Linghun

AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

Runs with mockssource: GitHubTypeScriptApache-2.0commit 05d8457bd04a

TypeScript, Apache-2.0 licensed. The project labels itself: agent runtime, agi, ai, ai agent, ai coding, capability runtime, coding agent and developer tools.

Linghun runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1.5 minutes and hit 10 errors on a clean machine with no GPU, and the whole session was recorded.

Install and build succeed CLI reports version 0 1 55 All commands render in help 6 of 13 failing test files fixed all remaining failures are pre-existing and confirmed in the original code

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 86 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
86 / 100
cost of the verifying run
$0.76 (measured)
recorded runs
1
last tested
stars
467
forks
19
open issues
0
watchers
1
size
28 MB
created
last push

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.

Time lost to each failure while testing Linghun, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • tui-interaction-contract: Todo test expected individual task summary that doesn't exist in refactored createTodoSurfacePreview3 minutes
  • mcp-index-runtime: bundled codebase-memory binary is Git LFS pointer, not real binary3 minutes
  • model-doctor-runtime: test expected English 'not configured/not-sent' but code now outputs Chinese '未生效'2 minutes
  • tui-interaction-contract: ProductBlock test checked for removed code pattern in refactored component2 minutes
  • failure-learning-runtime: Windows path test fails on Linux because basename doesn't parse backslashes2 minutes
  • index-runtime: Windows artifact path test fails on Linux because path.join uses forward slashes2 minutes
Install time
2 minutes
Cold machine to finish
74 minutes
Errors hit and fixed
10 hit, 7 fixed with no human help
How the result was proved
node apps/cli/dist/main.js --version returned '0.1.55'; node apps/cli/dist/main.js --help displayed all commands; 6 fixed test files now pass; pre-existing failures confirmed via git stash comparison
Model tokens used
4,207,477
Exact commit tested
05d8457bd04a
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.

2026-10-20T17:21:23.957387Z ERROR codex_core::session: failed to record rollout items: thread 01a15…
tokens used
4,207,477
Now I have the full picture. Here's the final report.
## Status
**Install & Build**: Succeeded. `node apps/cli/dist/main.js --version` returns `0.1.55`.
**CLI Verification**: `node apps/cli/dist/main.js --help` works properly, showing all commands.
**Test Fixes**: Fixed 6 of 13 failing test files by updating stale test expectations and adding pla…
**Remaining failures**: All pre-existing (confirmed by running the original code via `git stash`). …
- `packages/tui/src/index.test.ts` (849 tests, 113 failures — mostly provider/network timing integr…
- `packages/tools/src/index.test.ts` (4 failures — capability preflight and GB18030 encoding tests)
- `packages/tui/src/tui-permission-runtime.test.ts` (2 failures — architecture drift tests)

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

  • Installed in 1.5 minutes, faster than the median of the 4 comparable projects Argusic has measured.
  • Licensed Apache-2.0, as reported by its host.

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.
  • Hit 10 errors during setup, 3 of which were not solved.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 5 agent-runtime projects Argusic has installed and timed, Linghun was the 1st fastest to reach a running state, and 3 of 5 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks86.000.76

Topics (from GitHub)

agent-runtimeagiaiai-agentai-codingcapability-runtimecoding-agentdeveloper-toolsevidenceevidence-firsthallucination-resistantllmlocal-firstmulti-agentterminaltool-usetuitypescriptverification-loopworkflow-automation

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/Linghun.svg)](https://argusic.com/subject/linghun)

Questions

Does Linghun run?
Linghun runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 10 errors on the way, and recorded the session.
How did Argusic test Linghun?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 05d8457bd04a. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test Linghun?
The run that produced this verdict cost $0.76: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Linghun take to install?
1.5 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 Linghun need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Linghun?
10 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does Linghun compare with the alternatives?
Of the 5 agent-runtime projects Argusic has installed and timed, Linghun was the 1st fastest to reach a running state, and 3 of 5 reached one at all.
Where is the evidence for Linghun?
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.

Discussion