<!-- Full-page Markdown export (rendered HTML → GFM). Source: https://neotoma.io/ru/inspector/agents Generated: 2026-04-27T12:48:38.916Z --> # Inspector, Agents, attribution & grants Every write to Neotoma, observation, relationship, timeline event, source, interpretation, is attributed per row. Inspector exposes that attribution as a first-class concept so operators can answer questions like "which agents have written here?", "what tier did they sign in?", and "what is each agent permitted to do?". This is the surface for [AAuth](/aauth) in the Inspector UI. ## Agents list The agents view (`/agents`) lists every distinct writer Neotoma has seen, derived from AAuth thumbprints, JWT subjects, and `clientInfo.name` fallbacks. Each row shows the resolved **trust tier** (`hardware`, `software`, `unverified_client`, `anonymous`), write counts, last-seen timestamp, and the active grant (if any). inspector.neotoma.io/agents Inspector Neotoma Dashboard Conversations Turns Compliance Activity Feedback Entities Observations Sources Relationships Graph Explorer Schemas Timeline Interpretations Agents Agent grants Settings Agents 14 active identities · 8.2k writes · last 30d hardware (3)software (8)unverified (2)anonymous (1) | Agent | Tier | Alg | Writes | Last seen | Grant | | --- | --- | --- | --- | --- | --- | | claude-codeed25519:Aa…7Lk | software | EdDSA | 4,120 | 12:41 | default-write | | cursor-agentes256:Bp…4Zq | hardware | ES256 | 2,810 | 12:30 | default-write | | ingest-pipelineed25519:Cq…9Rt | software | EdDSA | 980 | 11:08 | import-only | | operator (mac · SE)es256:Dr…2Yj | hardware | ES256 | 412 | 10:55 | admin | | custom-script@myco- | unverified\_client | \- | 18 | Apr 24 | (none) | | anonymous- | anonymous | \- | 4 | Apr 22 | (none) | One row per distinct agent identity. Tier badges (hw / sw / unverified / anon) reflect the AAuth verification result. ◆ ## Agent detail Drill into an agent to see its public-key thumbprint, signing algorithm, JWT issuer/subject, capability grants, and a panel of recent writes scoped to that identity. The detail view is where operators decide whether to upgrade a tier (e.g. require hardware for write access) or revoke a key. inspector.neotoma.io/agents/claude-code Inspector Neotoma Dashboard Conversations Turns Compliance Activity Feedback Entities Observations Sources Relationships Graph Explorer Schemas Timeline Interpretations Agents Agent grants Settings claude-code EdDSA · software · 4,120 writes · last 30d softwareattestation: none Observations 3,402 last 30d Relationships 612 last 30d Sources 106 last 30d Identity thumbprint ed25519:Aa…7Lk iss=https://anthropic.com sub=agent:claude-code clientInfo.name="claude-code" v=2.4.1 Active grant default-write scope: store, retrieve, link · entity\_types: any · expires: 2026-07-31 Per-agent identity card with thumbprint, alg, attestation, grants, and a recent-writes activity panel. ◆ ## Grants Capability grants are typed entities that bind an agent identity to a scoped set of actions (e.g. `store`, `retrieve`, `link`, `correct`, `merge`) on a set of entity types, optionally with an expiration. Inspector renders them as first-class records with a history (granted, modified, revoked) and a reverse map back to the agents they bind. inspector.neotoma.io/grants Inspector Neotoma Dashboard Conversations Turns Compliance Activity Feedback Entities Observations Sources Relationships Graph Explorer Schemas Timeline Interpretations Agents Agent grants Settings Grants 6 active · 2 expired \+ New grant | Name | Scope | Types | Agents | Expires | | --- | --- | --- | --- | --- | | default-write | store, retrieve, link | any | claude-code, cursor-agent | 2026-07-31 | | import-only | store, link | transaction, receipt, file\_asset | ingest-pipeline | \- | | admin | all | any | operator (mac · SE) | \- | | read-only | retrieve | any | dashboard-bot | \- | Capability grants: scope, allowed entity types, expiry, and the agents bound to each grant. ◆ ## Trust tiers - hardware ES256 / EdDSA backed by a hardware key (Secure Enclave, TPM 2.0, YubiKey, Windows TBS). Highest trust, eligible for the strictest grants. - software Verified AAuth signature with a software-backed key. Trustworthy for most writes but not eligible for hardware-only grants. - unverified\_client No AAuth signature, but a meaningful `clientInfo.name`. Useful for triage; subject to stricter ACLs in future releases. - anonymous No signature, no usable client identity (or one of the blacklisted generic strings like `mcp`, `client`). Allowed for backwards compatibility but flagged in audit views. ◆ ## Activity Each agent detail page exposes a recent-activity stream, the same rows you'd see in the [timeline](/inspector/timeline), scoped to that one identity. Filters narrow by event kind, target entity type, or trust tier so you can answer "what did this agent write yesterday?" without leaving the page. inspector.neotoma.io/agents/claude-code/activity Inspector Neotoma Dashboard Conversations Turns Compliance Activity Feedback Entities Observations Sources Relationships Graph Explorer Schemas Timeline Interpretations Agents Agent grants Settings claude-code · activity last 24h · 218 writes store (162)correct (12)link (44) 12:41storetransaction · Subscription · Vercelsw 12:30storeagent\_message · turn 4 (assistant)sw 12:30linkPART\_OF · turn 4 → conversation Q2sw 11:08storereceipt · vercel-2026-04sw 11:08linkEMBEDS · receipt → file\_asset (pdf)sw Activity feed scoped to a single agent identity, with the same kind / type / tier filters as the global timeline.