awesome-agent-apis
660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping), one YAML file per entry, browsable by capability.
Runs with mockssource: GitHubhomepagePythonMITcommit bbef5eefd054
Python, MIT licensed. The project labels itself: agent apis, agent tools, agentic ai, ai, ai agent, ai models, api catalog and api directory.
awesome-agent-apis runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.6 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
PyYAML 6.0.3 installed; catalog_validate.py validates all 665 YAML entries in providers/ and models/ successfully with zero errors.
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.
- Install time
- under a minute
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- python3 scripts/catalog_validate.py providers/*.yaml models/*.yaml returned OK on all 665 files (1 provider, 664 models, template skipped) with exit code 0
- Model tokens used
- 206,037
- Exact commit tested
- bbef5eefd054
- 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.
2. Ran `python3 scripts/catalog_validate.py providers/*.yaml models/*.yaml` — **all 665 files passe… 3. Verified the validator correctly catches errors (confirmed with a deliberate bad-status test). **No errors encountered.** No mocks needed. No launchable app exists — the project is a static YAML… tokens used 206,037 Everything is in order. Here's my report: **Summary:** This is a YAML documentation catalog of API tools (660+ models, 2 providers). The only… **What I did:** 1. Installed `pyyaml` (via `pip3 install --user --break-system-packages pyyaml`) 2. Ran `python3 scripts/catalog_validate.py providers/*.yaml models/*.yaml` — **all 665 files passe… 3. Verified the validator correctly catches errors (confirmed with a deliberate bad-status test). **No errors encountered.** No mocks needed. No launchable app exists — the project is a static YAML…
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
- Installed in 0.6 minutes.
- Nothing broke on the way: zero errors between clone and running.
- Licensed MIT, 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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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 | 0.03 |
Topics (from GitHub)
agent-apisagent-toolsagentic-aiaiai-agentai-modelsapi-catalogapi-directoryaudio-generationawesome-listdata-enrichmentgenerative-aigenerative-mediaimage-generationmuapiseo-toolstext-to-imagetext-to-videovideo-generationweb-scraping
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/awesome-agent-apis)Questions
- Does awesome-agent-apis run?
- awesome-agent-apis runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test awesome-agent-apis?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit bbef5eefd054. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test awesome-agent-apis?
- 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 awesome-agent-apis take to install?
- 0.6 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 awesome-agent-apis need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing awesome-agent-apis?
- Nothing did, in the recorded run: zero errors between clone and running.
- Where is the evidence for awesome-agent-apis?
- 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.