llms.txt
+200 −5
https://textforagents.com/llms.txt
− connections on Tuesday, October 20, 2026.**− ## Connecting (from October 20, 2026)− **$5 per seat / month** (per operator seat on a shared team store), flat.− **Solo $9/mo per operator** (1 framework integration, verdict API + ledger; first month free, one-time trial) · **Team $29/mo per operator** (multi-framework, journal-completeness audit) · **Per-verdict API $0.005 per verdict** (x402).− **$0.10 per boarding** (pay per boarding, x402) · **Fleet $19/mo** (200 boardings included, capped; further boardings $0.10 each). Pilot-side revenue share 70/30 (pilot/TextForAgents) on paid boardings, as proposed in MEMO-016.+ connections shortly — as soon as final carrier approval lands.**+ ## Connecting (opening shortly)+ **$4.75 per seat / month** (per operator seat on a shared team store), flat.+ **Solo $9/mo per operator** (1 framework integration, verdict API + ledger; first month free, one-time trial) · **Team $25/mo per operator** (multi-framework, journal-completeness audit) · **Per-verdict API $0.005 per verdict** (x402).+ **$0.10 per boarding** (pay per boarding, x402) · **Fleet $19/mo** (200 boardings included, capped; further boardings $0.10 each). Pilot-side revenue share 70/30 (pilot/TextForAgents) on paid boardings.+ ## The capability diet: tool pruning for agents (P8) — TextForAgents LLC+ **$9 per fleet / month flat** — one fleet, all tracked tools, per-task-type manifests, JIT demotion/recovery, exposure accounting.+ Docs/packet summary: capability-diet-tool-pruning — see the product page for the full description, limits, and support (support@textforagents.com).+ ## Span-level replay: fork from the failure (P12) — TextForAgents LLC+ Span forensics + fork-safety verdict over customer-supplied recorded spans: submit one span (or a run's span set) and get a forensic report — canonicalization, env_digest binding, completeness, stub coverage — and a fork-safety verdict (FORK-SAFE-LIVE / FORK-SAFE-STUBBED / FORK-DEGRADED / FORK-UNSAFE) issued before any execution, for $0.01 per span checked. The verdict gates replay: a cleared fork replays one recorded span from a failed agent run and returns an attribution verdict — determinism,+ **Fork-safety check $0.01 per span checked · Tool-span replay $0.02 per replay · Model-decision replay $0.05 per replay** — pay per call (x402), no subscription, **no free tier**. A gate-refused replay settles $0.01, never a replay price.+ Docs/packet summary: span-level-replay-fork-from-failure — see the product page for the full description, limits, and support (support@textforagents.com).+ ## MCP OAuth client-interop conformance: prove real clients can connect (P22) — TextForAgents LLC+ **Solo $9/mo per server** (hourly client x IdP matrix checks, public badge) · **Fleet $29/mo** (up to 10 servers, per-check API for fleet pre-flight) · **Per-check API $0.01 per check** (x402, one full matrix run on demand).+ Docs/packet summary: mcp-oauth-client-interop-conformance — see the product page for the full description, limits, and support (support@textforagents.com).+ ## Compaction-loss audit (P32) — TextForAgents LLC+ A compaction witness for agent harnesses: pin your goal, acceptance criteria, and safety rules verbatim before the harness compacts; after compaction, get a per-span survival verdict (PRESERVED / DEGRADED / LOST, dropped text named), verbatim re-injection of what was lost, or a HALT verdict when a critical span cannot be restored — every event under a signed compaction receipt.+ **Solo $9/mo per operator** (up to 200 events/mo; first audit free, one-time trial) · **Fleet $19/mo per operator** (up to 2,000 events/mo, team receipt archive, HALT policy) · **Per-event API $0.01/event** (x402).+ Docs/packet summary: compaction-loss-audit — see the product page for the full description, limits, and support (support@textforagents.com).+ ## MCP protocol-era negotiation conformance (P33) — TextForAgents LLC+ Prove which MCP protocol era a server actually serves, per client era, continuously: fresh-connection-per-era negotiation over stdio and HTTP, per-era verdicts (EXACT / DOWNGRADED / REJECTED / NO_VERSION / STATEFUL_SINGLETON / NEW_ERA_OK), client pre-flight prediction, and a signed TTL'd verdict document with a drift fingerprint that alerts when a server's negotiated era changes.+ **Solo $9/mo per server** (hourly era probes across all known eras, badge + drift alert; first month free for the first server, one-time trial) · **Fleet $29/mo** (up to 10 servers, client-side pre-flight API) · **Per-check API $0.01/check** (x402).+ Docs/packet summary: mcp-protocol-era-negotiation-conformance — see the product page for the full description, limits, and support (support@textforagents.com).+ ## Context crossmatch (P30) — TextForAgents LLC+ A pre-ingestion compatibility gate for agent context: type any artifact (tool result, memory shard, peer output, document) by the content classes it carries, type the recipient agent in the same vocabulary, and get a crossmatch verdict before anything enters live context — TRANSFUSE, TRANSFUSE-REDUCED (automatic universal-donor, data-only form), or REFUSE — verified by sandboxed trial exposure under a signed, hash-bound antigen profile.+ **Solo $9/mo per operator** (up to 500 checks/mo, antigen typing + reduction; first crossmatch free, one-time trial) · **Fleet $19/mo per operator** (up to 5,000 checks/mo, recipient-policy registry, audit log) · **Per-check API $0.005/check** (x402).+ Docs/packet summary: context-crossmatch-compatibility-typing — see the product page for the full description, limits, and support (support@textforagents.com).+ ## Minimum Equipment List for agents (P31) — TextForAgents LLC+ Dispatch release under known degradation: maintain an MEL for each agent (capability x task class -> GO / GO-WITH-RESTRICTIONS with named compensations / NO-GO, evaluated fail-closed at dispatch), with deferral clocks (CAT1 72h / CAT2 240h / CAT3 2880h) whose expiry escalates restrictions automatically, compensation-gated restricted dispatch, and an Ed25519-signed dispatch release per run an agent can self-query before accepting work.+ **Solo $9/mo per operator** (up to 5 agents MELs, dispatch releases, deferral clocks; first agent's first dispatch release free, one-time trial) · **Fleet $19/mo per operator** (up to 50 agents, task-class matrices, team release archive) · **Per-query API $0.001/query** (x402).+ Docs/packet summary: minimum-equipment-list-dispatch — see the product page for the full description, limits, and support (support@textforagents.com).+ Product: https://textforagents.com/products/minimum-equipment-list-dispatch/+ ## Effect rewind: compensation registry (P35) — TextForAgents LLC+ Manufactured reversibility for agent tool effects: a proxy that registers the compensating inverse + pre-state snapshot before an effect lands (fail-closed, bound to the effect's receipt), a call-time reversibility verdict (FULLY REVERSIBLE UNTIL T / PARTIALLY REVERSIBLE with named residue / IRREVERSIBLE), and dependency-ordered run rewind restoring pre-run state with exact residue accounting. Snapshots live exactly the compensation window, then are purged.+ **Solo $9/mo per operator** (up to 1,000 registered effects/mo, verdict queries included; first 25 registered effects free, one-time trial) · **Fleet $19/mo per operator** (up to 10,000 effects/mo, run-graph rewind, residue reports) · **Per-verdict API $0.005/query** (x402).+ Docs/packet summary: effect-rewind-compensation-registry — see the product page for the full description, limits, and support (support@textforagents.com).+ Product: https://textforagents.com/products/effect-rewind-compensation-registry/+ ## MCP OAuth remediation verification (P83) — TextForAgents LLC+ Prove a fleet's MCP clients stopped leaking OAuth credentials, not just that they upgraded. Three-leg verdict per client (SDK version floor x provider-construction issuer binding x stored-registration issuer binding), proven behaviourally against a hostile test server naming a canary authorization server, dummy credentials only. Storage inspection is metadata-only — the issuer binding key, never credential values. Verdicts: VULNERABLE-VERSION / UNBOUND-PROVIDER / UNBOUND-STORAGE / LEAKS / BOUND + ## Moneyless clearinghouse: barter netting (P36) — TextForAgents LLC
Showing the first 40 of each.