moltis
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware.
Runs with mockssource: GitHubhomepageRustMITcommit 9c7ea0700a87
Rust, MIT licensed. The project labels itself: ai agent, ai assistant, clawdbot, llm, mcp, openclaw, rust and sandbox.
moltis runs, with stand-ins for the services it depends on. An Argusic agent installed it in 30 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Moltis gateway binary compiles from source in a fresh Ubuntu 24.04 container, launches on HTTP, prints the setup code banner, and 2810 unit tests pass across 15 of 59 workspace crates, with 5 pre-existing infrastructure-missing test failures (ssh-keygen, WASM, Docker).
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 92 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.
- libclang not found — llama-cpp-2 (bindgen) cannot compile5 minutes
- Rust toolchain not installed (no rustc/cargo)1 minute
- 3 test failures in moltis-httpd: ssh_keygen not found on system
- 2 test failures in moltis-tools: WASM sandbox not compiled + flaky docker fallback test
- Install time
- 30 minutes
- Cold machine to finish
- 48 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- cargo build --no-default-features -p moltis succeeded (exit 0); ./target/debug/moltis --version returned 'moltis 0.1.0'; gateway started on port 34500 printed full banner with setup code; 2810 tests passed across 15 crates
- Model tokens used
- 183,869
- Exact commit tested
- 9c7ea0700a87
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
moltis-code-index: 40 passed, 0 failed moltis-tools: 885 passed, 2 failed (1 WASM not compiled, 1 flaky docker fallback) moltis-auth: 49 passed, 0 failed moltis-vault: 44 passed, 0 failed moltis-skills: 166 passed, 0 failed moltis-projects: 40 passed, 0 failed === Total: 2810 passed, 5 infra-missing failures === Now let me produce the final structured report. 2026-09-17T23:04:19.397471Z ERROR codex_core::session: failed to record rollout items: thread 01a0b… tokens used 183,869 Now let me produce the final structured report.
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
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 30 minutes to install, slower than the median of the 11 comparable projects Argusic has measured.
Of the 12 ai-agent projects Argusic has installed and timed, moltis was the 12th fastest to reach a running state, and 9 of 12 reached one at all.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.14 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.10 |
Topics (from GitHub)
ai-agentai-assistantclawdbotllmmcpopenclawrustsandboxself-hostedsingle-binarytelegram-botvoice-assistant
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/moltis)Questions
- Does moltis run?
- moltis runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 30 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test moltis?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9c7ea0700a87. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test moltis?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does moltis take to install?
- 30 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 moltis need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing moltis?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does moltis compare with the alternatives?
- Of the 12 ai-agent projects Argusic has installed and timed, moltis was the 12th fastest to reach a running state, and 9 of 12 reached one at all.
- Where is the evidence for moltis?
- All 2 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.