Graphify
Graphify builds queryable, multi-modal knowledge graphs from code, docs, papers and diagrams to supercharge AI coding assistants.
- graphify.net
- AudienceDeveloper
- MarketsCN, TW, US
- Localesen, zh-CN, pt, es, ja, ko, ru, th
- Rank
- Top 51%Prev: #0 · top 51% of 518 tracked
- #266
- Developer tools rank
- Sector average 71.5
- #8 of 14
- Benchmark runs
- 3 providersAcross 3 providers
- 1
- Developer tools average 71.5
- +4.0
- Market average 72.5
- +3.0
Trend75.5One run so far. The trend fills in as the Index re-runs it each month. It sits 4.0 above the Developer tools average.Weakest area56.4Market ranking: Where do you sit in the lineup? Strongest is Brand awareness, at 91.4.Best agent88.1Claude. ChatGPT Agent trails at 46.2.Where agents get stuck9 issues3 high severity. Worst: No discoverable MCP server. ChatGPT apps and Claude connectors have no scoped way to call your product; agents must drive a browser instead.Technical readiness64/1004 essential checks failing, of 7. Protocol baseline by Is Agentic.
Opportunity cost · developer tools
Graphify could see ~$1,249,500 of new ARR exposed to agent-led journeys each year
Public agent-traffic forecasts suggest a growing share, modeled here at roughly 34%, of docs lookup, install and API key setup sessions in the developer tools sector could be initiated or completed by AI agents[1][2]. Graphify currently scores 75.5 on the Index[3], leaving a 25-point gap to the ideal agent experience (100). The illustrative figure below applies that gap to the agent-driven slice of a typical annual recurring revenue baseline for this sector. It is a directional estimate, not a measured conversion rate.
- Gap to leader
- 24.5 pts
- Above developer tools avg
- 0.0 pts
- Modeled new ARR at risk
- $1,249,500
Estimate assumes a $15M ARR baseline with agent-sourced adoption. Claim your domain to replace this placeholder with your reported new ARR.
Category breakdown
Strongest is Brand awareness; weakest is Market ranking.
Category breakdown
Strongest is Brand awareness; weakest is Market ranking.
Brand awarenessCan agents recognize you exist?
91
▼ 8.6
DiscoveryWill they pick you?
72
▼ 16.0
Information retrievalCan they read your site?
83
▼ 12.3
Market rankingWhere do you sit in the lineup?
56
▼ 16.8
AccuracyDo they tell the truth about you?
80
▼ 15.9
Task completionCan an agent complete a task on behalf of a user?
76
▼ 11.5
Delegated accessDo you let agents in, safely?
65
▲ 29.8
Contact & communicationCan an agent reach a human?
59
▲ 33.2
Score over time
Every run against the Developer tools and market medians.
Score over time
Every run against the Developer tools and market medians.
One run so far, on 29 Sept 2026. The line fills in as the Index re-runs it each month.
- This site
- Developer tools median
- Market median
Each category over time
- Brand awareness91
- Discovery72
- Information retrieval83
- Market ranking56
- Accuracy80
- Task completion76
- Delegated access65
- Contact & communication59
Every run, as a table
| Run | This site | Developer tools median | Market median |
|---|---|---|---|
| 29 Sept 2026 | 75.5 | 75.5 | 76.3 |
Medians are by month: each domain counts once, at its newest run that month. Dates are UTC. Latest run 29 Sept 2026.
Agents
Claude does best. Each provider's model and every session behind its score.
88.1
Agents
Claude does best. Each provider's model and every session behind its score.
How these are scored
The score beside each provider is its session quality over a rolling 30 days, from at least 10 sessions per provider.
Scores run 0 to 100. Each is one agent on one task, graded against that task’s fixed rubric, so no agent marks its own work. The median under a score is the sector median: the middle score for the same category, or the same provider, across the other Developer tools sites the Index has sent agents to.
- Excellent85+
- Good72-84
- OK58-71
- Poor40-57
- Critical<40
Latest run 29 Sept 2026 (UTC). Anyone signed in can re-run it from 30 Sept 2026, 18:55 UTC.
ClaudeAnthropic08 tasks88.1
ClaudeAnthropic
08 tasks88.1
Latest run average88.1median 100.0
- Market rankingmarket-ranking-devtools-v2 · 10s43median 58 Done
- Contact & communicationsupport-devtools-v1 · 1m 7s99median 74 Done
- Delegated accessdelegated-access-devtools-v1 · 2m 34s78median 91 Done
- Discoveryjourney-devtools-v1 · 3m 36s70median 76 Done
- Task completionjourney-devtools-v1 · 3m 32s100median 89 Done
- Information retrievalresearch-devtools-v1 · 5m 27s98median 74 Done
- Brand awarenessresearch-devtools-v1 · 5m 26s98median 92 Done
- Accuracyresearch-devtools-v1 · 5m 26s98median 73 Done
ChatGPT AgentOpenAI06 tasks46.2
ChatGPT AgentOpenAI
06 tasks46.2
Latest run average46.2median 100.0
- Market rankingmarket-ranking-devtools-v2 · 14s43median 58 Done
- Contact & communicationsupport-devtools-v1 · 11m 56s49median 74 Done
- Task completionjourney-devtools-v1 · 20m 21s43median 89 Done
- Accuracyresearch-devtools-v1 · 21m 45s43median 73 Done
- Information retrievalresearch-devtools-v1 · 21m 46s26median 74 Done
- Brand awarenessresearch-devtools-v1 · 21m 47s65median 92 Done
GeminiGoogle06 tasks53.3
GeminiGoogle
06 tasks53.3
Latest run average53.3median 100.0
- Market rankingmarket-ranking-devtools-v2 · 10s36median 58 Done
- Contact & communicationsupport-devtools-v1 · 2m 23s56median 74 Done
- Task completionjourney-devtools-v1 · 6m 37s36median 89 Done
- Discoveryjourney-devtools-v1 · 6m 38s43median 76 Done
- Accuracyresearch-devtools-v1 · 8m 45s36median 73 Done
- Brand awarenessresearch-devtools-v1 · 8m 46s88median 92 Done
Where agents get stuck
9 issues, worst first.
Where agents get stuck
9 issues, worst first.
HighDelegated access
No discoverable MCP server. ChatGPT apps and Claude connectors have no scoped way to call your product; agents must drive a browser instead.
HighDelegated access
No public API docs detected. Agents have no scoped way in; they must drive a browser.
HighContact & communication
No contact page linked or reachable. Agents acting on a user’s behalf have nowhere to send a message.
MediumMarket ranking
No price visible to non-JS clients. Agents may report "pricing not disclosed".
Show 5 more issuesShow fewer
MediumDelegated access
No OAuth/OIDC discovery metadata. Agents cannot bootstrap a scoped, revocable session; any delegation falls back to password sharing.
MediumContact & communication
No contact email visible in server-rendered HTML. Agents can’t fall back to email.
LowMarket ranking
No review or aggregateRating schema. Agents have no signal for ranking vs peers.
LowTask completion
No detectable agentic-commerce rail (Stripe SPT, Shopify/UCP, PayPal ACP). Agent-initiated payment needs custom work.
LowContact & communication
No help, support, or FAQ hub linked. Agents can’t self-serve an answer before reaching out.
Want to find these in your own flows before an agent does? Read how to test your product for AI agent users.
Technical readiness
The protocol baseline: robots, sitemaps, llms.txt, structured data and more.
64/100
Technical readiness
The protocol baseline: robots, sitemaps, llms.txt, structured data and more.
Protocol baseline by Is Agentic
- Score
- 64/ 100
- Important blockers remain
- Essential
- 45.7/ 80
- 3 of 7 passing
- Recommended
- 15.3/ 20
- 6 of 11 passing
- Bonus
- +3.1
- 14 positive signals
Fail
Agent crawler reachabilityessential
Some AI crawlers are blocked - ChatGPT-User: reachable, ClaudeBot: blocked, Google-Extended: reachable, ora-agent: reachable, DeepSeekBot: reachable
Fix: Verify that major agent User-Agents can reach the homepage. If your WAF or bot rules block them, remove or narrow the blocking rule. Add an allow rule only when your security setup denies them by default.
Fail
Markdown content negotiation (acceptmarkdown.com)essential
Homepage https://graphify.net does not meet the Markdown negotiation requirements: Accept: text/markdown returned text/html; Vary header missing Accept (got "accept-encoding")
Fix: Enable Markdown negotiation on the scanned homepage. Supporting it only on /docs or a separate .md URL does not satisfy this check. Requests with Accept: text/markdown must receive a nonempty Markdown body with Content-Type: text/markdown and Vary: Accept. Keep serving HTML for Accept: text/html. Adding Vary alone does not create a Markdown response. Verify both with `curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/` and `curl -sS -L -i -H 'Accept: text/html' https://yourdomain.com/`. Check the final response headers and body: Markdown with Vary: Accept for the first request, HTML for the second.
Partial
Agent-friendly 404sessential
The nonexistent path https://graphify.net/__ora-404-probe-ayjln6i0 correctly returns HTTP 404. Partial credit: no Markdown error body was detected.
Fix: Keep the correct HTTP 404 status. The remaining requirement is a Markdown error body when agents request Accept: text/markdown. Include at least 20 characters explaining the error and a link to your docs, sitemap, or llms.txt. Verify with `curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/some-path-that-does-not-exist`. Check both the final 404 status and the Markdown body with Content-Type: text/markdown. Checking the status alone does not verify the missing requirement.
Show 6 more issuesShow fewer
Partial
Not blocked by bot detectionessential
Some agents blocked: GPTBot, ClaudeBot
Fix: Allowlist known AI agent User-Agents (ChatGPT-User, ClaudeBot, Google-Extended, DeepSeekBot) in your WAF or bot-detection rules.
Partial
Developer resource discoverabilityrecommended
Name search surfaced no pages on graphify.net, although developer resources exist on the site (MCP server, SDK documentation) - weak search indexing or transient search noise
Fix: Check whether your developer resources (API docs, OpenAPI spec, auth docs, developer portal, MCP server, SDK documentation) surface in name-based searches. If they do not, use predictable URLs, link them in llms.txt, and include your product name in page titles and headings. This result reflects one search sample.
Partial
MCP server / manifestrecommended
MCP mentioned on site but no standard manifest endpoint found
Fix: Build an MCP (Model Context Protocol) server exposing your API as tools. Use Streamable HTTP transport for full score. This lets Claude, ChatGPT, and other AI agents call your product natively.
Partial
Organization schema completenessrecommended
Organization schema found but missing: contactPoint, address
Fix: Add Organization JSON-LD that includes both contactPoint (with email/phone and contactType) and address (PostalAddress). This lets AI verify your business legitimacy and answer contact queries.
Partial
Trust anchor pagesrecommended
Only Privacy page verified - missing: About, Contact
Fix: Publish real /about, /contact, and /privacy pages with at least 500 characters of content each. These are the pages AI agents check to verify your business is legitimate before recommending you.
Partial
JSON-LD structured datarecommended
JSON-LD SoftwareApplication found - missing url on this entity
Fix: Add url to the SoftwareApplication JSON-LD entity for full score.
18 checks · scanned 29 Sept 2026
Embed
Put this score on your site
A live badge for your footer, docs or README. It updates after every run and links back to this report.
Copy as