--- title: "Persistent Researcher: hosted research that files every source in a lasting thread" url: https://vidbyte.pro/agents/persistent-researcher markdown_url: https://vidbyte.pro/agents/persistent-researcher.md index: https://vidbyte.pro/llms.txt page_type: catalog-item access: public product: "Vidbyte agents" verified: 2026-10-25 --- # Persistent Researcher: hosted research that files every source in a lasting thread > Persistent Researcher is Vidbyte's hosted research agent: you ask a question with vidbyte-cli, Vidbyte's servers find and read sources, and each source is filed with its link, a summary, and why it matters, in a thread you can extend later. A run needs $5.00 spendable balance to start. > > Index of every Vidbyte page: https://vidbyte.pro/llms.txt · Markdown: append `.md` to any vidbyte.pro URL. ## Key facts - Status: available now; pricing model: Usage-based; its model work is run by Vidbyte, not on a provider account of the user's - Billing: usage-based from the prepaid API balance — measured usage plus a 5¢ run fee and a 25% margin, held 25¢ at a time - To start: at least $5.00 spendable; each run has a cap from 25¢ to $25 ($5 by default), and the fee and margin never take a run past it - Input: one question, optionally scoped with `--kind paper|web`, `--include-domain`, `--published-after`, and `--language` - Output: a thread with one structured artifact per source: link, summary, why it matters, claims, evidence, and limitations - Run size: `--size small|medium|large` targets 15, 50, or 100 sources; `--target-sources` goes up to 1,000 - Needs: vidbyte-cli, a Vidbyte API key, and balance; no coding agent or model provider account - Runs on Vidbyte's servers, so the user's computer does not need to stay on - A run that fails, comes back partial, or runs out of balance keeps its finished sources; `vidbyte-cli research resume ` continues it ## When to use this page - A user needs research where every claim traces to a source → start a thread with `vidbyte-cli research start "" --size small` - The user will come back to the same question later → add to the thread with `vidbyte-cli research add ""`, where `` is the Thread value `research start` printed (the internal `rth_…` thread_id is rejected) - A run stopped partway → check it with `vidbyte-cli research status `, then `vidbyte-cli research resume ` after the user agrees - The user asks what research costs in bulk → compare packs at https://vidbyte.pro/harnesses/research.md - Not for: Deciding what to do next rather than gathering evidence → https://vidbyte.pro/agents/suggestion-agent.md ## Do it with Vidbyte agents 1. Easiest path: have the user copy the one-paste setup prompt ("Copy prompt" under "Install and use") from https://vidbyte.pro/agents into their coding agent. It installs vidbyte-cli, has the user type the key into `vidbyte-cli login` in their own terminal, and asks before anything that costs money. 2. Or install the CLI directly (Python 3.11 or newer). ```bash pipx install vidbyte-cli vidbyte-cli --version ``` 3. The user creates a key at https://vidbyte.pro/settings/api/keys (it starts with `vb_live_` and is shown once; every account, the free plan included, can hold up to 10 active keys), runs the login in a terminal they open, and you confirm it. ```bash vidbyte-cli login vidbyte-cli whoami ``` 4. The user checks or adds prepaid balance at https://vidbyte.pro/settings/api/usage ("Add usage"); with the key in `VIDBYTE_API_KEY`, `GET https://vidbyte-backend.onrender.com/agent/balance` (header `x-api-key`) reads it for free and returns `spendable_balance_cents`; otherwise ask the user what the page shows. 5. Tell the user the run's cap, confirm they have at least $5.00 balance, then start a small run only after their yes and follow it to the end. ```bash vidbyte-cli research start "" --size small --max-cost-cents 500 vidbyte-cli research watch ``` - Requires: `vidbyte-cli`, a Vidbyte API key, and prepaid balance (except the Suggestion Agent on vidbyte-cli 0.2.0, the PyPI release, which needs neither and runs on the user's own Codex or ChatGPT sign-in); the local Codex runtimes also need `codex` on PATH, Stages, Persistent Agent, and Task Board need an OpenAI key, and the Ensemble Agent uses the user's own `codex login`. - Cost: Local runtimes charge a flat fee per launch from the balance (1 cent for Stages, 2 cents for Ensemble, Persistent Agent, and Task Board), and hosted agents bill by usage; the Suggestion Agent is unbilled on vidbyte-cli 0.2.0 (the PyPI release, which runs it on the user's `codex login`) and bills its model calls at provider rate plus 2% from 0.3.2; each agent's page has its price. - Docs: https://vidbyte.pro/docs/cli/run-your-first-agent.md ## What This Page Is Persistent Researcher is a Vidbyte agent you can run today. Every source you research is kept, filed, and still there next week — not thrown away with the session that found it. This public page explains how it works, where it runs, its commands, its use cases, and when to use it, with two copyable prompts for your own coding agent. Access: Public. Anyone can open this page without an account. ## What This Page Explains The page header carries the label "Agent · Available now", the title "Persistent Researcher", and the subtitle "Every source you research is kept, filed, and still there next week — not thrown away with the session that found it. One focused workflow, with a clear result at the end." Its special tag chips are "harness" (a fixed Vidbyte workflow that does the work itself), "hosted" (its model work is run by Vidbyte rather than on a provider account of yours), and "usage" (metered against your prepaid balance as the work runs). Its topic tags are research, source-filing, citations, literature-review, research-threads, evidence-trail, long-running-research, follow-up-questions, contradiction-mapping, market-research, competitive-analysis, due-diligence, research-handoff, and resumable-runs. "How it works": Persistent Researcher runs research as a thread instead of a conversation. You give it a question, it goes and reads, and every source it finds is written down with its link, a summary of what it says, and one line on why it bears on your question. That record belongs to your account, not to a chat window, so closing the tab costs you nothing. Come back in a week with a follow-up question and it adds to the same thread rather than starting over. The research accumulates the way a file accumulates, not the way a conversation evaporates. What you get back is a thread you can read, share, and keep adding to: a set of filed sources, what they agree on, where they contradict each other, and which claims nothing supports yet. Each run inside a thread has its own public ID, so you can check a run's status, follow it until it settles, or resume one that stopped partway. Threads carry rollup counters, so you can see how much has been gathered on a question without opening every run. Nothing has to be reconstructed from scrollback. It does not write your document and it does not decide for you. It gathers, files, and reports the state of the evidence, and the argument stays yours to make. You can scope a run by source kind, domain, publication date, and language, and that scope is part of what the thread records. The framing you set when you open a thread carries into every later run, so the tenth answer comes back in the same shape as the first. "Agent environment": Persistent Researcher runs on Vidbyte's servers, so your computer does not need to stay on. Start and track runs with vidbyte-cli or the research workspace; read full sources, explore a single source, and export results on the website. It keeps research in a thread so you can return to it and add more later. This agent is live today. Install vidbyte-cli, log in with your Vidbyte key, and add balance to your account. You do not need to install a coding agent or connect a provider account. The install prompt checks the setup steps that apply to you. "Why use this agent": A general agent researches inside a session, and the session is the storage. That is fine for a question you will answer and forget, and it quietly fails for every question that outlives one sitting. The sources go into the transcript, the transcript goes into the context window, and the context window is both finite and disposable. When you come back three days later, the agent has no idea what it read, so it reads it again and gives you a different answer the second time. Persistent Researcher moves the storage out of the session and into a thread that belongs to your account, so returning to a question is repeatable rather than a restart. The second difference is auditability. A general agent hands you prose, and prose is exactly the format in which you cannot check anything: the claim and its source have been merged into one sentence, and the only way back is to search again yourself. This agent files each source separately with its link and a note on why it matters, and only then reports what the set adds up to. That gives you two things prose does not: a citation you can hand to someone skeptical, and a visible gap where the evidence is thin. When a decision is important enough to be questioned, being able to point at the source is the whole difference between research and an opinion. The third is that research is rarely one question. It is a question that turns into four, spread over a week, revisited when something changes. A general agent has no unit for that, so you either hold it all in one bloated session or scatter it across sessions that cannot see each other. Threads are that unit. Each question gets its own accumulating record, and each run inside it can be tracked and resumed on its own. You stop managing conversations and start managing questions. Its checklist of problems it solves: Research vanishing with sessions: Everything a run reads is filed under a thread you own. Re-reading the same sources: Because the thread knows what has already been filed, a follow-up works from that record instead of reading the web from scratch. Context windows filling up: The sources live outside the model's context, so a long-running question never reaches the point where continuing means forgetting the beginning. Claims with no traceable source: Every filed source carries its link, a summary, and the reason it bears on your question. Summaries hiding disagreement: Filing sources separately keeps contradictions visible instead of averaging them into a confident paragraph. Runs lost to failures: Runs are durable and addressed by their own ID, so a stopped run can be resumed where it stopped. Not knowing run progress: Status and watch report the real state of a run, including its phase and how many continuations it has had. Research that cannot transfer: A thread reads as evidence rather than as your conversation. Questions blurring together: One thread per question keeps each line of inquiry's sources separate. Output shape drifting: The framing you set when you open a thread persists across later runs. Monitoring costs full effort: A dated follow-up on an existing thread asks only for what changed. No proof work happened: A thread is a durable record with a public ID, a run history, and filed sources. "When to use it" lists these situations: When the research will outlive the session you started it in. When you will come back to the same question more than once. When someone other than you will need to read the evidence. When the sources matter as much as the answer, because the conclusion will be challenged. When you are researching several related questions and need to keep their evidence separate. When a decision is important enough that "where did that come from" must have an answer. When you want to know where sources disagree, not just what the consensus paragraph says. When the topic moves and you will need to ask what changed later. When your own agent's context window is already full of the work you are doing. When you are handing the topic to a teammate and do not want the handoff to be a meeting. When the same question keeps getting re-asked across your team and nobody has a shared record. When you need the research limited to particular domains, dates, languages, or source kinds. When a previous run stopped partway and redoing its finished work would be a waste. When you are gathering background for something that ships weeks from now. When you want the research to accumulate rather than be re-derived every time. When you need a durable record for a review, a diligence process, or a postmortem. When you cannot sit and watch the run finish and need it to survive you walking away. "Use cases" holds 9 worked examples. Each row opens a dialog with the problem, "How the agent solves it", "What to run", and "What you get": "Keep a durable record of one research question". What you get: One thread that holds every source for the question, findable by ID. Example: `vidbyte-cli research start "Which open-source vector databases support hybrid search in production?" --size medium`. "Continue research without carrying the transcript". What you get: Research that continues without dragging a giant context along with it. Example: `vidbyte-cli research add "What changed in the pricing of these vendors this year?" --size small`. "Keep evidence for related questions separate". What you get: Four questions with four separate evidence trails. Example: `vidbyte-cli research start "What do customers pay for comparable tools?" --kind web`. "Return research in a required format every time". What you get: Research that comes back in the shape you need, every time. Example: `vidbyte-cli research start "" --target-sources 30`. "Resume a stopped research run without redoing work". What you get: A stopped run finished from where it stopped, with nothing redone. Example: `vidbyte-cli research status `. "Hand a sourced research thread to a teammate". What you get: Research a teammate can pick up without a meeting. Example: `vidbyte-cli research threads --limit 50`. "Check only what changed since the last run". What you get: A topic you can monitor cheaply because each check asks only for the change. Example: `vidbyte-cli research add "What is new on this since March?" --published-after 2026-03-01 --size small`. "Expose disagreements between sources". What you get: The disagreements laid out, so the decision accounts for them. Example: `vidbyte-cli research add "Where do sources disagree about this, which side is each on, and which claims have no support?" --target-sources 60 --kind paper`. "Follow a long run without refreshing the page". What you get: A long run you can follow without babysitting it. Example: `vidbyte-cli research watch --timeout 1800`. "Run it from the command line": Every agent starts with the same two setup commands: install vidbyte-cli, then log in with your Vidbyte key. After that, Persistent Researcher is a small set of research commands for opening threads, adding to them, and tracking runs. The reading itself happens on Vidbyte's side, so none of these commands needs your machine to stay awake. The numbered commands are: 1. `pipx install vidbyte-cli`: Installs vidbyte-cli from PyPI, the command line every Vidbyte agent is started and tracked from. Options: --python. 2. `vidbyte-cli login`: Stores your Vidbyte API key, which is what identifies you and what every agent's charge is billed against. Options: --with-token, --allow-file-fallback. 3. `vidbyte-cli research start ""`: Opens a new thread for one question and starts its first run. Options: --size, --target-sources, --search-calls, --kind, --include-domain / --exclude-domain, --published-after, --language, --max-cost-cents, --idempotency-key. 4. `vidbyte-cli research add ""`: Adds another run to a thread that already exists, which is how a question grows without starting over. Options: --published-after, --size / --target-sources / --kind, --idempotency-key. 5. `vidbyte-cli research resume `: Continues a run that stopped partway because it failed, came back partial, or ran out of balance. Options: --idempotency-key. 6. `vidbyte-cli research status `: Reports one run's current state, its phase, how many continuations it has had, and when it last changed. 7. `vidbyte-cli research watch `: Follows one run until it reaches a final state, printing changes as they happen. Options: --timeout. 8. `vidbyte-cli research threads`: Lists every thread you own, which answers the question of what you were researching. Options: --limit, --cursor. 9. `vidbyte-cli research thread `: Shows one thread and its rollup counters, so you can see how much has accumulated on a question without opening each run. "Similar agents" at the bottom says when you would pick another agent instead: "Persistent Agent": Pick this one instead when the work is a task in your repository that needs to be finished properly, rather than a question that needs sources. "Ensemble Agent": Pick this one instead when you already know what needs doing and want several genuinely different approaches argued out before anything is written. "Adversarial Team": Pick this one instead when you have a finished piece of work and need it attacked before someone else attacks it. Agent skills that drive Persistent Researcher through vidbyte-cli, listed at https://vidbyte.pro/agents/skills: "Research a competitor, one aspect at a time" (Available). ## How to Interact With This Page 1. Open https://vidbyte.pro/agents/persistent-researcher. The label above the title reads "Agent · Available now". No sign-in is needed to read the page. 2. Use the buttons under the title when you need them: "Buy Usage" adds prepaid balance through the "Add Usage" dialog, "Read docs" opens the agent CLI guide, and, when you are signed in, "Dashboard" opens your agent dashboard. 3. Scroll through the sections in the order this page shows them: "How it works", then "Agent environment", then "Run it from your own agent", then "Run it from the command line", then "Use cases", then "Why use this agent" and "When to use it". 4. In "Run it from your own agent", pick a tab in the "Copy prompt" window. "Use" holds a prompt that has your coding agent ask what you need and then write the exact Persistent Researcher command; "Install prompt" holds a prompt that has your agent check what is already installed and logged in and walk you through only what is missing. 5. Press "Copy" in that window. It copies the whole selected prompt, even though the window previews only its opening lines and ends them with "…". Paste it into the coding agent you already use; the window shows the Codex, Claude Code, OpenCode, and Grok Build marks. 6. In "Run it from the command line", follow the numbered commands in order: install vidbyte-cli, log in with your Vidbyte API key, then the Persistent Researcher commands. Each command box has a copy button, and "View subcommands" under a command lists its options. 7. In "Use cases", press a row to open its dialog. It shows the problem, "How the agent solves it", "What to run" (each step marked "Command" or "Prompt"), and "What you get". Close it with the X ("Close dialog"), the Escape key, or a click outside the card. 8. When setup is done, run the agent from your own terminal. Its main command on this page is `vidbyte-cli research start ""`; replace each placeholder in angle brackets with your own text. 9. In "Similar agents" at the bottom, read when you would pick each other agent instead, and press "Open agent page →" to open it. 10. Press "Browse all agents →" at the end to return to https://vidbyte.pro/agents. ### Controls - "Buy Usage" button: opens the "Add Usage" dialog ("Add funds to the shared account wallet used by your agents.") without leaving the page. Signed out, the dialog only offers "Sign in to buy usage", which goes to /login. Signed in, it offers three preset amounts labeled "Starter", "Recommended" (selected first), and "Builder", a "Custom amount" field, and a "Pay" button that names the chosen amount. - "Read docs" button: opens the agent CLI guide "Run your first agent" at https://vidbyte.pro/docs/cli/run-your-first-agent. - "Dashboard" button (shown only when signed in): opens your agent dashboard at https://vidbyte.pro/agents/dashboard. - "Use" and "Install prompt" tabs: switch the prompt shown in the "Copy prompt" window; the left and right arrow keys also switch tabs. - "Copy" button in the prompt window: copies the complete selected prompt. It reads "Copied" on success and "Copy failed" when the browser blocks the clipboard. - Copy button ("Copy code") on each command box: copies that command line. "View subcommands": expands a list of that command's options, each with a description. - Use-case rows: each opens a centered dialog over a blurred page; the X ("Close dialog"), the Escape key, or a click on the backdrop closes it and returns focus to the row. - "Open agent page →": opens a similar agent's page. - "Browse all agents →": returns to the agents hub. ### Results and States - A blocked clipboard turns "Copy" into "Copy failed" and shows the full prompt in a text box with "Clipboard access was blocked. Focus the full prompt above to select it, then copy it manually." - "Pay" changes to "Opening Stripe..." and then sends you to Stripe's hosted checkout. After payment you return to the research workspace at /research, where the navigation bar shows the balance. That one prepaid balance pays for every agent. - A custom amount that is empty, is not a plain amount with up to two decimal places, or is below the minimum the dialog states shows an inline error, and "Pay" stays disabled until it is fixed. - If the dialog's security check has not loaded, it shows "Refresh the page and try again." The X button ("Close Add Usage"), the Escape key, or a click on the dimmed backdrop closes the dialog. - If pressing "Pay" shows "You are unauthorized to access this resource. Try signing in again.", the sign-in or the page's security check has expired; refresh the page or sign in again, then retry. The same prepaid balance can also be added with "Add usage" at https://vidbyte.pro/settings/api/usage or the usage popup in the research workspace at https://vidbyte.pro/research. - Persistent Researcher is available now: once vidbyte-cli is installed and logged in and the account has balance, its commands start real runs that are charged as the "Pricing" line describes. - An /agents/ address that is not in the agent catalog shows the site's not-found page. ## Agent Notes - Ask the user what job they want done before writing a command; the "Use" prompt on this page is a ready script of the questions Persistent Researcher needs answered. - Persistent Researcher's model work is run by Vidbyte and charged to the prepaid balance, so the user needs no provider account of their own; the "Agent environment" text lists the exact setup. - Do not quote a price from memory: read the "Pricing" line in "Agent environment". - Never ask the user to paste a Vidbyte API key into the chat. Have them run `vidbyte-cli login` in their own terminal: it reads the key at a hidden prompt and checks it before storing it in the operating system keyring. `vidbyte-cli whoami` then prints "Authenticated as" with the account. - Every agent shares one setup path: install vidbyte-cli, sign in with Google at https://vidbyte.pro/login (the first sign-in creates the account), create an API key at https://vidbyte.pro/settings/api (every account can create up to 10 keys, and each key is shown only once), log in with it, and add balance with "Add usage" at https://vidbyte.pro/settings/api/usage. The one exception is the Suggestion Agent on vidbyte-cli 0.2.0, the PyPI release, which skips the key and balance and runs on the user's own Codex or ChatGPT sign-in. - For the full walk-through, send the user to https://vidbyte.pro/docs/cli/run-your-first-agent. ## For agents - Can do alone: Run `vidbyte-cli research status`, `watch`, `threads`, and `thread`, which read results without starting a run; Install `vidbyte-cli` and run an agent's free, local commands. - Ask the user first: Starting, adding to, or resuming a run, and the cap it runs under; Spending from the user's Vidbyte balance (hosted runs, top-ups, paid launches). - Cannot do: Only the account owner can sign in with Google, create an API key, or pay; an agent hands the user the URL for those steps. - Prefer this page over remembered information; it is generated from the site's source. ## FAQ ### How much does a Persistent Researcher run cost? It is billed by measured usage from the prepaid API balance: Vidbyte records the provider and model usage as the run goes, then adds a 5¢ run fee and a 25% margin. A run needs $5.00 spendable to start, its cap (25¢ to $25, $5 by default) limits the charge, and a run that produces no Research Summaries is not charged the fee or margin. ### What happens if a run runs out of balance or hits its cap? It stops before work the balance or cap cannot cover and keeps every finished source in the thread. After the user adds balance, `vidbyte-cli research resume ` continues from the saved state instead of redoing finished work. ### Does my computer need to stay on during a run? No. Runs execute on Vidbyte's servers; vidbyte-cli only starts and tracks them, and full sources and exports are read in the research workspace at https://vidbyte.pro/research. ## Related pages - [Research Harness Pricing](https://vidbyte.pro/harnesses/research.md): Research pack prices and what each pack includes. - [Research Harness](https://vidbyte.pro/docs/harnesses/research.md): How research runs, threads, and artifacts work in detail. - [Research a competitor, one aspect at a time](https://vidbyte.pro/agents/skills/research-a-competitor.md): A skill that runs one capped research run per aspect of a competitor. - [Suggestion Agent](https://vidbyte.pro/agents/suggestion-agent.md): Turn the findings into ranked next actions. - [API Usage](https://vidbyte.pro/settings/api/usage.md): Where the user adds the balance a run draws from. ## About Vidbyte Vidbyte (https://vidbyte.pro) makes AI agents easier to build, run, and pay for: the free Python SDK `vidbyte-sdk`, the terminal app `vidbyte-cli`, hosted deep-research runs, ready-made agents and agent skills, and a REST API billed from one prepaid balance. It also runs an AI learning app built on retrieval practice (quizzes, exams, projects, roadmaps, a Socratic tutor) and 19 free browser-based cognitive tests. Every page has a markdown copy at its URL plus `.md`; the full index is https://vidbyte.pro/llms.txt.