okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

Runssource: GitHubhomepageGoMITcommit 007ab4325fb4

Go, MIT licensed. The project labels itself: agent memory, ai agents, bm25, coding agents, developer tools, git native, go and golang.

okf-agent-memory runs. An Argusic agent installed it in 3 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

The okf binary compiles, runs, validates its own knowledge bundle with zero errors/warnings/orphans, performs BM25 semantic search across the knowledge corpus returning correct results, and all 7 Go packages (including vault, sync, okf core, CLI, and AAG linter) pass their full test suites with no failures and no race conditions.

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
$0.02 (measured)
recorded runs
2
last tested
stars
871
forks
72
open issues
2
watchers
6
size
1 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.

Install time
3 minutes
Cold machine to finish
4 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
make build produced bin/okf (11MB); ./bin/okf version returned 'okf version v0.0.0-20260927202010-007ab4325fb4 (OKF v0.2 specification)'; go test -count=1 ./... passed all 7 packages (0 failures); ./bin/okf validate knowledge --strict --drift returned '0 error(s), 0 gate finding(s), 0 warning(s), 0 broken link(s), 0 orphan(s), 0 stale. Conformant.'; ./bin/okf search architecture knowledge returned 10 matching concepts
Model tokens used
47,930
Exact commit tested
007ab4325fb4
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.

okf version v0.0.0-20260927202010-007ab4325fb4 (OKF v0.2 specification)
ok    github.com/okf-memory/okf-agent-memory/cmd/okf  0.005s
?     github.com/okf-memory/okf-agent-memory/cmd/okf-benchmark  [no test files]
ok    github.com/okf-memory/okf-agent-memory/internal/cli  0.040s
ok    github.com/okf-memory/okf-agent-memory/pkg/okf  0.569s
ok    github.com/okf-memory/okf-agent-memory/pkg/okf/aag  0.003s
ok    github.com/okf-memory/okf-agent-memory/pkg/sync  0.707s
ok    github.com/okf-memory/okf-agent-memory/pkg/vault  0.470s
Now I have all the data. Here is the final report:
tokens used
47,930
Now I have all the data. Here is the final 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

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 3 minutes.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

Of the 28 agent-memory projects Argusic has installed and timed, okf-agent-memory was the 11th fastest to reach a running state, and 24 of 28 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 3 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

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 Runner2/3Runs100.000.02
Argusic Runner1/3Runs100.000.24

Topics (from GitHub)

agent-memoryai-agentsbm25coding-agentsdeveloper-toolsgit-nativegogolangknowledge-baseknowledge-graphllm-memorymarkdownmcpmcp-servermodel-context-protocolokfopen-knowledge-formatpersistent-memory

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/okf-agent-memory.svg)](https://argusic.com/subject/okf-agent-memory)

Questions

Does okf-agent-memory run?
Yes. okf-agent-memory runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test okf-agent-memory?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 007ab4325fb4. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test okf-agent-memory?
The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does okf-agent-memory take to install?
3 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 okf-agent-memory need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing okf-agent-memory?
Nothing did, in the recorded run: zero errors between clone and running.
How does okf-agent-memory compare with the alternatives?
Of the 28 agent-memory projects Argusic has installed and timed, okf-agent-memory was the 11th fastest to reach a running state, and 24 of 28 reached one at all.
Where is the evidence for okf-agent-memory?
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.

Discussion