aft

Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbol-aware edits, semantic search, code health, fast grep/glob, bash compression, background tasks, PTY.

Runssource: GitHubhomepageRustMITcommit 17f2c807c9f5

Rust, MIT licensed. The project labels itself: agent framework, ai, ai agents, ai agents framework, opencode, pi, pi coding agent and rag.

aft runs. An Argusic agent installed it in 54.2 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

AFT v0.58.0 builds from source with Rust and TypeScript. The Rust binary (aft) receives JSON-over-stdio commands and responds to version queries. All 3957 Rust unit tests pass. TypeScript plugin build produces working dist bundles. All Pi plugin tests pass (839). OpenCode plugin tests: 1566 pass, 3 are ordering-dependent flakes that pass in isolation.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.41 (measured)
recorded runs
1
last tested
stars
348
forks
48
open issues
52
watchers
2
size
173 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 aft, 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.

  • Rust lib tests: 3 agent_child_env hook tests failed (duplicate Co-authored-by trailers)8 minutes
  • Missing unzip binary - 5 TypeScript tests failed4 minutes
  • Rust lib tests: InsecureParentDirectory error in 24 gh_shim/subc tests2 minutes
  • Pi plugin: read vision capability test used legacy gh_read config key1 minute
  • Missing rustc and cargo toolchain0.5 minutes
  • Missing bun runtime0.5 minutes
Install time
54 minutes
Cold machine to finish
55 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
cargo test -p agent-file-tools --lib: 3957 passed, 0 failed; bun test (opencode): 1566 pass, 3 pre-existing ordering failures; bun test (pi): 839 pass, 0 fail; cargo test (aft-tokenizer): 3 passed; cargo test integration (list_envelope_bash): 17 passed; cargo build --release: success; bun run build: success; ./aft binary responds to version command with 0.58.0
Model tokens used
845,358
Exact commit tested
17f2c807c9f5
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.

### Issues Fixed
1. **Missing `unzip`** — 5 TypeScript tests failed. Compiled `unzip` 6.00 from Info-ZIP source.
2. **`InsecureParentDirectory` in 24 Rust tests** — `tempfile::tempdir()` created dirs with `0775` …
3. **3 agent_child_env hook tests** — `git interpret-trailers --if-exists doNothing` didn't recogni…
4. **Pi plugin vision test** — Used legacy `gh_read.enabled` config key instead of `github.read`. F…
### Test Results
- **Rust lib tests**: 3957 passed, 0 failed
- **Tokenizer tests**: 3 passed
- **Integration tests** (list_envelope_bash): 17 passed
- **OpenCode plugin**: 1566 pass, 3 pre-existing ordering-dependent flakes, 86 skipped (subc-core n…
- **Pi plugin**: 839 pass, 0 fail, 3 skipped (subc-core/infra)
- **Binary verification**: `{"id":"1","success":true,"version":"0.58.0"}`

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 6 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 MIT, as reported by its host.

What did not, or is not known

  • Took 54.2 minutes to install, slower than the median of the 63 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 64 agent-framework projects Argusic has installed and timed, aft was the 64th fastest to reach a running state, and 51 of 64 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.41

Topics (from GitHub)

agent-frameworkaiai-agentsai-agents-frameworkopencodepipi-coding-agentragvector-search

Embed the badge

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

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

Questions

Does aft run?
Yes. aft runs. Argusic installed and launched it on a clean machine in 54 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test aft?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 17f2c807c9f5. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test aft?
The run that produced this verdict cost $0.41: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does aft take to install?
54.2 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 aft need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing aft?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does aft compare with the alternatives?
Of the 64 agent-framework projects Argusic has installed and timed, aft was the 64th fastest to reach a running state, and 51 of 64 reached one at all.
Where is the evidence for aft?
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