intent
Open-source workspace for coding agents: specialists plan, then Claude Code, Codex & Cursor build in parallel, on your machines or in the cloud.
Runssource: GitHubhomepageJavaScriptApache-2.0commit 39e2b86821f3
JavaScript, Apache-2.0 licensed. The project labels itself: agent orchestration, ai agents, claude code, codex, coding agents, cursor, developer tools and e2b.
intent runs. An Argusic agent installed it in 10 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
intentd 0.11.190 builds and runs on Linux x86_64 with Rust 1.96.0; the backend daemon binary (390 MB debug) compiles, prints version, and passes 140+ tests across 14 crate test suites with zero failures
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.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- bootstrap-dev-host failed because Node 24 and system packages (gh, shellcheck) require root for apt-get5 minutes
- ACP callback fixture requires Node v24.21.0 but the build used v24.22.32 minutes
- make test-intentd rebuilds all crates into a separate target directory, exceeding the time budget1 minute
- Install time
- 10 minutes
- Cold machine to finish
- 71 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- make build-intentd compiled intentd successfully; target/debug/intentd --version returned 'intentd 0.11.190'; prebuilt test binaries from intent-gates ran 140+ tests across 14 crates all passed (daemon_test, intentd-fe22, e2e_core_slug_and_config, e2e_core_daemon_control, note_write_path_lint, observation_adapter, observation_policy, cli_help, build_script, e2e_pty_job_control, intent_svc_runtime, install_ps1_daemon_mode, install_ps1_owner, install_sh_daemon_mode, install_sh_probe, install_sh_startup); intentd doctor confirmed the daemon is functional
- Model tokens used
- 138,383
- Exact commit tested
- 39e2b86821f3
- 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.
echo "Build time: ~6m 51s"
echo "Test binaries verified: 14 crates, 140+ tests passed"' in /work/repo
succeeded in 0ms:
-rwxrwxr-x 2 runner runner 390M Nov 12 07:25 /work/repo/packages/intentd/target/debug/intentd
Runtime since start of work: ~70 minutes
Build time: ~6m 51s
Test binaries verified: 14 crates, 140+ tests passed
exec
/bin/sh -lc "echo 'ARGUSIC_RESULT: {\"install_succeeded\": true, \"launch_succeeded\": true, \"inst…
succeeded in 0ms:
tokens used
138,383Replay 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.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- 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 10 minutes to install, slower than the median of the 20 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 21 agent-orchestration projects Argusic has installed and timed, intent was the 15th fastest to reach a running state, and 15 of 21 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 10 minutes after the clone.
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)
agent-orchestrationai-agentsclaude-codecodexcoding-agentscursordeveloper-toolse2bmcpopen-source
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/intent)Questions
- Does intent run?
- Yes. intent runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test intent?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 39e2b86821f3. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test intent?
- The run that produced this verdict cost $0.51: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does intent take to install?
- 10 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 intent need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing intent?
- 3 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 intent compare with the alternatives?
- Of the 21 agent-orchestration projects Argusic has installed and timed, intent was the 15th fastest to reach a running state, and 15 of 21 reached one at all.
- Where is the evidence for intent?
- 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.