#8686th of 107 in Coding agents and AI editors
twinny
VS Code assistant for completion, chat and edits against your own model server
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.7k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- TypeScript
3,579 on 31 Mar 20263,673 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
twinny is a VS Code extension that provides fill-in-the-middle completion, inline diff edits, chat with @-attached context, an experimental agent mode, workspace indexing and code review. It connects to local servers (Ollama, LM Studio, llama.cpp), paired devices, hosted APIs, or a shared twinny-server gateway for teams. It has no telemetry or sign-in; the gateway is free for five developers and paid per seat beyond that.
Who it is for: Developers and teams wanting a self-hosted-model coding assistant inside VS Code
Strengths
- Works with Ollama, LM Studio, llama.cpp, OpenAI-compatible servers, and hosted APIs like OpenAI and Anthropic
- No telemetry and no account; prompts go only to the server you configure
- Inline edits shown as diffs with per-hunk accept or reject
- Team gateway runs via npx with per-developer keys and usage metrics
Weaknesses
- VS Code only (1.93 or newer); no other editors mentioned
- Agent mode is labelled experimental
- Team policy, recording, plugins and SSO need a paid licence ($15 per seat per month)
- Maintained by one person; README says provided as is
What it needs
- GPU optional
- Needs VS Code 1.93+, Model server (Ollama, LM Studio, llama.cpp, or hosted API)
- Models: Ollama, LM Studio, llama.cpp, OpenAI-compatible servers, OpenAI
Also in Coding agents and AI editors
See all 107| Rank | Project | Score |
|---|---|---|
| 1 | claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs | 83 out of 100 |
| 2 | ArchonYAML workflow engine that runs AI coding agents through fixed dev steps | 83 out of 100 |
| 3 | Open SWEAgent that turns issues into pull requests, reviews PRs and monitors CI | 81 out of 100 |
| #4 | oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory | 80 out of 100 |
| #5 | gooseRust AI agent with desktop app, CLI and API, extended through MCP | 80 out of 100 |