codify
The ai agent workflow tool that scales from small, simple projects to large, complex codebases. Community Maintained Version (OSS)
Runssource: GitHubhomepageTypeScriptApache-2.0commit 72d51fad0a11
TypeScript, Apache-2.0 licensed. The project labels itself: agent, agent memory, agent orchestration, agentic workflow, ai, codify, workflow and workflow automation.
codify runs. An Argusic agent installed it in 12 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
cg binary (2.5 MB, v1.3.0) compiles from source, indexes 282 files into a SQLite code graph, runs all 356 unit tests and all 40 integration tests passing, and responds to commands like --version, init, search, and serve over stdio.
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.
- libsqlite3-dev package not installed (only libsqlite3-0 runtime present)3 minutes
- sqlite3 CLI binary not in PATH, causing 2 integration test failures1 minute
- Install time
- 12 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- make unit passed 356/356 tests across 7 suites; make integration passed 40/40 test scripts with sqlite3 CLI in PATH
- Model tokens used
- 203,530
- Exact commit tested
- 72d51fad0a11
- 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 1, run , the attempt that decided the verdict above. 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.
**Unit tests**: 356/356 passed (config: 95, drivers: 52, json: 17, kvx: 52, lang: 105, sha256: 6, u… **Integration tests**: 40/40 passed (graph, vcs, agentic, mcp, spec, watch, trace, memory, root, li… **End-to-end**: `cg init` indexes 282 files into the graph, `cg search`, `cg serve` JSON-RPC over s… tokens used 203,530 Here's the final summary of everything done: **Build**: Compiled `cg` (2.5 MB static binary, v1.3.0) from C11 source with `cc` and extracted `li… **Error 1** — Missing `libsqlite3-dev` (only `libsqlite3-0` runtime present, no `sqlite3.h` or `.so… **Error 2** — Missing `sqlite3` CLI tool (affecting integration tests 15_accuracy.sh and 21_groundi… **Unit tests**: 356/356 passed (config: 95, drivers: 52, json: 17, kvx: 52, lang: 105, sha256: 6, u… **Integration tests**: 40/40 passed (graph, vcs, agentic, mcp, spec, watch, trace, memory, root, li… **End-to-end**: `cg init` indexes 282 files into the graph, `cg search`, `cg serve` JSON-RPC over s…
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.
- Recovered from all 2 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 12 minutes to install, slower than the median of the 140 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 141 agent projects Argusic has installed and timed, codify was the 96th fastest to reach a running state, and 94 of 141 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)
agentagent-memoryagent-orchestrationagentic-workflowaicodifyworkflowworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codify)Questions
- Does codify run?
- Yes. codify runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test codify?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 72d51fad0a11. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test codify?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does codify take to install?
- 12 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 codify need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing codify?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does codify compare with the alternatives?
- Of the 141 agent projects Argusic has installed and timed, codify was the 96th fastest to reach a running state, and 94 of 141 reached one at all.
- Where is the evidence for codify?
- 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.