Endoplexity
Agentic browser control driven by your own Claude / Cursor subscriptions
Runssource: GitHubTypeScriptApache-2.0commit 315e0d89e035
TypeScript, Apache-2.0 licensed. The project labels itself: ai agent, browser automation, cdp, chrome extension, claude, cursor and mcp.
Endoplexity runs. An Argusic agent installed it in 2.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Bridge runs on Node 24, MCP endpoint responds with 14 browser tools, 175/175 tests pass, .endo-token file created with 0600 permissions
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.
- Node.js v18.19.1 in container, but project requires Node >=24 (type stripping experimental feature)1.5 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test exited 0, 175 passed; curl to MCP endpoint returned 14 tools via tools/list; bridge logs 'bridge listening on ws://127.0.0.1:<port>' on startup
- Model tokens used
- 77,650
- Exact commit tested
- 315e0d89e035
- 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.
Good - token files have `0600` permissions as documented. Now let me compile the report. Here's my complete report: **Error encountered:** The existing Node.js in the container is v18.19.1, but the project requires … **What was done:** 1. Downloaded `node-v24.0.0-linux-x64` from `nodejs.org` to `/tmp/node24/node-v24.0.0-linux-x64/bin… 2. Ran `npm install` with Node 24 — added 95 packages successfully 3. Ran `npm test` — **all 175 tests pass** (0 fail, 0 skip) 4. Started the bridge with `ENDO_PORT=8789 npm start` — it binds on `ws://127.0.0.1:8789` and creat… 5. Verified the MCP endpoint responds correctly: `tools/list` returns **14 browser tools** (`snapsh… 6. Verified token-gating works: `tabs` call correctly returns `"error: no side panel connected"` be… **Install notes:** The bridge runs TypeScript directly with Node 24's type stripping (no build step… Note: I kept `minutes` in integer form for the error - it was actually 1.5 minutes to download/extr…
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 2.5 minutes, faster than the median of the 69 comparable projects Argusic has measured.
- 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 Apache-2.0, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 70 ai-agent projects Argusic has installed and timed, Endoplexity was the 19th fastest to reach a running state, and 42 of 70 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 2.5 minutes after the clone.
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)
ai-agentbrowser-automationcdpchrome-extensionclaudecursormcp
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/endoplexity)Questions
- Does Endoplexity run?
- Yes. Endoplexity runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test Endoplexity?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 315e0d89e035. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Endoplexity?
- 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 Endoplexity take to install?
- 2.5 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 Endoplexity need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Endoplexity?
- 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.
- How does Endoplexity compare with the alternatives?
- Of the 70 ai-agent projects Argusic has installed and timed, Endoplexity was the 19th fastest to reach a running state, and 42 of 70 reached one at all.
- Where is the evidence for Endoplexity?
- 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.