{"id":50854741,"url":"https://github.com/marvinvista/agentic-ready","last_synced_at":"2026-06-14T17:32:20.669Z","repository":{"id":358804927,"uuid":"1243135772","full_name":"marvinvista/agentic-ready","owner":"marvinvista","description":"Audit whether agents can find, call, trust, price, and defend your B2B product.","archived":false,"fork":false,"pushed_at":"2026-05-19T13:01:11.000Z","size":19,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-10T10:30:49.422Z","etag":null,"topics":["agents","ai-agents","b2b","developer-tools","docs","llms-txt","mcp","openapi"],"latest_commit_sha":null,"homepage":"https://fob.dev","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/marvinvista.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-05-19T04:41:58.000Z","updated_at":"2026-05-19T13:01:55.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/marvinvista/agentic-ready","commit_stats":null,"previous_names":["marvinvista/agentic-ready"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/marvinvista/agentic-ready","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marvinvista%2Fagentic-ready","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marvinvista%2Fagentic-ready/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marvinvista%2Fagentic-ready/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marvinvista%2Fagentic-ready/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/marvinvista","download_url":"https://codeload.github.com/marvinvista/agentic-ready/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marvinvista%2Fagentic-ready/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34331808,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-14T02:00:07.365Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","ai-agents","b2b","developer-tools","docs","llms-txt","mcp","openapi"],"created_at":"2026-06-14T17:32:19.930Z","updated_at":"2026-06-14T17:32:20.661Z","avatar_url":"https://github.com/marvinvista.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# agentic-ready\n\nMost B2B products are invisible to agents.\n\n`agentic-ready` is a small CLI that checks whether an agent can discover, evaluate, and use your product from the outside. It looks for the five things that now matter in an automated buying flow: can agents **find** you, **call** you, **trust** your output, **price** the product, and **defend** the choice?\n\n```bash\nagentic-ready https://docs.example.com\n```\n\nIf agents cannot find, call, trust, price, or defend your product, you are invisible in the new buying flow.\n\nBuilt by Marvin Vista. Need hands-on help? [fob.dev](https://fob.dev) helps B2B teams make their products ready for agent-led discovery, evaluation, and implementation.\n\n## Install\n\n```bash\npython3 -m pip install \"git+https://github.com/marvinvista/agentic-ready.git@v0.1.0\"\n```\n\nRun an audit:\n\n```bash\nagentic-ready https://docs.stripe.com\n```\n\nWrite a report:\n\n```bash\nagentic-ready https://developer.zendesk.com --output examples/reports/support-zendesk.md\n```\n\nUse it in CI:\n\n```bash\nagentic-ready ./public --json --fail-under evaluable\n```\n\nFor local development:\n\n```bash\ngit clone https://github.com/marvinvista/agentic-ready.git\ncd agentic-ready\npython3 -m pip install -e .\n```\n\n## What It Checks\n\n| Dimension | Question | Common proof |\n| --- | --- | --- |\n| Find | Can agents find the product surface? | `llms.txt`, sitemap, docs, API reference, `.well-known` manifests |\n| Call | Can agents call it? | OpenAPI, MCP/tool definitions, SDKs, auth docs, sandbox/test mode |\n| Trust | Can agents trust the output? | Schemas, structured examples, errors, versioning, status/security proof |\n| Buy | Can agents evaluate buying friction? | Pricing, usage limits, rate limits, plan boundaries, free/sandbox path |\n| Defend | Can agents defend choosing it? | Proprietary data, system-of-record position, integrations, network effects, trust |\n\n## Real Examples\n\nThese are live public docs audits generated by the CLI:\n\n```bash\nagentic-ready https://docs.github.com --output examples/reports/devtools-github.md\nagentic-ready https://developers.hubspot.com --output examples/reports/crm-hubspot.md\nagentic-ready https://docs.stripe.com --output examples/reports/billing-stripe.md\n```\n\nSee the full report set in [`examples/reports/`](examples/reports/).\n\n## What We Found After Auditing 10 Products\n\nWe ran `agentic-ready` across five B2B categories: devtools, CRM, billing, support, and data APIs.\n\n| Category | Product | Result | Report |\n| --- | --- | --- | --- |\n| Devtools | GitHub Docs | Evaluable, 4/5 | [`devtools-github.md`](examples/reports/devtools-github.md) |\n| Devtools | Supabase Docs | Ready, 5/5 | [`devtools-supabase.md`](examples/reports/devtools-supabase.md) |\n| CRM | HubSpot Developers | Ready, 5/5 | [`crm-hubspot.md`](examples/reports/crm-hubspot.md) |\n| CRM | Salesforce Developers | Evaluable, 4/5 | [`crm-salesforce.md`](examples/reports/crm-salesforce.md) |\n| Billing | Stripe Docs | Ready, 5/5 | [`billing-stripe.md`](examples/reports/billing-stripe.md) |\n| Billing | Chargebee API Docs | Evaluable, 3/5 | [`billing-chargebee.md`](examples/reports/billing-chargebee.md) |\n| Support | Intercom Developers | Evaluable, 3/5 | [`support-intercom.md`](examples/reports/support-intercom.md) |\n| Support | Zendesk Developers | Discoverable, 2/5 | [`support-zendesk.md`](examples/reports/support-zendesk.md) |\n| Data APIs | Databricks Docs | Ready, 5/5 | [`data-databricks.md`](examples/reports/data-databricks.md) |\n| Data APIs | Snowflake Docs | Evaluable, 3/5 | [`data-snowflake.md`](examples/reports/data-snowflake.md) |\n\nThe pattern is clear:\n\n- Strong human docs are common.\n- API and SDK surfaces are increasingly visible.\n- Pricing, rate limits, usage limits, and plan boundaries are still the most common source of agent hesitation.\n- Output-layer proof is usually implied in prose, not exposed as machine-readable evidence.\n- Most products still do not publish an agent-specific manifest such as `agentic-ready.json`, `.well-known/agentic-ready.json`, or `.well-known/mcp.json`.\n\nThe blunt claim:\n\n\u003e Most B2B products are not ready for non-human users. This tool shows why.\n\n## Example Output\n\n```text\nAgentic readiness: Discoverable\nTarget: https://developer.zendesk.com\nScore: 2/5\n\nWhy agents drop you:\n1. No machine-readable API, MCP, SDK, auth, or sandbox path was found.\n2. Buying and usage friction require a human to interpret.\n3. The defensible output layer is not visible.\n\nNext best fix:\nPublish OpenAPI or MCP, auth docs, and a sandbox/test-mode example.\n```\n\n## Levels\n\n| Level | Meaning |\n| --- | --- |\n| `Ready` | Agents can find, evaluate, and call the product with low human fallback. |\n| `Evaluable` | Agents can compare the product, but usage or proof gaps remain. |\n| `Discoverable` | Agents can find the product, but cannot reliably evaluate or use it. |\n| `Not ready` | The product still depends on human browsing, sales, or tacit knowledge. |\n\n## Scope\n\nThis is a smoke test, not a crawler, benchmark suite, or certification. The best use is to run it before shipping docs, pricing, API, MCP, or agent-facing proof changes.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarvinvista%2Fagentic-ready","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmarvinvista%2Fagentic-ready","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarvinvista%2Fagentic-ready/lists"}