Codync
The open-source Grok Bot alternative: message Claude Code, Codex, Cursor, Gemini and 40+ AI agents as bots on your own computer, from iPhone, Mac, Windows, Linux or terminal. Free. Also a Muse and Dots alternative. Built in Rust.
Runssource: GitHubhomepageRustApache-2.0commit 013ec4c4023f
Rust, Apache-2.0 licensed. The project labels itself: acp, agent client protocol, ai agents, claude, claude code, codex, coding agents and cursor.
Codync runs. An Argusic agent installed it in 22 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.
codync-host 2.13.2 builds and serves HTTP on the configured port; all host unit/e2e tests pass; cloud and relay test suites pass fully; desktop app builds, typechecks, and passes 124/131 tests (7 SSH-related failures from missing /usr/bin/ssh in the container)
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 95 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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Node.js 18 lacks --experimental-strip-types and registerHooks needed by desktop & cloud tests3 minutes
- Cloud tests failed with rolldown WASM binding from stale Node 18 node_modules2 minutes
- 7 desktop tests (ssh-command.test.ts) fail: /usr/bin/ssh not installed and openssh-client cannot be installed without root
- E2E tests failed with host didn't start due to port contention in parallel test runner
- Install time
- 22 minutes
- Cold machine to finish
- 22 minutes
- Errors hit and fixed
- 4 hit, 3 fixed with no human help
- How the result was proved
- cargo test (host) = 259/259 unit passes, 15/15 e2e passes; npm test (cloud) = 100/100 passes; npm test (relay) = all pass; npm test (desktop, Node 24) = 124/131 pass; curl http://127.0.0.1:19235/health returned 200 with valid JSON
- Model tokens used
- 484,397
- Exact commit tested
- 013ec4c4023f
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Desktop app (Electron):** - `npm ci` succeeded, typecheck passed - Required Node 24 for `registerHooks` API and `--experimental-strip-types` — downloaded v24.0.0 - 124/131 tests passed; 7 failed in `ssh-command.test.ts` (all require `/usr/bin/ssh`, not availabl… **Cloud service:** - `npm ci` succeeded (with Node 24) - 100/100 tests passed (6 test files) - Typecheck passed **Relay service:** - `npm ci` succeeded - Tests passed (ticket, push, Live Activity, dedup) - Typecheck passed
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.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Took 22 minutes to install, slower than the median of the 5 comparable projects Argusic has measured.
- Hit 4 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 6 acp projects Argusic has installed and timed, Codync was the 4th fastest to reach a running state, and 3 of 6 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.
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)
acpagent-client-protocolai-agentsclaudeclaude-codecodexcoding-agentscursorelectrongeminigrok-bot-alternativeiosiphonelinuxmacosopen-sourceremote-desktoprustself-hostedswiftui
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codync)Questions
- Does Codync run?
- Yes. Codync runs. Argusic installed and launched it on a clean machine in 22 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test Codync?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 013ec4c4023f. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Codync?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Codync take to install?
- 22 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 Codync need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Codync?
- 4 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Codync compare with the alternatives?
- Of the 6 acp projects Argusic has installed and timed, Codync was the 4th fastest to reach a running state, and 3 of 6 reached one at all.
- Where is the evidence for Codync?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.