Feature inventory
The complete workbench
Row-Bot combines provider-aware reasoning with parent-led agents, durable document processing, explicit goals, local memory, real tools, authenticated browser access, background workflows, 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 one authoritative parent can plan, delegate, join required results, continue through several work waves, and produce the final answer.
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.
Delegate required or background work with dependencies, duplicate-objective checks, multiple work waves, live joins, and visible capacity limits. The parent remains responsible for follow-up and the final response.
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.
An ordered inbox returns approvals, completions, retries, steering, and stop events to the parent. Checkpoints, leases, and finalization claims recover interrupted work without duplicate synthesis, delivery, or final answers.
Keep the selected Chat, Developer, or Designer thread in a compact always-available surface on Windows and macOS. Buddy shares the thread’s draft, model, tools, approvals, and run state instead of creating a second conversation.
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 through provider-scoped saved credentials. Last-known-good provider rows survive failed or incomplete refreshes, while live, cached, fallback, and empty outcomes remain visible.
A desktop meter estimates the complete next model input, including system prompts, images, and bound tool schemas. Model-aware rolling compaction starts with safe headroom, preserves recent complete turns, and records durable status, while prompt-cache diagnostics and provider-specific reporting keep long conversations predictable.
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, progressively discover enabled external capabilities, limit them through profiles, pause for approval, and return generated files to the conversation or configured delivery channel.
Progressive tools and skills →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.
Keep core tools ready while deterministic local search finds enabled MCP, plugin, Custom Tool, and channel capabilities only when a request needs them. Auto mode binds the exact selected schema instead of unrelated catalogs; eager compatibility mode remains available without changing provider checks, profiles, approvals, budgets, or workspace policy.
Read and manage files, run approval-gated shell commands, and automate managed Chromium sessions under Row-Bot’s browser policy. Snapshot-bound observations, sensitive-output redaction, visible consequential navigation, takeover controls, and action receipts keep browser work reviewable.
Opt into the Computer Use beta for Windows and macOS through the pinned, checksum-verified Cua Driver 0.20.0. Target-window capture, semantic actions before coordinate fallback, action receipts, 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, with xAI image options discovered from live model capability metadata.
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.
Stream bounded uploads into a persistent SQLite queue, deduplicate content, make the complete batch searchable before extraction, and publish sharded vector manifests atomically. Pause, resume, cancel, retry, repair, and restart without losing safe progress.
Extract knowledge from PDFs, spreadsheets, JSON, TSV, images, and common text formats through bounded map-and-reduce checkpoints. Source metadata stays attached and final document, graph, and Wiki Vault updates commit idempotently.
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.
The local desktop, authenticated remote desktop, and compact phone layout are presentations of the same Row-Bot owner. The host remains the system of record, compact mode changes layout rather than authority, and every remote session can be reviewed and revoked.
Remote access documentation →Compact interface documentation →
Use the complete desktop workspace remotely or switch to Chat, Activity, Workflows, Knowledge, and Settings navigation designed for a small screen. Create threads, attach files, choose profiles and models, approve work, and stop active runs.
Run row-bot serve for a long-lived headless host. HTTP and WebSocket requests share exact-origin, allowed-host, trusted-proxy, and authenticated-owner gates; server loopback does not bypass authentication.
Create origin-bound, expiring, one-time invitations from the app or CLI. Instance-isolated HttpOnly sessions renew authoritatively, record secret-free audit events, and support logout plus immediate session or device revocation.
Save exact owner-controlled HTTP or HTTPS browser addresses so admission, invitations, and later removal take effect without a restart. Environment-managed origins remain read-only, assigned non-private interfaces carry explicit exposure warnings, and Row-Bot cleans up only the Tailscale routes it owns.
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. Authenticated browsers can capture, transcribe, and play speech locally to that session without starting the host microphone service or retaining browser media.
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 Row-Bot select up to five relevant enabled skills per parent task or child Agent. Reopened tasks restore their skill state, while skills remain instructions and cannot grant tools or bypass profile, approval, budget, or workspace boundaries.
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, orchestration records, workflows, document queues and indexes, memory, Designer projects, plugin state, code context, and owner access records under the Row-Bot data directory.
Use the operating-system credential store on desktop or an isolated encryption key with encrypted provider and channel records in server deployments. Read-only secret directories, safe fingerprints, and redacted status keep plaintext credentials out of application metadata and diagnostics.
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.
Select conversations with filter-aware bulk controls and remove them through one cleanup path. Active work is cancelled before deletion, while dirty Developer recovery state, workspaces, and Designer project ownership are preserved.
Windows and macOS are first-class desktop targets, Linux provides the browser/server application through a verified XDG user install, and the official multi-architecture container provides a hardened headless path for private servers and VPS hosts.
Installation documentation →Docker and VPS operations →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.
Run the locked non-root amd64 or arm64 image with a read-only root filesystem, dropped capabilities, bounded logs, a persistent data volume, and a separate persistent secrets volume. Compose, VPS, Caddy, systemd, backup, upgrade, and rollback examples keep operations explicit.
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.