache-2.0
runsyour server
installRun the server from Docker or a standalone binary, then connect an editor extension
enginesLocal llama.cpp-backed completion, chat and embedding models or separately configured remote HTTP model endpoints
dataModels, configuration, logs, indexed source and Tabby's database live under TABBY_ROOT, which defaults to the user's .tabby directory
setupDownload and size suitable models, provide enough GPU or RAM, start the server, and configure each editor client
facts verified 2026-08-10
Copilot-shaped completions and chat, paid for with your own GPU instead of a seat.
the catchCompletion quality and latency depend on the chosen model and hardware, and the GitHub and editor experience is less turnkey than Copilot.
the verdict →all GitHub Copilot alternatives →
Self-hosted completions and chat inside JetBrains; your GPU becomes the subscription.
the verdict →
The direct answer: self-hosted repository completions and chat through your own models.
the verdict →
Self-hosted repository completions and chat, without Sourcegraph's enterprise search layer.
the catchIt covers self-hosted completions and chat, but not Sourcegraph's enterprise-scale cross-repository search and context graph.
the verdict →all Sourcegraph Cody alternatives →last updated 2026-08-10 · up to $348/yr replaced · no votes, no pay-to-list
