memfree
MemFree - Hybrid AI Search Engine & AI Page Generator
Runs with mockssource: GitHubhomepageTypeScriptMITcommit 3163843f3475
TypeScript, MIT licensed. The project labels itself: ai, ai search, ai search engine, devfast, generate ui, hacktoberfest, hacktoberfest accepted and hybrid ai search.
memfree runs, with stand-ins for the services it depends on. An Argusic agent installed it in 8 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The MemFree monorepo has all packages installed (bun i succeeded in frontend, vector, mdreader, and extention). The frontend test suite passes 13/13. The Next.js dev server starts and serves HTTP 200 at /. The mdreader launches and returns HTTP 200. The vector service launches and responds to requests. 1 vector local test (compact) passes.
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 56 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.
- Frontend test 'should update the active search' failed because updateActiveSearch didn't sync changes back to the searches array3 minutes
- Vector redis tests require real Upstash Redis (the @upstash/redis SDK uses internal pipeline protocol not compatible with a simple HTTP mock)2 minutes
- Vector embedding tests connect to real OpenAI API and fail with 401 on mock key
- 6 vector test files import functions (changeEmbedding, createEmptyTable, checkout, deleteUrls, reCreateEmptyTable) that were commented out in db.ts
- Install time
- 8 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- cd /work/repo/frontend && bun run test => 2 suites passed, 13 tests passed. curl -s -o /dev/null -w '%{http_code}' http://localhost:3000 => 200 after full Next.js compilation. curl -s http://localhost:3006/ => 'Welcome to mdreader' HTTP 200. bun run index.ts in vector/ => Listening on port and returning HTTP 401 (auth required, correct behavior).
- Model tokens used
- 83,964
- Exact commit tested
- 3163843f3475
- 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.
import { describe, it } from "bun:test";
import { reCreateEmptyTable } from "../db";
const testUser = process.env.TEST_USER || "localTest";
=== test/select-detail.test.ts ===
import { describe, it } from "bun:test";
import { DatabaseFactory } from "../db";
import { testConfig } from "../config";
import { documentSchema, testSchema } from "../schema";
Now I have all the data compiled. Here's the final report:
tokens used
83,964
Now I have all the data compiled. Here's 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
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
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.
- Took 8 minutes to install, slower than the median of the 102 comparable projects Argusic has measured.
Of the 103 ai projects Argusic has installed and timed, memfree was the 62nd fastest to reach a running state, and 71 of 103 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.12 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.25 |
Topics (from GitHub)
aiai-searchai-search-enginedevfastgenerate-uihacktoberfesthacktoberfest-acceptedhybrid-ai-searchpage-generatorreactsearch-engineserverless-vectorshadcn-uivector-search
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/memfree)Questions
- Does memfree run?
- memfree runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 8 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test memfree?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3163843f3475. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test memfree?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does memfree take to install?
- 8 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 memfree need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing memfree?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does memfree compare with the alternatives?
- Of the 103 ai projects Argusic has installed and timed, memfree was the 62nd fastest to reach a running state, and 71 of 103 reached one at all.
- Where is the evidence for memfree?
- 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.