AgentCrush

AgentCrush is the public record of AI agents.

Independent. Cross-protocol. Open methodology. Machine-callable from your code or your agent.

1,358
agents indexed
153
evidence-ranked
17.7% alive
Ghost Index →
33,500
daily snapshots
01
DISCOVER
Index every AI agent…
→
02
VERIFY
Check every claim against…
→
03
SCORE
Rank by evidence, not…
→
04
TRACK
Snapshot every indexed agent…
→
05
EXPOSE
Make the data callable…
→
06
PUBLISH
Ship findings in public.…
▸ What each step means — the full pipeline, in public
01
DISCOVER
Index every AI agent that leaves a public signal.
GitHubnpmPyPIHuggingFacex402ERC-8004VirtualsAgentverseA2AMCP
Protocol-neutral. We read the registries; we don't belong to any of them.
02
VERIFY
Check every claim against its primary source.
GitHub commitsnpm downloadson-chain holdersBazaar endpointsA2A stars
No self-reported data. Every signal has a source URL.
03
SCORE
Rank by evidence, not by who shouted loudest.
v2.c-public (developer)v1.4 (model families)v1.1-tvl (tokenized)v1.1-forks (service)
Four separate methodologies. Each one documented, versioned, and publicly auditable.
04
TRACK
Snapshot every indexed agent daily. Store it forever.
daily snapshotsweekly deltarank historysignal historytrend detection
Other directories show today's list. We show how rankings change over time.
05
EXPOSE
Make the data callable — by humans and by agents.
MCP server (free)x402 REST endpointsOpenAPI 3.1JSON-LD/llms.txt
$0.02 / call on Base. No API key needed. Your agent can pay with USDC.
06
PUBLISH
Ship findings in public. Let anyone cite them.
open methodologyversioned diffscitable blog postsweekly digestRSS
Every methodology change is logged. Every post has a citation block.
What brings you here?
I'm looking for an agent →
Answer 3 questions, get a shortlist of verified, evidence-ranked agents for your use case.
I'm building an agent →
MCP server, x402 REST, OpenAPI 3.1, embed badges, ERC-8004 context — all free to start.
I'm researching the ecosystem →
FOR ANALYSTS
Case studies, methodology findings, weekly digest. Every post has citation blocks + data downloads.
I want to understand the ecosystem →
Agent Economy Index — which protocols are gaining ground, which are stalling.
I'm just exploring →
What are AI agents? What do the protocol layers mean? Start here.
Rankings
4 rankings — equal peers
⇄ Compare →All rankings →
Developer
102 evidence-ranked·v2.c-public
1
OpenClaw Agents
OpenClaw Agents
79
+19
2
CrewAI
CrewAI
74
+24
3
DSPy Agents
DSPy Agents
73
+5
Full ranking →
Model Families
7 evidence-ranked·v1.4
1
A
Alibaba Qwen
83
2
Google Gemini
Google Gemini
80
+3
3
Mistral
Mistral
74
Full ranking →
Tokenized
16 evidence-ranked·v1.1-tvl
1
AIXBT
AIXBT
81
2
Ribbita
Ribbita
73
3
G.A.M.E
G.A.M.E
66
Full ranking →
Service
28 evidence-ranked·v1.1-forks
1
A
A2A
77
2
A
a2a-python
73
3
E
evolver
73
Full ranking →
⇄ COMPAREHead-to-head on every signal — pick two agents, get one URL.
crewai vs autogpt →Open compare →
Live signals
STAR1h ago
magic
+? GitHub stars
STAR1h ago
tabularis
+? GitHub stars
STAR1h ago
sandbox
+? GitHub stars
STAR1h ago
Product-Manager-Skills
+? GitHub stars
DEV1h ago
hatchet
dev activity
STAR1h ago
obscura
+? GitHub stars
STAR1h ago
NeMo-Agent-Toolkit
+? GitHub stars
STAR1h ago
langchain-in-action
+? GitHub stars
Integrate
Call it from your code or your agent
Developer docs →
Free MCP server
13 tools · POST /api/mcp/v1 · no auth · 60 req/min
search_agentsget_agent_detailsget_agent_trustget_agent_historyget_agent_changescompare_agentslist_categoriesget_category_rankingget_top_moversget_protocol_adoptionget_ecosystem_summaryget_methodology
Paid x402 API
USDC on Base · no API key · pay per call
$0.02/api/agent/:handle/trust-summary
$0.02/api/agent/:handle/history
$0.005/api/agent/:handle/verification-status
$0.10/api/trust/evaluate/full
Or skip per-call payments: Pro API $29/mo →
Embed badge
Live SVG · auto-updates · copy into any README
/embed/{handle}
Shows rank, score, and evidence badge. Refreshes on every request.
Field notes
Public record & findings
/weekly →/blog →Farcaster →X →
◆ WEEKLY DIGESTW23 · 2026-06-07
Promotions · Top movers · New to index · Protocol activity · Editorial
Weekly intelligence roundup. Evidence-ranked moves, new entries, protocol signals, and editorial context — every Friday.
Read →
FindingsMay 2026
Three Agent Commerce Readiness Audits
FARCASTER · CAST
View latest casts →
X · POST
View latest posts →
Get your agent indexed →
Free. Evidence-based. No pay-to-rank.
→

Daily snapshots since 2026-04-15 · 33,500 snapshots · updated every 4h · public methodology

© 2026 AgentCrush · The public record of AI agents.

AboutTerms