Maintainer of this skill?
Automated security scan — not a certification.
by Anil-matcha
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.
# Add to your Claude Code skills
git clone https://github.com/Anil-matcha/awesome-agent-apisGuides for using ai agents skills like awesome-agent-apis.
Last scanned: 9/3/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-03T08:33:59.472Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how awesome-agent-apis compares with popular alternatives.
awesome-agent-apis is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Anil-matcha. 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. It has 1,057 GitHub stars.
Yes. awesome-agent-apis passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/Anil-matcha/awesome-agent-apis" and add it to your Claude Code skills directory (see the Installation section above).
awesome-agent-apis is primarily written in Python. It is open-source under Anil-matcha on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh awesome-agent-apis against similar tools.
No comments yet. Be the first to share your thoughts!
30 days in the Featured rail · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
A catalog of API tools an agent can call — 660+ generative-media models available through muapi out of the box, plus a growing set of third-party tools (SEO, enrichment, social, scraping, and more) that anyone can add with a single PR.
This is a reference catalog, not a live proxy. Every entry is documentation —
what a tool does, what it costs, how to call it — not something this repo calls
for you. models/ entries run through your own muapi key; providers/ entries
run through the contributor's own account with that provider.
Agents: read llms.txt — one fetch teaches you how to browse and
use this whole catalog, no install or auth required.
The tools worth calling from an agent are scattered across dozens of vendors, each with its own docs, auth quirks, and pricing page — and most of the useful ones sit behind a subscription nobody buys for a single call (Semrush $139/mo, Moz $99/mo, Crunchbase $99/mo), or behind docs vague enough that you don't know what a call actually costs or returns until you've already signed up. This catalog puts the facts that matter — auth shape, real pricing, a captured example response — in one consistent shape, so an agent (or a person) can scan it and know exactly what a tool needs before ever opening its docs.
models/*.yaml |
providers/*.yaml |
|
|---|---|---|
| What it is | One of muapi's own hosted generative-media models | A third-party API a contributor already uses |
| Called with | Your muapi API key | The contributor's/your own key for that provider |
| Who adds it | Auto-synced from muapi's live catalog | Anyone, via PR |
| Editable by PR? | No — see "muapi-hosted models" below | Yes — this is the open contribution path |
ls providers/ models/ # browse what's catalogued
cat capabilities.yaml # browse by category instead — media.*, seo.*, people.*, ...
cat providers/<provider>.yaml # base_url, auth, endpoints, pricing for a third-party tool
cat models/<model>.yaml # what a muapi-hosted model does, its cost, its docs page
providers/_TEMPLATE.yaml to providers/<your-provider>.yaml.CONTRIBUTING.md for the
full checklist, including the one non-negotiable step: get a real key and
confirm at least one endpoint actually works before opening the PR. A schema
that was never called against the real API is not accepted.python3 scripts/catalog_validate.py providers/<your-provider>.yaml
status to verified.See CONTRIBUTING.md for the full guide, including selection
heuristics (what gets accepted vs. rejected) and common gotchas per auth style.
models/)These entries are generated directly from muapi's own live catalog — not hand-written,
and not open to arbitrary edits, since they describe what muapi itself already runs.
Each one deliberately omits how muapi actually serves the model (no base_url, no
auth details, no vendor name) — only the model itself, its cost, and a link to its
docs page. Missing a model, or see one that's wrong? Open an issue rather than a PR;
the catalog is refreshed from the source of truth periodically.
draft (providers only) — submitted, not yet independently verified by a maintainer.verified (providers only) — a maintainer confirmed the entry against a real key
and a real call; examples/<id>.json holds a real captured response.live (models only) — currently available through muapi.Treat draft entries as a starting point, not a guarantee — verify before relying
on one yourself.
MIT — see LICENSE.