Feature inventory
The complete workbench
Row-Bot combines the reasoning flexibility of a model router with durable agents, explicit goals, local memory, real tools, background workflows, phone access, messaging, code workspaces, design canvases, and reviewable extensions. This page documents what ships and where each capability fits.
Row-Bot turns a chat thread into a controlled working environment. Profiles define how an agent should operate, Goal Mode keeps long-running intent visible, and delegated child agents handle bounded work without severing the parent conversation.
Profiles, goals, and agents documentation →
Give a thread a reusable role with instructions, usage guidance, handoff contracts, workspace policy, enabled tools and skills, approval policy, and model preferences. Profile snapshots travel with delegated work so the operating contract remains explicit.
Keep the objective, current progress, evidence, blockers, next step, status, and completion summary beside the conversation. Goal turns can use tools, delegate work, resume after approvals, and deliver terminal notices through configured channels.
Spawn focused runs with parent linkage, live status, event history, queues, tool boundaries, wait and stop controls, and durable completion summaries. Promote successful patterns into reusable profiles or reviewable workflows.
Bound long-running Agent work with durable model-and-tool round counters, repeat-stall protection, exactly-once finalization, and configurable nesting, concurrency, and active-time limits. Extra child runs wait in a fair queue instead of bypassing capacity.
Child approvals, completion notices, failures, queued turns, and durable, deduplicated run summaries surface in the parent thread instead of disappearing into background state.
Every selection stays provider-qualified from setup through runtime. Row-Bot separates model discovery, credentials, capabilities, readiness, context policy, and transport behavior so similarly named models do not become interchangeable by accident.
Models and providers documentation →
Discover and use Ollama plus OpenAI-compatible runtimes such as LM Studio, vLLM, llama.cpp, LocalAI, LiteLLM, SGLang, and oMLX. Local endpoints remain distinct from hosted services and can work offline when their runtime and model are local.
Connect OpenAI, Anthropic, Google AI, xAI, OpenRouter, Requesty, Atlas Cloud, MiniMax, OpenCode providers, Ollama Cloud, and custom endpoints. Capability mapping routes chat, tools, reasoning, vision, image, and video models to compatible surfaces.
Keep xAI Grok OAuth, ChatGPT/Codex, and Claude Subscription authentication separate from API-key providers. OAuth health, credential source, model visibility, and runtime readiness appear in provider settings.
Targeted, startup, and scheduled refreshes discover newly available models. Last-known-good provider rows survive failed or incomplete refreshes, while live, cached, fallback, and empty outcomes remain visible.
Model-aware context budgets, compaction, prompt-cache diagnostics, cache-stable prefixes, and provider-specific reporting make long conversations more predictable. Unsupported or chat-only transports receive explicit fallbacks.
Inspect the effective schema sent through each adapter. Gemini-compatible filtering catches untyped arrays before a request is made, while unaffected providers keep the original tool contract and explicitly requested incompatible tools fail clearly.
Row-Bot can chain built-in tools inside an agent turn, limit them through profiles, pause for approval, and return generated files to the conversation or configured delivery channel.
Tools and approvals documentation →Computer Use documentation →
Search the web through configured services or DuckDuckGo, read URLs, query Wikipedia and arXiv, inspect YouTube content, work with local documents, and preserve useful findings in memory or the wiki vault.
Read and manage files, run approval-gated shell commands, automate browser sessions under Row-Bot’s browser policy, inspect page state, redact sensitive tool output, and bring generated files back into a thread. Consequential navigation and browser takeover remain visible.
Opt into the Computer Use beta for Windows and macOS through a pinned, checksum-verified Cua Driver. Target-window capture, an exclusive interactive lease, point-of-risk approvals, blocked sensitive surfaces, ephemeral Vision fallback, and Stop/Take over/Resume controls constrain every session. The separately installed driver’s consent-gated third-party telemetry is disclosed before enablement and is not a Row-Bot telemetry pipeline.
Use Gmail and Google Calendar with OAuth-backed tools for search, drafting, event lookup, typed mutations, and bulk creation. Calendar operations use request-scoped clients, safe concurrent refresh, retries, ordered writes, and timeout reconciliation.
Calculate, query Wolfram Alpha, inspect weather, analyse images, search conversations, create charts, generate or edit images, and produce video through compatible provider models. Media choices remain scoped to the correct surface.
Useful recall needs more than an opaque summary. Row-Bot stores structured local records, combines semantic, lexical, and graph signals, and keeps review state and trace information available when you need to understand why something returned.
Knowledge and memory documentation →
Represent people, projects, preferences, facts, events, documents, and other entities as typed nodes and relationships. Browse the graph, review extracted memories, normalise relations, and repair inconsistent records without touching real user data in tests.
Combine configurable embeddings, FAISS semantic search, FTS5 lexical matching, and bounded graph expansion. Local embedding startup is cache-only, downloads and repair are explicit, and missing models fall back quickly to lexical and graph retrieval instead of stalling the request.
Read PDFs, spreadsheets, JSON, TSV, images, and common text formats; extract knowledge under reviewable policies; and retain source metadata so derived facts can be traced to their origin.
Export an Obsidian-compatible local wiki, synchronise selected knowledge, and let the idle-aware Dream Cycle consolidate memory or prepare bounded improvement proposals while preserving busy-state and review controls.
Turn repeated tasks into scheduled or manually triggered pipelines without turning them into invisible automation. Profiles, delivery defaults, conditions, approvals, run history, and recovery state stay attached to the workflow.
Choose a profile, model override, tool policy, prompt, schedule, persistent thread, conditions, approval mode, and delivery destination. Advanced graph steps support multi-stage work while the mobile editor covers common prompt workflows.
Pause consequential actions for approval in the app or supported channels. Workflow-level delivery defaults distinguish no destinations from inherited destinations, and channel retries retain terminal notices until they can be reconciled.
Inspect scheduled runs, subtasks, pipeline state, errors, completion summaries, database recovery diagnostics, insight cards, and attention states in a collapsible console rather than relying on ephemeral notifications.
Stop connects the active generation to provider responses, subprocesses, tool waits, browser work, MCP calls, voice turns, and child agents spawned by that generation. Unrelated runs remain untouched.
Mobile Companion is a phone-native interface served by the running Row-Bot host—not a separate Row-Bot cloud service. Pair over an approved route, keep the host as the system of record, and revoke access locally.
Mobile Companion documentation →
Use Chat, Activity, Workflows, Knowledge, and Settings navigation designed for a small screen. Create threads, attach files, choose skills, profiles, and models, follow generation state, and stop active work.
See active chat generations, running workflows, recent runs, tool approvals, and workflow approvals in one phone-safe surface with approve, deny, and stop actions.
Create short-lived single-use QR links, store session tokens in HttpOnly cookies, rate-limit failed attempts, review display-safe access events, list paired devices, and revoke a phone immediately.
Connect over a local network, Tailscale direct or Serve routes, an existing ngrok tunnel, or an advanced custom origin. Remote HTTP and WebSocket traffic remains pairing-gated while direct desktop loopback stays open.
Messaging adapters share one delivery engine while preserving the limits and native interaction model of each platform. Channel work uses the same threads, profiles, Goal Mode, approvals, media handling, and final records as desktop turns.
Channels and voice documentation →
Coalesce edits, keep typing alive, bound previews, split long output safely, respect rate limits, clean up previews, and send a fresh final message when an edit cannot complete. Discord, Slack, Telegram, and WhatsApp use the best supported path.
Approve or deny through Discord buttons, Slack Block Kit actions, Telegram inline controls, WhatsApp resume flows, or explicit SMS YES/NO handling. SMS intentionally remains final-text-only with safe chunking.
Use local Whisper speech-to-text and Kokoro text-to-speech, or opt into compatible realtime voice providers. Voice turns share agent tools and cancellation behavior while provider usage remains explicit.
Receive images and documents, return generated files, show reactions and health state, and deliver compact once-only Goal Mode or child-agent completion notices. Failed terminal notices remain available for retry.
Developer Studio connects conversational work to explicit Git repositories and durable worktrees. It is designed for reviewable implementation, not a hidden command runner.
Developer Studio documentation →
Connect local repositories, restore code threads from the sidebar, allocate worktrees to threads or delegated runs, preserve workspace context, and keep source changes separate from unrelated work.
Inspect diffs, run focused tests, manage todos, review command output, prepare commits and pull requests, and require approval for install, network, delete, commit, push, or PR actions.
Run commands and edits in a shadow copy, inspect the result, and import approved changes back into the real repository. Import gates protect the workspace from unexpected sandbox output.
Profiles, goals, child agents, tool policy, write locks, cancellation, and approval reasons remain available inside the coding surface, so long-running implementation follows the same operational model as other Row-Bot work.
Designer Studio provides mode-aware canvases for presentations, documents, landing pages, app mockups, and storyboards. Generated output remains open to targeted edits, previews, export, and repair.
Designer Studio documentation →
Choose the canvas and constraints appropriate to a deck, document, web page, interface, or storyboard. Templates and brand controls keep format-specific decisions visible instead of forcing everything through one generic layout.
Render deterministic previews, select the part that needs work, request bounded changes, and preserve unaffected content. History, thumbnails, and snapshots make iteration reviewable.
Generate or edit images, add provider-compatible video, insert charts, attach references, and keep assets associated with the project before the first build or later revision.
Export structured artifacts and publish shareable interactive HTML while the sandboxed runtime constrains generated scripts. Critique and repair loops check the work before handoff.
Skills, plugins, MCP servers, and Custom Tools add capability through separate contracts. Enablement, permissions, configuration, health, and profile policy determine what becomes available to an agent.
Install, enable, and pin reusable instruction packages, invoke slash commands, and let Agent Profiles narrow which skills enter a run. Bundled, user, and plugin-provided skills retain clear ownership.
Install reviewable plugins that provide native tools, packaged MCP servers, bundled skills, or channels. Manifests declare permissions, settings, secrets, authentication, health checks, versions, and supported extension surfaces.
Connect stdio, HTTP, or SSE servers with capability metadata, safety classification, requirements, probes, conflict handling, and approval gates. Marketplace metadata, including catalog entries such as Xquik, remains intact through configuration edits.
Turn a repository, local folder, or current workspace into a reusable tool through Source, Inspect, Test, and Enable stages. Safer Git setup, isolated environments, command checks, removal, and optional chat promotion keep experiments bounded.
Local-first means durable application state belongs to the user, external routes are explicit, and consequential actions remain reviewable. It does not pretend that a hosted model or online tool can be used without sending that service the data required for the request.
Privacy and safety documentation →
Store conversations, profiles, goals, child-run records, workflows, memory, documents, Designer projects, plugin state, code context, and paired-device records under the local Row-Bot data directory.
Use the operating-system credential store when available, session-only fallback where supported, fingerprints and hashes for display-safe identity, and metadata files that do not contain provider tokens as plain secrets.
Classify destructive, networked, private-data, metered, installation, Git, shell, browser, channel, and MCP actions conservatively. Approval cards show bounded reasons while retaining the original action payload for the decision.
Row-Bot has no required account, hosted sync service, or first-party telemetry pipeline. Optional providers, channels, tunnels, updates, search, and external tools remain individually visible choices. The opt-in Cua Driver has separately disclosed, consent-gated third-party telemetry; it is the reviewed exception, not Row-Bot telemetry.
Windows and macOS are first-class desktop targets, while Linux provides the browser/server application through a verified XDG user install. Packaging includes the application source, locked runtime dependencies, bundled skills, UI assets, and required installer metadata.
Installation documentation →Troubleshooting documentation →
Use the Windows x64 installer, macOS Apple-silicon DMG, or verified Linux one-line installer and tarball. Published artifacts, checksums, and platform trust details are listed with each release so signing or notarization is never implied.
Resume onboarding across provider configuration, credentials, model selection, tools, optional integrations, and runtime checks. Setup guidance distinguishes missing configuration, missing dependencies, unhealthy credentials, and unsupported models.
Inspect provider health, model count and provenance, OAuth state, prompt-cache metrics, workflow attention, task recovery, app performance, update state, and subsystem readiness without digging through raw configuration files.
Check signed release metadata, download compatible updates, validate installer contents, and preserve local data through upgrades. Deeper installer verification covers clean installs, repair, upgrade, uninstall, and installed-package smoke checks.
Get Row-Bot
Start locally, add providers and integrations deliberately, and let the workbench grow with the work.