Connect Codex, Claude Code, OpenCode, OpenClaw, Hermes Agent, Cursor, GitHub Copilot, Google Antigravity, or another compatible harness to power VTX bot inference or perform deep trade-chain analysis.
Start with the machine-readable contract, then use the live capability registry to analyze evidence, operate bots, and verify the result.
Use the connected harness as the live inference engine behind Main, Review, or Screener. VTX supplies the exact prompt, market context, and output contract; the harness returns the model response or structured decision that powers the normal VTX trading loop.
Authentication identifies the VTX account using the connector, but it does not establish whether a supplied profile handle is owned or public. For named-profile work, discover the profiles once, confirm the ownership label for every requested handle or wallet, use the matching exact owned or public selection, and preserve that resolved selection with one evidence cutoff. Then connect effective settings and prompt generations to decisions, reasoning, executions, fills, position campaigns, fees, funding, and realized outcomes. Report unavailable evidence instead of silently narrowing the claim.
Resolve the owned profile, read its current execution mode and runtime state, request bot-control access, and start the normal VTX Trader. Server Mode runs on VTX and uses the normal fee. A Client Mode start records the requested intent but still needs a fresh owner: open that profile on Trade in a browser or desktop app, or run vtx auth login --scopes read,bot:control followed by vtx --profile <profile-id> runtime run --follow for the supported headless path. The bot is not running until current heartbeat and ownership evidence confirm it.
Search the live capability registry instead of guessing tool names. Read each capability's permission and input contract, preview consequential changes, ask for approval, and verify receipts against effective state and observed results. A bot is not running until current runtime evidence confirms it.
Read https://api.vtxmacro.com/insights/access-center/metadata, choose the appropriate bundled skill and live capability, request only the permissions required for my outcome, and explain what you will verify before taking any consequential action.
Codex and Claude Code plugin installs include both skills. OpenCode, OpenClaw, and Hermes Agent can install the same skills separately, and other compatible harnesses can use the VTX capabilities through MCP.
The general VTX router and safety contract. It discovers the right capability, preserves complete evidence, separates permissions, and verifies settings, profile, connection, bot-control, and trading actions.
Use $vtx-insights-analysis to work with VTX safely and choose the right capability.The specialist performance workflow. It reconstructs settings generations, decisions, executions, fills, positions, exits, fees, funding, PnL, and market context before recommending a focused improvement.
Use $vtx-bot-trade-chain-analysis to explain why my bots are winning or losing and recommend the smallest evidence-backed improvements.Choose a compatible harness, install the VTX connector, and approve only the access it needs.
codex plugin marketplace add DataDoesYou/codex plugin add vtx-insights@codex mcp login vtx-insights --scopes insights:read[mcp_servers.vtx-insights] url = "https://api.vtxmacro.com/insights/mcp" tool_timeout_sec = 120
VTX sign-in lets you approve analysis, settings management, bot control, and trading separately.
See which agent apps have VTX OAuth access, what each one may do, and remove access at any time. This list does not prove that a native client initialized, discovered tools, or loaded the installed plugin; verify those in the agent app.
The complete guide is public. Your connections, permissions, profile data, and actions remain private.
Durable means VTX can operate the vendor's official machine interface after this setup chat ends. Foreground harnesses remain useful, but their agent loop must stay open.
The existing pinned App Server path remains the reference implementation, including ChatGPT identity, live model and effort discovery, quota telemetry, cancellation, and exact crash recovery.
VTX uses GitHub's official SDK with the package-owned pinned platform runtime, authenticated GitHub login identity, exact enabled model and effort events, token usage, and cooperative cancellation. Auto-only catalogs fail closed because they cannot prove the effective model. Output text is schema-validated by VTX; uncertain interrupted calls are quarantined.
VTX uses the exact-pinned official DeepSeek Harness runtime in both Provider and Main Agent modes. The key remains in the local VTX private credential boundary, Provider runs have no tools, Agent runs expose only the three assignment-scoped VTX tools, and a loopback receipt verifies the provider-returned model and response ID. VTX validates final JSON; interrupted ambiguous work is never blindly retried.
The pinned Pi SDK supports Provider mode and Main Agent mode through the existing controls. The initially qualified models use one separately stored OpenAI API key per instance and advertise exact provider/model identities from the release's configured qualification policy and SDK catalog. Provider runs have no tools; persistent Agent sessions expose only the three assignment-scoped VTX tools. VTX validates structured output and execution receipts. Uncertain interrupted model calls stop safely; Pi does not claim same-attempt recovery. Subscription OAuth and unqualified provider protocols are not enabled by this adapter.
Exo means exoharness/exo. The VTX-owned bridge runs the pinned Exo custom harness automatically in Provider and Main Agent modes; no manual job transfer is needed. Each instance advertises only the release-qualified routes for its OpenAI or Venice credential. Venice currently offers Gemma 4 31B IT with effort None only. Provider runs receive complete VTX input with no tools; Agent runs expose only assignment-scoped VTX tools. VTX validates canonical JSON; native structured-output enforcement is not claimed. VTX OAuth stays outside Exo. This Linux/WSL foreground preview has no durable service or same-attempt recovery: uncertain interrupted work remains fenced. It does not add native Exo MCP support.
A live 1.1.13 Starter Quota acceptance exposed shell, file, browser, web, MCP, subagent, and messaging tools even under an isolated agent declaring tools: [], and the requested final JSON Schema was not enforced. VTX therefore keeps Antigravity in a monitored foreground loop.
The current official individual OAuth flow rejects this client and directs users to Antigravity. API-key and Vertex routes are API-billed rather than a consumer-subscription subsidy, and the CLI does not enforce a final response schema.
Claude Code has a strong official programmatic contract, but Anthropic currently says third-party developers may not route Free, Pro, or Max credentials on users' behalf without prior approval. VTX therefore keeps it on the user's foreground first-party loop.
Grok Build uses the pinned official runtime and a separate local OAuth session for Provider and Main Agent modes. Provider runs have no tools; Agent runs expose only the three assignment-scoped VTX tools. VTX validates structured output, model identity, and reported usage. Uncertain interrupted requests remain fenced; same-attempt recovery and Codex subscription quota telemetry are not supported.
Kiro API keys legitimately consume paid subscription credits, but its headless chat lacks a stable JSON result, effective-model, token-usage, and cancellation receipt.
Cursor's official SDK has strong lifecycle and usage telemetry, but SDK authentication is API-key and token-billed rather than a clear consumer-subscription subsidy.
Amp offers subscriptions, credits, and linked ChatGPT capacity, but its selectable product is a managed mode rather than a stable underlying model identity.
Auggie exposes account, models, credits, ACP cancellation, and sessions, but its SDK currently declares structured output unsupported and recovery remains incomplete.
Junie has headless JSON, ACP, sessions, and subscription routing, but effort can fall back and its public machine contract does not yet provide the exact effective identity and usage evidence required for a durable VTX worker.
Warp and Oz can consume plan credits and run cloud agents, but they do not expose the exact effort, structured result, token accounting, and direct inference lifecycle required for a durable VTX provider.
Qwen Code has a strong no-tools, JSON Schema, usage, and cancellation contract, but the Coding Plan prohibits automated scripts, application backends, and non-interactive use. Standard ModelStudio API quota is a normal API/BYOK route rather than subscription capacity.
OpenCode can run VTX Provider jobs or claim a true Main Agent assignment while its foreground loop stays open, and it can connect directly to VTX Insights with scoped OAuth and native Agent Skills. The open-source harness has a strong SDK and session contract, but its generic receipts do not prove provider-returned model identity or complete ambient-tool isolation. Its hosted terms also prohibit unattended programmatic output extraction, and upstream vendors do not authorize OpenCode as a durable router for their consumer subscription OAuth credentials.
OpenClaw's published package supports remote OAuth MCP servers, so it can use VTX Insights directly. Durable VTX inference remains disabled because the published runtime does not expose a package-owned terminal receipt with complete effective model, provider-call usage, tool, cancellation, and interruption evidence.
Hermes supports remote OAuth MCP servers, so it can use VTX Insights directly. Its one-shot runner can make unreported auxiliary model calls, undercounts usage, reports requested rather than proven effective identity, can exit successfully after provider failures, and has no structured interruption receipt or clean no-tools mode, so it is not a durable VTX adapter.
Use this path when several existing profiles or durable inference hosts must move to a new computer. A new installation creates new host identities even when the vendor credential is unchanged, so every saved profile lane must be checked and any stale binding must be explicitly previewed and rebound.
The service is per-user login startup, not a pre-login machine service. Nothing runs while the computer is powered off, and workers cannot serve while it is asleep, signed out, or offline. After the user signs in, instances whose desired state is running reconnect automatically. Workers on the same computer share that computer-level failure domain.
Add your exact profile names and account order after copying this prompt.
Read https://vtxmacro.com/insights#subscription-inference and set up or move my exact existing durable inference fleet to this computer. Before changes, list the exact profiles, named instances, adapters, primary and fallback order, model, reasoning, control mode, and execution mode. Use the adapter-specific vendor login or key-import step and one native OS supervisor with isolated workers. DeepSeek Harness is limited to one worker for that adapter per computer until it can advertise a stable provider account identity. Explicitly preview and rebind stale host identities, preserve all unrelated settings, and verify effective readback plus a fresh completed inference from each primary. Do not call routing, a start receipt, or running Trader state proof of inference completion. Explain user-login startup and computer-off behavior before any reboot.
Install, connect, choose a control mode, and verify the host.
Install @vtxmacro/cli from npm, then connect Codex, GitHub Copilot, DeepSeek Harness, or Pi as a durable host. Pi is a preview for supported OpenAI models in Provider and Main Agent modes, using a separate OpenAI API key with API billing; subscription logins are not supported. Antigravity and other compatible harnesses can operate the foreground loop.
Both modes return the same structured trading decision to VTX. The difference is who decides when to run and which data the model needs.
VTX keeps its normal cadence, builds the lane's prompt and context, and asks the connected model for a response. This remains the only mode for Review and Screener.
VTX assigns the running Trader to an explicitly capable Main agent. The agent chooses when to act, requests any assignment-scoped VTX data it needs or none, and submits the same structured trading decision VTX normally consumes.
Any compatible Insights agent can read this public guide and walk you through setup without access to private host status.
Read https://vtxmacro.com/insights#subscription-inference and help me connect your supported VTX inference host. Install the durable service when your harness has a supported headless adapter; otherwise use the foreground host path and keep its agent loop open. For Main, help me choose Provider or Agent based on the model's explicit capabilities; keep Review and Screener in Provider mode. Save the setting and start the normal VTX Trader only after I approve. Confirm either that the OS service remains active independently of this chat or that the required foreground loop is still open. Do not advertise durability or Agent control that your harness cannot provide.
Connections are governed by the Privacy Policy and Terms of Service.
Optional reference material for deeper exploration. The machine-readable guide remains canonical.
Describe the outcome you want and let the agent choose the best VTX and native tools for the job.
Name the population: my profiles, exact public handles or wallets, or the whole platform. For named profiles, the agent verifies each ownership label before choosing the owned or public selection.
Name the time window and the decision you are trying to make.
Ask for the analysis, comparison, recommendation, or action that helps you decide.
Review important assumptions and approve consequential changes or trades in plain language.
Treat policy replay as a counterfactual, not as observed live performance.
Your agent decides how to investigate, calculate, recommend, and respond. VTX supplies the tools; it never grades or rewrites the answer.
Choose analysis, settings management, bot control, profile management, connection management, and trading access separately. Your agent app receives only the permissions you approve.
Changes and trades are limited to profiles you own and still pass the same VTX trading safeguards.
Insights is built for trading and bot operations. Manage billing and account security directly in VTX.
Review examples drawn from current VTX trading activity, then copy and adapt a prompt.
Sign in to see current showcase results and their exact coverage and sources. Public setup, capabilities, and prompt ideas remain available below.
Search starting points for performance reviews, trade-chain analysis, settings ideas, market research, and VTX product help.
How am I trading this week?
How is this account trading this week?
How am I trading this month?
Compare all my bots this month. Which model is performing best?
What was my account PnL and ROI over the last 30 days?
Rank my bots by PnL, win rate, and drawdown over the last 30 days.
Browse capabilities by permission group, or search for an exact analysis or owned-profile action.
Markets, profiles, decisions, settings, performance, and strategy evidence.
account.snapshotAccountInspect live positions, balances, orders, fills, and account activity.
analysis.cancelLarge analysesStart or resume a complete analysis that needs more time to finish.
analysis.startLarge analysesStart or resume a complete analysis that needs more time to finish.
analysis.statusLarge analysesStart or resume a complete analysis that needs more time to finish.
analytics.queryTrading analysisCompare performance, settings, trades, decisions, and strategy outcomes.
artifact.manifestLarge resultsWork through complete large result sets without losing requested evidence.
artifact.queryLarge resultsWork through complete large result sets without losing requested evidence.
artifact.query_manyLarge resultsWork through complete large result sets without losing requested evidence.
artifact.readLarge resultsWork through complete large result sets without losing requested evidence.
artifact.resumeLarge resultsWork through complete large result sets without losing requested evidence.
decision.contextDecisionsInspect the market and bot context behind stored trading decisions.
decision.outcomesDecisionsConnect stored decisions with what happened afterward.
decisions.historyTrading analysisCompare performance, settings, trades, decisions, and strategy outcomes.
execution.qualityExecutionAnalyze fills, fees, slippage, and order execution quality.
help.openVTX HelpFind current VTX product guidance and operating behavior.
help.searchVTX HelpFind current VTX product guidance and operating behavior.
inference.statusexternal inferenceUse this VTX ability in your connected agent.
market.calendarMarketsRead current markets, price history, news, and the economic calendar.
market.historyMarketsRead current markets, price history, news, and the economic calendar.
market.newsMarketsRead current markets, price history, news, and the economic calendar.
market.snapshotMarketsRead current markets, price history, news, and the economic calendar.
policy.evaluateStrategy testsReplay trading policies and compare counterfactual outcomes.
policy.replayStrategy testsReplay trading policies and compare counterfactual outcomes.
position.excursionsTrading analysisCompare performance, settings, trades, decisions, and strategy outcomes.
positions.episodesTrading analysisCompare performance, settings, trades, decisions, and strategy outcomes.
profiles.discoverProfilesFind your profiles, exact public profiles, or the full public platform.
runtime.provenanceChange historyTrace runtime, model, settings, and deployment changes behind behavior.
screener.candidatesScreenerInspect Screener candidates, runs, assignments, and outcomes.
screener.contextScreenerInspect Screener candidates, runs, assignments, and outcomes.
screener.historyScreenerInspect Screener candidates, runs, assignments, and outcomes.
screener.rankScreenerInspect Screener candidates, runs, assignments, and outcomes.
settings.readSettingsInspect, preview, snapshot, apply, and restore bot settings without a fleet-size cap.
settings.schemaSettingsInspect, preview, snapshot, apply, and restore bot settings without a fleet-size cap.
trade_chain.since_changetrade chainUse this VTX ability in your connected agent.
Preview, snapshot, tune, and restore settings across one bot or your owned fleet.
settings.applySettingsApply an approved common or per-bot settings plan with a pre-change snapshot.
settings.diffSettingsInspect, preview, snapshot, apply, and restore bot settings without a fleet-size cap.
settings.previewSettingsInspect, preview, snapshot, apply, and restore bot settings without a fleet-size cap.
settings.snapshot.createSettingsSave an immutable rollback point for selected bots or your complete owned fleet.
settings.snapshot.listSettingsInspect, preview, snapshot, apply, and restore bot settings without a fleet-size cap.
settings.snapshot.readSettingsInspect, preview, snapshot, apply, and restore bot settings without a fleet-size cap.
settings.snapshot.restoreSettingsRestore an approved fleet snapshot with version checks and complete per-bot outcomes.
settings.updateSettingsApply approved AI and bot-setting changes to a profile you own.
Inspect, start, stop, restart, trigger immediate cycles, or change execution mode across your owned bot fleet.
control.assistant.startBot controlStart the dry-run Assistant for one, selected, or all owned Server Mode profiles.
control.assistant.stopBot controlStop the dry-run Assistant for one, selected, or all owned Server Mode profiles.
control.bot.restartBot controlRestart one, selected, or all owned Server Mode bots with resumable stop/start stages.
control.bot.startBot controlStart one, selected, or all owned Server Mode bots through normal VTX runtime checks.
control.bot.statusBot controlCheck complete Server Mode status for one, selected, or all profiles you own.
control.bot.stopBot controlStop one, selected, or all owned Server Mode bots and retain every verified outcome.
control.bot.trigger_analysisBot controlRequest an immediate cycle for active owned Server Mode Traders or dry-run Assistants; Trader cycles may place trades.
control.execution_mode.updateBot controlMove one, selected, or all owned profiles between Client Mode and Server Mode.
Place market and limit orders or cancel open orders for profiles you own.
trade.batchTradingRun an ordered, resumable mix of trading actions across any number of owned profiles.
trade.cancel_orderTradingCancel an open order for a profile you own.
trade.cancel_twapTradingCancel one exact owned-profile TWAP and verify its latest exchange state.
trade.close_all_positionsTradingClose every open position for one owned profile after explicit confirmation.
trade.close_positionTradingClose one complete owned-profile position and verify the market is flat.
trade.limit_orderTradingPlace a limit order for a profile you own.
trade.market_orderTradingPlace a market order, including reduce-only closes, for a profile you own.
trade.scale_orderTradingPlace a complete ladder of limit orders and retain every child outcome.
trade.trigger_orderTradingPlace a take-profit or stop-loss trigger order for a profile you own.
trade.update_leverageTradingUpdate cross or isolated leverage for one owned-profile market.
Create, clone, rename, archive, restore, or delete profiles you own.
profile.archiveProfile managementArchive stopped owned profiles while preserving at least one active profile.
profile.cloneProfile managementClone settings from owned profiles without copying wallets, keys, or credentials.
profile.createProfile managementCreate one or more owned profiles through the account's current capacity rules.
profile.deleteProfile managementRemove explicitly confirmed owned profiles while retaining their historical public trading records.
profile.renameProfile managementRename owned profiles through the same uniqueness and cooldown rules as VTX.
profile.restoreProfile managementRestore selected or all archived profiles you own.
Add, validate, replace, or remove exchange and model-provider credentials. Secrets are never displayed back.
credentials.exchange.createConnection managementConnect owned-profile exchange wallets and signing keys through canonical validation.
credentials.exchange.removeConnection managementRemove explicitly confirmed exchange wallet and signing-key connections.
credentials.exchange.replaceConnection managementReplace an exchange connection after wallet ownership and signed-action validation.
credentials.exchange.validateConnection managementValidate configured exchange connections without returning wallet keys.
credentials.provider.createConnection managementConnect model-provider keys to owned profiles through encrypted write-only storage.
credentials.provider.removeConnection managementRemove explicitly confirmed model-provider connections from owned profiles.
credentials.provider.replaceConnection managementReplace complete model-provider key sets without exposing the previous or new values.
credentials.provider.validateConnection managementValidate configured model-provider connections and return status metadata only.
Open this reference when connecting, updating, disconnecting, or recovering an agent app.
Get a connection or workflow back on track quickly.
Refresh its plugin or MCP integrations, confirm VTX Insights is enabled, or use the manual setup shown on this page. Update the app or integration if it is still unavailable.
Start the agent's VTX sign-in flow, choose the permissions you want, and approve the connection. If access was revoked or expired, relink the client from this page.
Start VTX authentication from the MCP client and approve the browser request. In ChatGPT desktop use Settings, MCP servers, VTX Insights, and Authenticate. In Codex CLI or the IDE run codex mcp login vtx-insights --scopes insights:read.
Codex 0.146.0 has a known OAuth issuer-validation regression. Check codex --version, upgrade Codex, and start a new VTX login.
OAuth succeeded, but VTX could not return the authorized MCP tool catalog. This is a VTX MCP service or catalog problem, not a request for more browser or extension permissions. Retry after VTX service health is restored.
That authorization link is no longer usable. Return to the MCP client and start a new login; do not reuse the URL.
Ask which profiles and time window were used, what was unavailable, and whether population coverage differs from exact-economics coverage. Replay and excursion calculations run when requested; they are not an always-running simulator or an exact alternate-PnL forecast.
At least one exact handle or wallet could not be resolved in the selected owned or public population. Ask the agent to discover the profiles again, confirm each ownership label, and retry with the corrected exact selection. VTX stops before starting a background analysis rather than silently analyzing a smaller population.
Ask it to show the VTX evidence and calculations, challenge the assumptions, or try a different approach. Models can make mistakes; VTX does not approve or correct their conclusions.
The agent can continue the complete analysis in the background and resume retrieval from its last acknowledged checkpoint without shrinking the profiles or time window you asked for.
Targeted discovery is recursive and does not change the server index. The agent should query the artifact root, then each needed disclosed object path and continuation, then the disclosed list parent before batching exact child paths. Large typed filters scan that exact indexed parent incrementally and may continue through background analysis if they exceed the response window.
The essentials of agent choice, permissions, trading, and control.
Yes. With your approval, a connected agent can update AI settings on profiles you own, control Server Mode bots, request Client Mode Trader starts and stops, and place or cancel orders through VTX. Client control does not take over an owner; waiting for an eligible browser, desktop, or headless owner is not the same as running, and an in-flight stop may wait for settlement before its owner lease is revoked.
No. The VTX Insights connector ships a dedicated trade-chain analysis skill for Codex, Claude Code, OpenCode, OpenClaw, Hermes Agent, and other compatible skill hosts. It teaches the agent how to reconstruct bot campaigns, compare settings generations, verify evidence, and recommend focused improvements.
Yes. Select exact public handles or wallets, or compare the whole platform. Actions always remain limited to profiles you own.
No. The connected agent app owns model choice, conversation, inference, and native tools.
The response may summarize the result, but complete evidence remains available for focused indexed queries or restart-safe acknowledged retrieval.
Use VTX Help for product guidance outside Insights, or join the VTX Macro Telegram group for community help and setup discussion. Connected agent apps can also search and open the same canonical Help content.
Keep the agent integration current and remove access whenever a connected app is no longer trusted.