twinny
Open-source AI coding assistant for VS Code. Coding agent, code completion, chat, edits and reviews with local or hosted models. Your models, your infrastructure.
Runssource: GitHubhomepageTypeScriptMITcommit 4685b7fb87ca
TypeScript, MIT licensed. The project labels itself: ai coding assistant, artificial intelligence, code chat, code completion, code generation, code review, code review assistant and developer tools.
twinny runs. An Argusic agent installed it in 5.5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
npm install completed, TypeScript compilation and esbuild bundling succeed, the full VS Code extension test suite passes (642 passed, 0 failed), and both twinny-node and twinny-server CLI binaries respond correctly.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
- Install time
- 6 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- xvfb-run -a npm test: 642 passing, 4 pending, 0 failing, exit code 0. twinny-server --version: 4.2.1. twinny-node --help: printed usage.
- Model tokens used
- 83,582
- Exact commit tested
- 4685b7fb87ca
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 2, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
The test suite exercises real extension behavior (completion lifecycle, chat, embeddings, gateway, … tokens used 83,582 Everything works. Let me compile the final report. **Observations from the full session:** - **`npm install`** installed 1549 packages with only deprecation warnings (no errors). - **`npm run build-tests`** (TypeScript compilation) completed successfully. - **`npm run build`** (esbuild bundling) completed successfully. - **`xvfb-run -a npm test`** ran the full VS Code integration test suite against a real VS Code ins… - **`node:sqlite`** is unavailable (Node 18.19.1 vs required 22+), so the one standalone test was s… - **`twinny-node --help`** prints usage; **`twinny-server --version`** prints `4.2.1`. Both CLIs ar… The test suite exercises real extension behavior (completion lifecycle, chat, embeddings, gateway, …
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 5.5 minutes, faster than the median of the 7 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 3 times, so the result is not a one-off.
Of the 8 ai-coding-assistant projects Argusic has installed and timed, twinny was the 3rd fastest to reach a running state, and 8 of 8 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 5.5 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
ai-coding-assistantartificial-intelligencecode-chatcode-completioncode-generationcode-reviewcode-review-assistantdeveloper-toolsembeddingsllamacppllmlocal-aiollamaprivate-aiself-hostedself-hosted-aiself-hosted-llmvscode-extension
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/twinny)Questions
- Does twinny run?
- Yes. twinny runs. Argusic installed and launched it on a clean machine in 6 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test twinny?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4685b7fb87ca. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test twinny?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does twinny take to install?
- 5.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does twinny need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing twinny?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does twinny compare with the alternatives?
- Of the 8 ai-coding-assistant projects Argusic has installed and timed, twinny was the 3rd fastest to reach a running state, and 8 of 8 reached one at all.
- Where is the evidence for twinny?
- All 3 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.