engram
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
Runssource: GitHubhomepageGoMITcommit e108c2f5fbbe
Go, MIT licensed.
engram runs. An Argusic agent installed it in 2 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Engram binary builds, serves HTTP API on port 7437 responding to health checks, CLI save/context/search/stats all work, MCP server initializes, doctor passes, built-in self-tests pass, and 150+ Go unit tests pass across all packages.
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.
- Go compiler not found in container2 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 28 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- curl -s http://localhost:7437/health returned 200 with version JSON; engram version returned 2.0.0; engram test --quick passed; engram save/context/stats CLI commands all worked; Go test suite passes for all individual packages
- Model tokens used
- 164,937
- Exact commit tested
- e108c2f5fbbe
- 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.
tokens used
164,937
Here's my final assessment:
**Build & install**: The binary built cleanly from source — `go build ./cmd/engram` produced a 30MB…
**CLI**: All commands work — `version`, `help`, `doctor` (7/7 checks pass), `save`, `context`, `sea…
**HTTP API**: Server starts on port 7437, `GET /health` returns `200 {"service":"engram","status":"…
**MCP server**: Initializes correctly via stdio JSON-RPC.
**Self-tests**: `engram test --quick` reports PASS (3 suites, 401ms).
**Go test suite**: All 20+ packages pass individually. `internal/store` has ~150 tests that all pas…
**Issues encountered & fixed**:
1. Go not installed — downloaded and installed Go 1.27.1
2. GOPATH/GOROOT collision — set to separate directoriesReplay 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 2 minutes.
- Recovered from all 1 error 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.
- Measured 2 times, so the result is not a one-off.
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 2 minutes after the clone.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/engram)Questions
- Does engram run?
- Yes. engram runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test engram?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e108c2f5fbbe. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test engram?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does engram take to install?
- 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 engram need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing engram?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for engram?
- 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.