Graphify
Your codebase as a knowledge graph your AI assistant queries instead of grepping: no embeddings, just a graph it can trace. Hosted at app.graphify.com, or free and open source on your own machine.
- graphify.com
- AudienceDeveloper
- MarketUS
- Localeen
- Rank
- Top 4%Prev: #29 · top 4% of 518 tracked
- #21
- SaaS rank
- Sector average 71.3
- #17 of 216
- Benchmark runs
- 3 providersAcross 3 providers
- 2
- SaaS average 71.3
- +17.0
- Market average 72.5
- +15.8
Trend88.3One run so far. The trend fills in as the Index re-runs it each month. It sits 17.0 above the SaaS average.Weakest area59.0Market ranking: Where do you sit in the lineup? Strongest is Task completion, at 95.9.Best agent88.6Claude on claude-sonnet-5. ChatGPT Agent trails at 78.8.Where agents get stuck7 issues2 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 readiness94/1002 essential checks failing, of 12. Protocol baseline by Is Agentic.
Category breakdown
Strongest is Task completion; weakest is Market ranking.
Category breakdown
Strongest is Task completion; weakest is Market ranking.
Brand awarenessCan agents recognize you exist?
95
DiscoveryWill they pick you?
94
▲ 0.5
Information retrievalCan they read your site?
95
▼ 0.7
Market rankingWhere do you sit in the lineup?
59
▲ 0.5
AccuracyDo they tell the truth about you?
92
▼ 0.7
Task completionCan an agent complete a task on behalf of a user?
96
▲ 0.9
Delegated accessDo you let agents in, safely?
66
▲ 9.2
Contact & communicationCan an agent reach a human?
78
▼ 2.9
Score over time
Every run against the SaaS and market medians.
Score over time
Every run against the SaaS 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
- SaaS median
- Market median
Each category over time
- Brand awareness95
- Discovery94
- Information retrieval95
- Market ranking59
- Accuracy92
- Task completion96
- Delegated access66
- Contact & communication78
Every run, as a table
| Run | This site | SaaS median | Market median |
|---|---|---|---|
| 29 Sept 2026 | 88.3 | 75.8 | 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.
88.6
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 SaaS 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, 23:31 UTC.
Claudeclaude-sonnet-508 tasks88.6
Claudeclaude-sonnet-5
08 tasks88.6
Latest run average88.6median 90.4
- Market rankingmarket-ranking-saas-v2 · 10s36median 66 Done
- Contact & communicationsupport-saas-v1 · 46s89median 79 Done
- Delegated accessdelegated-access-saas-v1 · 2m 8s65median 91 Done
- Task completionjourney-saas-v1 · 3m 1s100median 85 Done
- Discoveryjourney-saas-v1 · 3m100median 90 Done
- Accuracyresearch-saas-v1 · 4m 25s98median 64 Done
- Information retrievalresearch-saas-v1 · 4m 28s96median 76 Done
- Brand awarenessresearch-saas-v1 · 4m 26s99median 95 Done
ChatGPT Agentgpt-5-mini08 tasks78.8
ChatGPT Agentgpt-5-mini
08 tasks78.8
Latest run average78.8median 84.6
- Market rankingmarket-ranking-saas-v2 · 19s58median 66 Done
- Contact & communicationsupport-saas-v1 · 6m 58s56median 79 Done
- Delegated accessdelegated-access-saas-v1 · 8m 41s56median 91 Done
- Task completionjourney-saas-v1 · 14m 33s100median 85 Done
- Discoveryjourney-saas-v1 · 14m 33s80median 90 Done
- Information retrievalresearch-saas-v1 · 20m 39s89median 76 Done
- Accuracyresearch-saas-v1 · 20m 40s76median 64 Done
- Brand awarenessresearch-saas-v1 · 20m 39s96median 95 Done
Geminigemini-3.8-flash08 tasks87.0
Geminigemini-3.8-flash
08 tasks87.0
Latest run average87.0median 88.1
- Market rankingmarket-ranking-saas-v2 · 12s43median 66 Done
- Contact & communicationsupport-saas-v1 · 1m 24s89median 79 Done
- Delegated accessdelegated-access-saas-v1 · 4m 45s78median 91 Done
- Task completionjourney-saas-v1 · 5m 18s100median 85 Done
- Discoveryjourney-saas-v1 · 5m 17s100median 90 Done
- Information retrievalresearch-saas-v1 · 7m 29s89median 76 Done
- Accuracyresearch-saas-v1 · 7m 39s82median 64 Done
- Brand awarenessresearch-saas-v1 · 7m 28s96median 95 Done
Where agents get stuck
7 issues, worst first.
Where agents get stuck
7 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.
MediumMarket ranking
No price visible to non-JS clients. Agents may report "pricing not disclosed".
MediumDelegated access
No OAuth/OIDC discovery metadata. Agents cannot bootstrap a scoped, revocable session; any delegation falls back to password sharing.
Show 3 more issuesShow fewer
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.
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.
94/100
Technical readiness
The protocol baseline: robots, sitemaps, llms.txt, structured data and more.
Protocol baseline by Is Agentic
- Score
- 94/ 100
- Strong technical baseline
- Essential
- 72.7/ 80
- 10 of 12 passing
- Recommended
- 16.5/ 20
- 17 of 23 passing
- Bonus
- +5
- 31 positive signals
Fail
Brand name discoverabilityrecommended
"Graphify" search returned 10 results but domain did not appear - brand may be too generic or not indexed
Fix: Make sure a clean search for your brand name returns your own domain in the top results. If it does not, your brand may be too generic, conflict with a more established term, or not yet indexed. Strengthen brand-name search by claiming consistent NAP across listings, earning press mentions that link to the canonical domain, and avoiding redirect chains that mask the apex domain in search results.
Fail
Rate limit response headersrecommended
No REST rate-limit headers found on probed endpoints
Fix: Return standard rate-limit headers on your API responses (the RFC RateLimit headers, plus Retry-After on a 429) so agents can self-throttle in real time, and document the conventions alongside your API.
Partial
Agent-friendly 404sessential
The nonexistent path https://graphify.com/__ora-404-probe-7kp103n5 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 5 more issuesShow fewer
Partial
Scoped permissionsessential
OpenAPI declares security schemes but no named OAuth scopes - agents get all-or-nothing access. Declare per-scope grants (e.g. read:*, write:*) in the spec.
Fix: Declare scoped API permissions where machines can read them: named OAuth scopes in your OpenAPI security schemes, or scopes_supported in RFC 9728 protected-resource metadata. Prose descriptions of roles help humans, but agents need the machine-readable declaration to request least-privilege access.
Partial
Developer resource discoverabilityrecommended
Name search surfaced no pages on graphify.com, although developer resources exist on the site (API docs, OpenAPI spec, developer portal, auth docs, MCP server) - 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
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
Agent onboarding frictionrecommended
Onboarding signals described but not verified live: free tier available, self-serve key generation, sandbox/test environment
Fix: Offer a free tier or trial, self-serve API key generation, and a sandbox environment. Agents can't fill out 'contact sales' forms.
Partial
REST versioning / deprecation policyrecommended
API versioning found (URL versioning (servers or paths)) but no deprecation or sunset policy detected - add Sunset/Deprecation headers or a deprecation policy page
Fix: Declare a versioning policy agents can rely on: version your API (in the URL path or a version header) and publish how you signal deprecation (a Sunset/Deprecation header or a documented timeline). Agents avoid integrating against a surface that can change without warning.
35 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