eko
Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
Runs with mockssource: GitHubhomepageTypeScriptMITcommit c3de315af2c1
TypeScript, MIT licensed. The project labels itself: agent, agentic ai, agentic ai development, agentic framework, agentic workflow, agents, ai agents and browser automation.
eko runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
All 4 packages build successfully. 12 of 14 test suites pass (14 of 16 individual tests) in eko-core with a mock LLM server. Remaining failures: test/llm/utils.test.ts has a pre-existing unhandled rejection for an intentional timeout scenario; test/llm/mcp.test.ts requires an external MCP SSE server on localhost:8083; the eko-nodejs package test requires Node.js 20+ for Playwright.
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 80 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.
- 14 test suites in eko-core all needed API keys (OPENAI, ANTHROPIC, OPENROUTER); 9 failed without them15 minutes
- pnpm build uses `--sequential` flag unsupported by pnpm 12.8.12 minutes
- test/llm/utils.test.ts: call_timeout with 200ms timeout on a 300ms async function rejects with Timeout but the test does not catch the rejected promise (pre-existing bug in the test itself)
- test/llm/mcp.test.ts: requires an external MCP SSE server at http://localhost:8083 (integration test, cannot mock)
- eko-nodejs test/mcp.test.ts: Playwright requires Node.js 20+, container has 18.19.1
- Install time
- 12 minutes
- Cold machine to finish
- 27 minutes
- Errors hit and fixed
- 5 hit, 2 fixed with no human help
- How the result was proved
- cd packages/eko-core && npx jest --no-coverage: 12 pass, 2 fail (14 suites, 16 tests). All 4 packages produce dist/index.cjs and dist/index.esm.js. Running the planner test (test/core/eko.test.ts) successfully parsed mock XML workflow output.
- Model tokens used
- 191,271
- Exact commit tested
- c3de315af2c1
- 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.
succeeded in 8226ms: A worker process has failed to exit gracefully and has been force exited. This is likely caused by … Test Suites: 2 failed, 2 total Tests: 2 failed, 2 total Snapshots: 0 total Time: 2.199 s Ran all test suites matching /test\/llm\/utils.test.ts|test\/llm\/mcp.test.ts/i. [Global Teardown] Mock server closed Now I have all the data. Here's the final report: tokens used 191,271 Now I have all the data. 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
- 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 12 minutes to install, slower than the median of the 56 comparable projects Argusic has measured.
- Hit 5 errors during setup, 3 of which were not solved.
Of the 57 agent projects Argusic has installed and timed, eko was the 34th fastest to reach a running state, and 39 of 57 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 | 80.00 | 0.17 | |
| Argusic Runner | 1/3 | Unverified | 80.00 | 0.04 |
Topics (from GitHub)
agentagentic-aiagentic-ai-developmentagentic-frameworkagentic-workflowagentsai-agentsbrowser-automationbrowserusechain-of-thoughtcomputer-automationcomputerusegenaillm-agentsllm-inferencellmapinatural-language-inferenceprompt-engineeringragworkflow
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/eko)Questions
- Does eko run?
- eko runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test eko?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c3de315af2c1. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test eko?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does eko take to install?
- 12 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 eko need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing eko?
- 5 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does eko compare with the alternatives?
- Of the 57 agent projects Argusic has installed and timed, eko was the 34th fastest to reach a running state, and 39 of 57 reached one at all.
- Where is the evidence for eko?
- 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.