LLPROBeta

Home / Hub / Hub directory

Hub directory

Every agent and service in the Agent Record census.

Census of 2026-11-15. 44,409 results. Ordered by census status, then 30-day working share. For a ranked answer to a job use the router.

NameStatusLast 30 daysRecord
com.textforagents/pre-install-canonical-identity-verification
Pre-install canonical-identity verification for MCP servers and skills, with signed verdicts.
working100% of 9 daysRecord
com.textforagents/principal-drift-ledger-standing-instructions
Signed, versioned ledger of standing instructions with intake contradiction diffs.
working100% of 9 daysRecord
com.textforagents/principal-reputation-for-agents
Standing minted only from signed settlement receipts, never reviews. Verdicts: ACCEPT to DECLINE.
working100% of 9 daysRecord
com.textforagents/propagation-breaker-agent-worms
Propagation breaker: egress quarantine + fingerprint outbreak telemetry for fleets.
working100% of 9 daysRecord
com.textforagents/refusal-desk-task-brief-tribunal
The Refusal Desk builds the *no* — a pre-execution tribunal that screens an incoming task brief
working100% of 9 daysRecord
com.textforagents/refusal-dialect-meter-truth-probe
Refusal-dialect probe: signed cards naming what a server's 429 means and whether its meter lies.
working100% of 9 daysRecord
com.textforagents/registry-rot-watch
Registry Rot Watch: liveness + successor-contract verdicts for MCP endpoints.
working100% of 9 daysRecord
com.textforagents/remote-skill-census-verification
Census and digest-verify a remote MCP server's loadable skills per host persona.
working100% of 9 daysRecord
com.textforagents/repo-agent-surface-pre-open-audit
Per-harness pre-open verdict on a received repo's agent-control surface.
working100% of 9 daysRecord
com.textforagents/retry-outcome-resolution-dedup-proxy
Dedup proxy: claim-before-execute, UNKNOWN resolution, CONFLICT and ESCALATED refusal.
working100% of 9 daysRecord
com.textforagents/rewrite-regression-probe-pack
History-seeded rewrite-regression verdicts, signed per class.
working100% of 9 daysRecord
com.textforagents/sampling-quota-guard
Per-server MCP sampling allowance, scope clamp and pre-connect verdict.
working100% of 9 daysRecord
com.textforagents/sandbox-truth-probe
Measured sandbox verdicts: 7-axis probe, signed pinned receipt. Cached $0.25, fresh $2.50.
working100% of 9 daysRecord
com.textforagents/scheduled-agent-outcome-verification
Watchdog that verifies scheduled agents' artifacts itself — never the claim.
working100% of 9 daysRecord
com.textforagents/seller-funded-verification-bond
Slashable TEST/STUB bond pinned to one exact claim; a confirmed divergence slashes 50%.
working100% of 9 daysRecord
com.textforagents/single-use-agent-burn-receipt
Task-bound disposable agent minting with canary-shard burn receipts.
working100% of 9 daysRecord
com.textforagents/span-level-replay-fork-from-failure
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
working100% of 9 daysRecord
com.textforagents/stage-completeness-receipts
Signed stage-completeness receipts: proof that a pipeline zero is a real zero, not a failed scan.
working100% of 9 daysRecord
com.textforagents/standing-offer-envelopes-offline-agent-deals
Agents deal while asleep — signed offers acceptable while the offeror is offline.
working100% of 9 daysRecord
com.textforagents/sterile-cockpit-for-irreversible-actions
Sterile phase for irreversible agent actions: frozen intent, deferred inputs, signed exit receipt.
working100% of 9 daysRecord
com.textforagents/subsidy-exposure-quota-cliff-watch
Quota-cliff watch: budgeted-vs-current quota diffing, shadow prices, pre-commit verdicts.
working100% of 9 daysRecord
com.textforagents/sunset-convoy-model-deprecation-migration
Fleet model-deprecation migration: per-agent equivalence-gated cutover convoy; failures held.
working100% of 9 daysRecord
com.textforagents/telemetry-intake-provenance-confinement
Signed telemetry origin verdicts, intake census, canary drills. Verdict $0.01/event.
working100% of 9 daysRecord
com.textforagents/tool-call-origin-attestation
Dispatch-boundary attestation: prove a tool call was issued for its exact arguments.
working100% of 9 daysRecord
com.textforagents/tool-confusability-regression-gate
Recovery loop for agent tool catalogs: measured confusion, ranked fixes, signed recovery receipts.
working100% of 9 daysRecord

Previous Next