OpenAgentCore
The OpenAI Agents API, open source and self-hosted. Run Codex, Claude Code or MiniMax Code on your own machines with your own models, through the official OpenAI SDK.
Runssource: GitHubhomepageGoMITcommit daeb75465fac
Go, MIT licensed. The project labels itself: agent runtime, ai agents, claude code, codex, coding agent, llm, mcp and openai.
OpenAgentCore runs. An Argusic agent installed it in 48 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
OpenAgentCore development environment is fully operational inside this container: Go 1.26.10 compiler, PostgreSQL 16 (localhost:15432), Node.js 24.22.1, and pnpm 10.30.3 are all installed and working. All 5 Core binaries compile and produce executables. All 61 Go service packages pass their tests against a real PostgreSQL database. All 171 Claude SDK adapter tests pass.
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.
- PostgreSQL not installed — all Core database tests would be skipped5 minutes
- Go compiler not found in container2 minutes
- Node.js v18.19.1 in container lacks node:module.registerHooks() needed by Claude SDK adapter test suite2 minutes
- pnpm not installed — needed for web/frontend builds and tests1 minute
- Install time
- 48 minutes
- Cold machine to finish
- 49 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- go test ./services/core/... ./internal/... ./packages/agents-client/... returned 61 ok, 0 FAIL; pnpm --dir packages/claude-sdk-adapter test returned 171 pass, 0 fail; pnpm test:web returned 22 files 744 pass + 70 files 381 pass; mcode harness node --test returned 7 pass 0 fail 4 skip; all 5 Python test suites passed; Core binaries (oac-core, oac-node, oac, oac-core-device, oac-core-environment-key) built and exist at /home/runner/.oac/build/oac-core/
- Model tokens used
- 315,869
- Exact commit tested
- daeb75465fac
- 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.
} exec /bin/sh -lc '# Stop PostgreSQL gracefully export PGBIN="/tmp/pg-extract/usr/lib/postgresql/16/bin" export LD_LIBRARY_PATH="/tmp/pg-extract/usr/lib/x86_64-linux-gnu:/tmp/pg-extract/usr/lib/postgresql… export PGDATA="/tmp/pgdata" $PGBIN/pg_ctl -D $PGDATA stop 2>&1 || true' in /work/repo succeeded in 0ms: waiting for server to shut down.... done server stopped tokens used 315,869
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.
- Recovered from all 4 errors 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.
What did not, or is not known
- Took 48 minutes to install, slower than the median of the 4 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 5 agent-runtime projects Argusic has installed and timed, OpenAgentCore was the 5th fastest to reach a running state, and 3 of 5 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.
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)
agent-runtimeai-agentsclaude-codecodexcoding-agentllmmcpopenaiopenai-agents-apisandboxself-hosted
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openagentcore)Questions
- Does OpenAgentCore run?
- Yes. OpenAgentCore runs. Argusic installed and launched it on a clean machine in 48 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test OpenAgentCore?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit daeb75465fac. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test OpenAgentCore?
- The run that produced this verdict cost $0.54: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does OpenAgentCore take to install?
- 48 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 OpenAgentCore need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing OpenAgentCore?
- 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 OpenAgentCore compare with the alternatives?
- Of the 5 agent-runtime projects Argusic has installed and timed, OpenAgentCore was the 5th fastest to reach a running state, and 3 of 5 reached one at all.
- Where is the evidence for OpenAgentCore?
- 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.