AI Architect bronze
www.ai-architect.tools
“Zetetic AI — verification-first, open-source MCP servers and Claude Code plugins. Cortex (persistent memory, distributed as hypermnesia-mcp, 97.8% LongMemEval-S Recall@10, measured on v4.20.0), AI Architect Codebase (Rust codebase intelligence, 26 MCP tools), and AI Architect Spec (PRD verification). Every output is traceable; every claim is checked by deterministic algorithms — not LLM-judges-LLM.
https://www.ai-architect.tools/.well-known/agent-card.json its cardwe checked this the operator says this
Verified by agenttru.st
Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.
- Certificate
-
Issued by Google Trust Services
domain-validated
Valid until 7 Nov 2026.Control of the hostname was checked; nothing about who operates it.
- DANE / TLSA
- Not verified (TLSA query returned RCodeNameError)
- Discovery
- Well-known document
- AI use policy
-
What this site's
robots.txtsays about how AI may use its content. Recorded as the operator wrote it, not enforced — these are preferences about use, not access, and agenttru.st only reads the agent's own discovery documents. - AI-facing documents
-
Publishes
/llms.txt— “AI Architect — Persistent Memory, Context Tooling & Codebase Intelligence” a curated map of the site's content for language modelsFetched from this host during verification. Neither document is how this agent was discovered. - First seen
- 19 Sep 2026
View verification details
- Assurance
- bronze Bronze — agent card fetched over HTTPS with a valid certificate
- Protocols
- A2A verified by handshake or card fetch, not merely advertised
- Hosted in
- 🇺🇸 US · Fastly, Inc. (AS54113)
- Last checked
- 3d ago
What this agent says it can do
Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of www.ai-architect.tools controls every word below.
cortex/recall
Search and retrieve memories from Cortex persistent memory using intent-adaptive WRRF fusion (vector + FTS + trigram + heat + recency) with FlashRank reranking. 97.8% Recall@10 on LongMemEval-S (v4.20.0, 2026-09-09).
cortex/remember
Store decisions, patterns, errors, and lessons through a hierarchical predictive-coding write gate. Only stores what violates the model's expectations (predictive coding, Friston 2005).
cortex/consolidate
Run memory maintenance — decay old memories, compress stale content, consolidate episodic to semantic (CLS), run sleep-like replay.
cortex/visualize
Launch the hypermnesia-mcp-viz (Cortex Viz, formerly cortex-viz) unified neural workflow graph showing projects, files, AST symbols (10 languages), memories, and entities with typed call/import edges.
cortex/setup-project
Bootstrap Cortex for a new project: PostgreSQL + pgvector, schema, embedding model, cognitive profile, codebase seeding, hook registration.
pipeline/analyze_codebase
Index + resolve + cluster + build hybrid search index for a codebase in any of 11 languages in one call. Returns property graph with nodes, edges, communities, processes.
pipeline/validate_prd_against_graph
Validates a PRD against the actual codebase graph. Catches symbol hallucinations, scope mismatches, and false 'doesn't affect main' claims.
pipeline/verify_semantic_diff
Compares before/after graphs of a code change. Detects new cycles via Tarjan SCC, dangling edges, disappeared symbols. Returns regression score with verdict.
Technical agent card
Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.
- Protocol
- a2a
- Version
- 1.0.0
- Card completeness
-
a2a.proto v1.0 requires eight top-level fields. This card omits:
Missing fields do not affect listing — they describe how much the operator has published, not whether the agent was verified.
View all card details
- Capabilities
- extendedAgentCard pushNotifications streaming
- Agent card
- https://www.ai-architect.tools/.well-known/agent-card.json
Operate this agent and would rather not be listed? Request removal.