Row-Bot
A local-first desktop assistant that combines models, durable memory, and controlled tools for personal work.
- Source repo
- siddsachar/row-bot
- Stars
- ★ 1.7k
- Last updated
- today
- License
- Apache-2.0
- Primary language
- Python
- FA score
- 59/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformChatGPT · Codex · Claude.ai · OpenAI API · Claude APIClaude Code (Partial support)
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A researcher working from PDFs, spreadsheets, and personal notes can extract source material into a knowledge graph and retrieve it in later conversations.
- Not a fit if
- Teams needing multi-user hosting or tenant isolation; it is single-owner, multi-device only
- Anyone needing Computer Use on Linux or in the background; it is Windows/macOS interactive only
- Source review
- 59/100 · Major gaps
What does this agent do, and when should you use it?
Row-Bot is a local-first desktop AI assistant organized around reasoning, orchestration, and work across conversations, models, memory, and tools. Its execution layer includes a LangGraph ReAct agent, Goal Mode, Agent Profiles, and scoped child-agent delegation with visible goals, approvals, and local run history. The app combines a personal knowledge graph, document extraction, browser and shell access, workflows, messaging channels, Developer Studio, and Designer Studio. It can run with local Ollama models or opt-in providers including OpenAI, Anthropic, Google AI, xAI, OpenRouter, and custom OpenAI-compatible endpoints. It ships for Windows, macOS, and Linux, with authenticated single-owner remote access and a row-bot serve mode for browser-based server operation.
Row-Bot uses a LangGraph ReAct agent to assemble the active conversation, memory recall, and tool results into budgeted execution. It reads PDF, CSV, Excel, JSON, JSONL, TSV, and image files; extracts documents with source provenance; and stores or recalls knowledge through a personal graph. It can use Tavily, DuckDuckGo, Wikipedia, arXiv, YouTube transcripts, and URL reading for research, execute filesystem and shell actions in a configured workspace, and control a visible Chromium browser. Developer Studio links or clones Git workspaces, creates worktrees, shows diffs, runs tests, and prepares branches, commits, pushes, and PRs; Designer Studio produces decks, documents, landing pages, mockups, and exports. The row-bot serve command exposes session-gated browser access, while row-bot access invite creates one-time device invitations.
- A researcher working from PDFs, spreadsheets, and personal notes can extract source material into a knowledge graph and retrieve it in later conversations.
- A developer maintaining a repository can link or clone it in Developer Studio, use an isolated worktree, run tests, inspect diffs, and prepare Git changes under approval controls.
- An individual automating recurring work can build workflows with schedules, webhooks, completion triggers, conditions, approvals, and notifications.
- A single owner who wants access from a phone, tablet, or another computer can create an authenticated Remote Access invitation to the same running local instance.
- A user handling communications can authorize Gmail, Google Calendar, Telegram, WhatsApp, Discord, Slack, or SMS integrations for specific email, calendar, and messaging tasks.
- A privacy-focused user can run Ollama locally for inference while only opting into cloud or self-hosted endpoints when a task requires them.
How do you install or deploy this agent?
Source installation requires Python 3.12+. Install Ollama first only if you want local models; provider-only and custom-endpoint setups can skip it. Run:
git clone https://github.com/siddsachar/row-bot.git
cd row-bot
python -m venv .venv
source .venv/bin/activate
python -m pip install "uv>=0.7,<1.0"
uv sync --locked --all-extras --group test
uv run python launcher.pyOn Windows, activate with .venv\Scripts\activate. Alternatively, download the Windows installer or macOS DMG from GitHub Releases. On Linux, run curl -fsSL https://raw.githubusercontent.com/siddsachar/row-bot/main/installer/install-linux.sh | bash. In the first-run wizard, select Ollama, a provider, or a custom OpenAI-compatible endpoint; cloud features require the corresponding API key or in-app OAuth sign-in.
How do you use this agent?
After launch, choose a model path in the setup wizard: select Ollama and a model for local use; enter credentials such as OPENAI_API_KEY or ANTHROPIC_API_KEY for a supported provider; or enter a compatible self-hosted endpoint such as http://127.0.0.1:1234/v1. Then send a task such as “Read report.pdf in my workspace” or “Run git status on my project.” For larger work, create a Goal, choose an Agent Profile, and delegate a bounded child task. For headless operation, run uv run python launcher.py serve --port 8080, or use row-bot serve in an installed build; create a browser invitation with row-bot access invite --layout desktop --origin https://row-bot.example.com.
What are this agent's strengths and limitations?
- Local-first storage covers conversations, the knowledge graph, workflows, and settings by default; the project states that Row-Bot has no account system or hosted inference middleman.
- It supports Ollama, custom compatible endpoints, multiple API providers, and in-app paths for ChatGPT/Codex, Claude Subscription, and xAI Grok.
- Knowledge management, Git worktrees, browser automation, workflows, and channel messaging are coordinated through shared goal, approval, and execution-budget controls.
- Remote access is designed for one owner with single-use invitations, revocable sessions, hashed local credentials, and session-gated browser access.
- Local inference requires Ollama; the documented recommendation for stronger agent behavior is a 14B-class model and 16–32 GB RAM or suitable GPU, which can raise hardware costs.
- Cloud models, search, email, calendar, channels, and media generation depend on provider credentials, OAuth, or network access; selected conversation and tool context are sent to the chosen endpoint.
- Computer Use is an opt-in beta limited to interactive local Windows and macOS sessions, requiring Cua Driver installation and OS permissions; it does not support Linux or background use.
- Users migrating from Thoth or an early Row-Bot build must first launch a prior migration-capable release because the current startup path no longer performs the old rebrand migration.
- Server, reverse-proxy, and Docker deployments require the operator to manage TLS, trusted proxies, backups, rate limiting, and firewall policy.
How does this agent compare with similar options?
Compared with using Ollama alone for local inference, Row-Bot adds provider-qualified cloud and OpenAI-compatible endpoint paths while preserving model capability and fallback status. Compared with browser automation, native Computer Use targets local Windows/macOS applications but requires separate installation and consent; the project identifies browser automation as the preferred website mechanism. Docker Sandbox differs from direct local execution by working in a shadow workspace that must be explicitly imported before it changes the real repository.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Row-Bot This agent | 59 · Major gaps | Desktop appFree + model costs | ★ 1.7k | today | Python | ChatGPT · Codex · Claude.ai · OpenAI API · Claude API |
| Skales | 36 · Major gaps | Desktop appFreemium | ★ 2.2k | 3d ago | — | ChatGPT · OpenAI API · Claude API |
| TuriX | 34 · Major gaps | CLIFree + model costs | ★ 3.2k | 1mo ago | Python | Claude.ai |
| TARS Multimodal Operator | 30 · Major gaps | CLIFree + model costs | ★ 40k | 28d ago | TypeScript | Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows: README explicitly states local-first, data stays on machine by default, uses OS credential store and Docker encrypted volumes, emphasizes invitation/session separation, revocable sessions, strict origin checks, and optional Computer Use requires explicit consent. Deductions: dependency security only lists version ranges without vulnerability scanning or audit evidence; rollback only mentions recovery tools without specific mechanisms; publisher identity unverified, source attribution based only on repository metadata.
Evidence shows: README consistent with pyproject.toml, CI configures multi-platform tests and dependency verification, test files include guards preventing writes to live user state. Deductions: no specific failure message examples or error handling documentation, dependency availability only guaranteed by version ranges without runtime verification.
Evidence shows: README details multiple usage scenarios (local, providers, custom endpoints), explicitly lists capability boundaries (e.g., SMS text-only, Computer Use off by default), provides trigger examples (common prompts), and supports multiple platforms (Windows/macOS/Linux/Docker). Deductions: no detailed trigger conditions or environment configuration requirements, environment fit based only on claims.
Evidence shows: README well-structured, provides install instructions, quick start, remote access guide, naming stable (Row-Bot formerly Thoth), example prompts, known limitations explicit (e.g., SMS text-only, Computer Use off by default), license Apache-2.0. Deductions: no version history or changelog, maintenance responsibility only implied via SECURITY.md and CI, no explicit maintainer.
Evidence shows: README describes outputs as usable reports, action plans, and designs, provides video demos, emphasizes local-first and cost control (optional cloud models). Deductions: no performance benchmarks or user feedback, marginal value based only on feature list.
Evidence shows: README feature claims partially correspond to pyproject.toml dependencies and CI tests, but no specific test results or independent verification provided. Deductions: claims are mostly assertions without traceable test evidence, facts and inferences not clearly separated.
- Publisher identity unverified; verify source before installation.
- Dependency security lacks vulnerability scanning or audit evidence; review dependency versions.
- Rollback mechanism only mentions recovery tools without specific steps.
- Version history or changelog missing; proceed with caution before upgrading.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v5.3.2 v5.3.2 - Videos That Look And Sound Right, A Calmer App
Release notes excerpt
v5.3.2 - Videos That Look And Sound Right, A Calmer App Row-Bot 5.3.2 makes its videos look like a studio made them and never lets a silent one slip out, asks you less for the things you clearly asked for, and makes Home and Settings calmer. It comes from a week of using Row-Bot like you would, on Windows and a Mac, with ChatGPT and a model on this computer. From 5.3.1 it arrives through background updates. Videos - Made like a studio - a camera that follows what's done, the page framed on your brand's backdrop, titles as lit slides and lower thirds, captions a …View on GitHub ↗ -
v5.3.1 v5.3.1 - Real Work, Video, Linked Conversations & Waits
Release notes excerpt
v5.3.1 - Real Work, Video, Linked Conversations & Waits Row-Bot 5.3.1 is about getting real work done. It follows the approval level you chose, with far fewer refusals. It can make and edit videos and talk to its other conversations. A chat or workflow can wait for something without using your plan, and Row-Bot tells you what it's doing as it works. From 5.3.0 it arrives through background updates: Settings › Updates offers Restart now. Read Upgrade Notes below before upgrading. New Since The Beta - Weekday schedules run on weekdays - a workflow set to "1-5" runs Monday …View on GitHub ↗ -
v5.3.0 v5.3.0 - A Browser In The App, Pages, Outlook & Reviewed Approvals
Release notes excerpt
v5.3.0 - A Browser In The App, Pages, Outlook & Reviewed Approvals Row-Bot 5.3 puts its browser inside the app and rebuilds computer use. Row-Bot can make pages you work in beside the chat, ask you questions with options, and connect Outlook and several X accounts. Chats can be incognito, background work shows up at once, Auto approvals are reviewed and a new Hands-off level asks nothing. Row-Bot can run servers and long jobs in the background, edit video, send you files and work on code from any of your devices. Claude works with your …View on GitHub ↗