open-agent-connector
Open-source, self-hosted alternative to Composio, Nango, Merge.dev, and Arcade.dev for AI agent integrations. Run GitHub, Slack, Hacker News, and custom HTTP actions over MCP or REST.
Runs with mockssource: GitHubPythonApache-2.0commit 41d306722688
Python, Apache-2.0 licensed. The project labels itself: agent tools, ai agents, api gateway, api integrations, arcade dev, composio, connector gateway and fastapi.
open-agent-connector runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Server starts on port 8000, responds to /health with 200, lists 236 providers via /v1/providers, exposes 8,024 actions via /v1/actions, and all 134 in-process pytest tests pass; web console builds with Next.js 16.
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 92 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 18.19.1 incompatible with Next.js 16 (requires >=20.9.0)2 minutes
- Python externally-managed environment blocks pip install1 minute
- Stale node_modules from Node 18 caused zod/vitest type errors in build1 minute
- Standalone test_security_contracts.py fails on action execution (needs real GitHub credentials)
- Install time
- 12 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pytest tests/ exited 0, 134 passed; curl -s localhost:8000/health returned 200; curl -s /v1/providers returned 200 with provider listing; npm run build (Next.js) compiled successfully; 4 warnings (datetime.utcnow() deprecation) are cosmetic
- Model tokens used
- 62,488
- Exact commit tested
- 41d306722688
- 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.
/bin/sh -lc 'pkill -f "uvicorn main:app" 2>/dev/null; echo "cleanup done"' in /work/repo exited 143 in 0ms: Here's the summary of everything I found: exec /bin/sh -lc 'cd /work/repo/server && CONNECTOR_ADMIN_TOKEN=test-admin /work/repo/server/venv/bin/py… succeeded in 51249ms: -- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html 134 passed, 54 warnings in 50.03s Here's the final result summary: tokens used 62,488 Here's the final result summary:
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 Apache-2.0, as reported by its host.
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 3 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 4 agent-tools projects Argusic has installed and timed, open-agent-connector was the 3rd fastest to reach a running state, and 2 of 4 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 | 1/3 | Runs with mocks | 92.00 | 0.12 |
Topics (from GitHub)
agent-toolsai-agentsapi-gatewayapi-integrationsarcade-devcomposioconnector-gatewayfastapigithubintegrationsmcpmerge-devmodel-context-protocolnangopythonrest-apiself-hostedslacksqlitetypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/open-agent-connector)Questions
- Does open-agent-connector run?
- open-agent-connector runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test open-agent-connector?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 41d306722688. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test open-agent-connector?
- 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 open-agent-connector 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 open-agent-connector need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing open-agent-connector?
- 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 open-agent-connector compare with the alternatives?
- Of the 4 agent-tools projects Argusic has installed and timed, open-agent-connector was the 3rd fastest to reach a running state, and 2 of 4 reached one at all.
- Where is the evidence for open-agent-connector?
- 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.