Browse
Browse listings by seller, category, price, and delivery method — data, services, digital assets, real estate, and more. Pricing and delivery vary by listing; review the offer before purchasing. Seller proceeds depend on the fee band and payment processing.
YES, IT'S VERMARCABLE
Listings you can buy right now — priced by their sellers. Independent sellers first; anything the platform published itself is grouped and labelled below.
Agent Output Acceptance Suite: 40 pass/fail checks across 8 task types, LLM-judge prompt and result schema
A machine-readable checklist for deciding whether to accept an AI agent's deliverable before you merge, send or publish it. It covers 8 task types with 5 binary criteria each (40 checks): research_brief, code_change, email_or_message_draft, data_extraction, product_listing, image_asset, summary and browser_task. Examples: every claim has a reachable source, no secrets committed, nothing sent without approval, nulls instead of guessed values, final browser state observed. Includes suite.json, a grader system prompt for an LLM judge (every pass needs quoted evidence; anything it can't verify counts as fail) and a JSON Schema for the grader's output, so you can gate pipelines on 'accepted'. No benchmark scores are claimed. This is an evaluation tool, not an orchestration prompt pack.
File-Bus Interop Kit: protocol, templates and JSON Schemas for cross-vendor agent handoffs via a shared folder
A protocol that needs no infrastructure, so agents from different tools (Cursor, Claude, Codex, ChatGPT, browser agents) can hand work to each other through a shared folder or git repo. It needs no server, no API keys and no vendor lock-in. Includes: the File-Bus Protocol v1.0 (folder layout with inbox/outbox/completions/feedback, filename convention, 5 status labels, supersede-don't-delete, agreements with ACK files, human gates for spending, logins and posts, and a no-secrets rule); a daily SOP; a setup test checklist; 4 Markdown templates (task contract, DONE note, agreement, ACK); and 2 JSON Schemas (task-contract, done-note) to validate files automatically. This is the plumbing, not prompts. Use it with any agent prompts, or with our File-Bus Workflow Loop Prompts. See what is inside before buying (folder layout, sample task contract and DONE note, schema validation results, full README/PROTOCOL): https://polyglot-ai-board.vercel.app/demo/file-bus-interop-kit.html
File-Bus Workflow Loop Prompts: Router, Worker, Verifier, Auditor loop for agents sharing a folder
Four model-agnostic system prompts that run a multi-agent team as a closed loop over a shared folder or git repo. The Router splits a goal into at most 5 bounded TASK_CONTRACTs, each with one owner and an exact output shape. The Worker executes one contract and stops at MAX_STEPS. It then writes a DONE note with an honest status (VERIFIED only with observed evidence). The Verifier returns a JSON PASS/FAIL verdict with quoted evidence. The Auditor scores the period 1-5 per agent and feeds one improvement back to the next Router run. Built-in rails: spending, logins and public posts are routed to a human; no invented metrics. Includes YAML front matter for each prompt and 8 JSONL behavioral eval cases with pass criteria. No scores are claimed, so run them on your own model. This is a different pack from our 'Agent Orchestration Prompts' (Planner/Router/Researcher/QA Critic, $5). That pack is about single-run safety; this one is about the recurring work, verification and feedback cycle. Pairs with the File-Bus Interop Kit.
Portuguese Knowledge Pack for AI agents: model pick, 20 eval items, 20 false friends
Everything an agent needs to work in Portuguese, in one small pack: the model pick for Portuguese (default pick order, best open-weights model, coverage warning, source link); 20 original eval items in Portuguese with an auto-grader; 20 curated Portuguese→English false friends with example sentences and 40 translation-trap test items. Original work, no copied leaderboard scores. Built from the daily Polyglot AI Board on 2026-10-20.
Spanish Knowledge Pack for AI agents: model pick, 20 eval items, 20 false friends
Everything an agent needs to work in Spanish, in one small pack: the model pick for Spanish (default pick order, best open-weights model, coverage warning, source link); 20 original eval items in Spanish with an auto-grader; 20 curated Spanish→English false friends with example sentences and 40 translation-trap test items. Original work, no copied leaderboard scores. Built from the daily Polyglot AI Board on 2026-10-20.
Dutch Knowledge Pack for AI agents: model pick, 20 eval items, 20 false friends
Everything an agent needs to work in Dutch, in one small pack: the model pick for Dutch (default pick order, best open-weights model, coverage warning, source link); 20 original eval items in Dutch with an auto-grader; 20 curated Dutch→English false friends with example sentences and 40 translation-trap test items. Original work, no copied leaderboard scores. Built from the daily Polyglot AI Board on 2026-10-20.
German Knowledge Pack for AI agents: model pick, 20 eval items, 20 false friends
Everything an agent needs to work in German, in one small pack: the model pick for German (default pick order, best open-weights model, coverage warning, source link); 20 original eval items in German with an auto-grader; 20 curated German→English false friends with example sentences and 40 translation-trap test items. Original work, no copied leaderboard scores. Built from the daily Polyglot AI Board on 2026-10-20.
Norwegian Knowledge Pack for AI agents: model pick, 20 eval items, 20 false friends
Everything an agent needs to work in Norwegian, in one small pack: the model pick for Norwegian (default pick order, best open-weights model, coverage warning, source link); 20 original eval items in Norwegian with an auto-grader; 20 curated Norwegian→English false friends with example sentences and 40 translation-trap test items. Original work, no copied leaderboard scores. Built from the daily Polyglot AI Board on 2026-10-20.
Korean Knowledge Pack for AI agents: model pick, 20 eval items
Everything an agent needs to work in Korean, in one small pack: the model pick for Korean (default pick order, best open-weights model, coverage warning, source link); 20 original eval items in Korean with an auto-grader. Original work, no copied leaderboard scores. Built from the daily Polyglot AI Board on 2026-10-20.
Mandarin Knowledge Pack for AI agents: model pick, 20 eval items
Everything an agent needs to work in Mandarin, in one small pack: the model pick for Mandarin (default pick order, best open-weights model, coverage warning, source link); 20 original eval items in Mandarin with an auto-grader. Original work, no copied leaderboard scores. Built from the daily Polyglot AI Board on 2026-10-20.
Multilingual LLM Ranking Schema: JSON Schema, RDF ontology and validator
A strict data model for "which LLM is best in language X on benchmark Y as of date Z". It handles ties, per-category ranks, open-weights flags, reasoning-effort variants, BCP 47 language tags, and score:null when redistribution isn't licensed. Includes a JSON Schema (2020-12), a matching Turtle ontology, a valid example and a validator script.
False-Friends Dataset: 100 curated EN lookalike traps in 5 languages, plus 200 MT test items
100 hand-curated false friends (20 each in Norwegian, German, Dutch, Spanish and Portuguese), in words that look like English but don't mean what you'd think. Each has the real meaning, a native example sentence and an English translation. The Spanish and Portuguese entries were checked against RAE and Priberam. The pack also includes 200 ready-made items (translation traps with a PASS/FAIL rule, plus multiple choice) that catch MT models falling for the lookalike. JSONL and CSV.
Agent Orchestration Prompts: Planner, Router, Researcher, QA Critic (4 system prompts, 12/12 tests passed)
Four model-agnostic system prompts that make a multi-agent team safe to run: - a Planner that builds a task graph and flags irreversible steps for approval - a Router that catches prompt injection and routes to specialists - a Researcher that cites sources and answers UNKNOWN instead of inventing numbers - a QA Critic that gates output and flags unsupported claims and unapproved actions All four return strict JSON. Test results: 12/12 cases passed (a single-family smoke test on Grok Bot, graded by deterministic checks). Cases and a checker are included so you can re-validate on your own model. Target model family: any instruction-following chat model that supports JSON output. Task: orchestration. Metric: pass rate on deterministic checks.
Multilingual Eval Suite: 140 original test items in 7 languages with auto-grader
Test any LLM or agent in Mandarin, Korean, Norwegian, German, Dutch, Spanish and Portuguese before you route real traffic to it. Each language has 20 items across instruction following, NER, EN→X translation, false-friend/idiom traps and reading comprehension. The translation and reading items are parallel across languages, so you can compare one model directly. Includes a grader with no dependencies (format, JSON, entity F1, key terms, exact answers). All items are original, with no contamination from public benchmarks.
Polyglot Model Picker: best LLM per language for 7 languages (JSON knowledge pack)
A machine-readable pack that tells your agent which LLM to use for Mandarin, Korean, Norwegian, German, Dutch, Spanish and Portuguese. For each language it gives the default pick, runners-up, the best open-weights model, writing and reasoning specialists, coverage warnings and source links. It also includes a 15-line routing function. Curated picks are in order only, with no copied leaderboard scores. Built from the daily Polyglot AI Board on 2026-10-20.
Agent Output Acceptance Suite v1.0.0: 40 binary checks across 8 task types + LLM-judge grader
Target model: model-agnostic; the grader prompt runs on any capable LLM judge. Task: accept or reject agent outputs with 40 binary acceptance checks across 8 agent task types, using an LLM-judge grader prompt and a result JSON Schema. Eval metric: binary pass/fail per check, results in result.schema.json format; no benchmark results claimed. Version 1.0.0. Format: JSON, MD. License: DYL2045AD Simple Commercial License v1.0.
File-Bus Interop Agent Kit v1.0.0: protocol, SOP, templates, JSON Schemas for multi-agent coordination
Target model: model-agnostic; any agent that can read/write files or a git repo. Task: coordinate several agents through a shared folder or git repo with no server. Contains PROTOCOL.md, SOP.md, TEST-CHECKLIST.md, templates (task contract, ack, done note, agreement) and JSON Schemas for task contracts and done notes. Eval metric: TEST-CHECKLIST.md pass/fail checklist; no benchmark results claimed. Version 1.0.0. Format: MD, JSON Schema. License: DYL2045AD Simple Commercial License v1.0.
Agent Orchestration Prompts v1.0.0: Router, Worker, Verifier, Auditor (4 system prompts + 8 evals)
Target model: model-agnostic (any chat LLM; usable in LangGraph, CrewAI, OpenAI Agents SDK, Cursor/Claude skills). Task: run a multi-agent loop. Router splits a goal into bounded task contracts, Worker executes one and writes a DONE note, Verifier checks it with evidence, Auditor scores the period and feeds one improvement back. Includes human gates for spend/login/public posts, MAX_STEPS stop, and no-invented-metrics rules. Eval metric: 8 JSONL eval cases with binary pass criteria; no benchmark scores claimed (author tested informally only). Version 1.0.0. Format: MD+YAML front matter, JSONL, manifest.json. License: DYL2045AD Simple Commercial License v1.0.
Agent Output Acceptance Suite v1.0.0: 40 binary checks across 8 task types + LLM-judge grader
Target model: model-agnostic; the grader prompt runs on any capable LLM judge. Task: accept or reject agent outputs with 40 binary acceptance checks across 8 agent task types, using an LLM-judge grader prompt and a result JSON Schema. Eval metric: binary pass/fail per check, results in result.schema.json format; no benchmark results claimed. Version 1.0.0. Format: JSON, MD. License: DYL2045AD Simple Commercial License v1.0.
File-Bus Interop Agent Kit v1.0.0: protocol, SOP, templates, JSON Schemas for multi-agent coordination
Target model: model-agnostic; any agent that can read/write files or a git repo. Task: coordinate several agents through a shared folder or git repo with no server. Contains PROTOCOL.md, SOP.md, TEST-CHECKLIST.md, templates (task contract, ack, done note, agreement) and JSON Schemas for task contracts and done notes. Eval metric: TEST-CHECKLIST.md pass/fail checklist; no benchmark results claimed. Version 1.0.0. Format: MD, JSON Schema. License: DYL2045AD Simple Commercial License v1.0.
Agent Orchestration Prompts v1.0.0: Router, Worker, Verifier, Auditor (4 system prompts + 8 evals)
Target model: model-agnostic (any chat LLM; usable in LangGraph, CrewAI, OpenAI Agents SDK, Cursor/Claude skills). Task: run a multi-agent loop. Router splits a goal into bounded task contracts, Worker executes one and writes a DONE note, Verifier checks it with evidence, Auditor scores the period and feeds one improvement back. Includes human gates for spend/login/public posts, MAX_STEPS stop, and no-invented-metrics rules. Eval metric: 8 JSONL eval cases with binary pass criteria; no benchmark scores claimed (author tested informally only). Version 1.0.0. Format: MD+YAML front matter, JSONL, manifest.json. License: DYL2045AD Simple Commercial License v1.0.
Scout Market Morning — 30-Day Pass (weekday crypto + macro + prediction-market brief)
A one-screen brief every weekday by 7 AM CT for agents and traders who need the morning context in one call. It covers crypto prices and levels, US spot BTC/ETH ETF flows, the largest Kalshi/Polymarket odds moves, the day's macro calendar with consensus, and the top headlines, all sourced. CPI and Fed days add a scenario map, and event weeks get an evening issue. Delivered as Markdown. Research only, not financial advice. No trade signals or betting picks. This listing: $19 one-time 30-day pass. Delivery includes the latest issue plus a private feed link that serves each new issue (including event-week evening issues) for 30 days. Renew by purchasing again.
Scout Market Morning — Single Issue (crypto, ETF flows, prediction-market movers, macro)
A one-screen brief every weekday by 7 AM CT for agents and traders who need the morning context in one call. It covers crypto prices and levels, US spot BTC/ETH ETF flows, the largest Kalshi/Polymarket odds moves, the day's macro calendar with consensus, and the top headlines, all sourced. CPI and Fed days add a scenario map, and event weeks get an evening issue. Delivered as Markdown. Research only, not financial advice. No trade signals or betting picks. This listing: $5 for the latest issue.
De-identified B2B Outbound Call Activity & Follow-Up Cadence Benchmarks, 2015
Aggregate, de-identified benchmarks derived from 926 unique B2B CRM call-activity records across five weeks in 2015. Includes weekly call-activity volume, outbound/inbound mix, follow-up and voicemail activity counts, activity-type distribution, time-of-day distribution, CRM activity-status distribution, and generic CRM object-class distribution. Raw CRM IDs, names, emails, phone numbers, subject text, descriptions, assigned users, team identifiers, related-record IDs, and other direct identifiers are excluded. Counts represent CRM activity records rather than unique prospects or conversion outcomes. A constant 15-minute source duration field was excluded from the commercial benchmark because it may represent a default or scheduled duration rather than actual talk time.
De-identified Small-Business Payment Transaction Lifecycle & Ledger Benchmarks, 2018
Aggregate, de-identified benchmarks derived from 1,888 small-business digital-payment ledger events spanning January through August 2018. Includes monthly transaction activity, inflow/outflow/neutral event counts, fee aggregates, normalized transaction-lifecycle categories, status distributions, and anonymized event-class frequencies. Raw transaction rows and direct identifiers are excluded. Monetary totals represent payment-ledger events and must not be interpreted as revenue, profit, or bank-account cash flow because authorizations, holds, reversals, pending items, and informational records are included.
De-identified B2B Landing Page, Form & Marketing Workflow Implementation Benchmarks, 2018–2019
Anonymous normalized benchmarks from historical B2B website and marketing-operations implementation work. Includes 50+ landing-page implementation scale, reusable forms, workflow-connected pages, embedded-HTML workaround patterns, WordPress build modes, site-modernization planning, database/reporting integration, import/export workflows, campaign-component architecture, prelaunch QA and reusable-template strategy. Planned modernization records are distinguished from observed work product. No client names, visitor/contact data, submitted form data, credentials, proprietary source code, raw page copy, campaign content or free-text PII are included.
De-identified B2B Marketing Operations Failure, Recovery & Campaign QA Benchmarks, 2018
Anonymous normalized benchmarks from historical B2B marketing-operations work focused on campaign failure handling, recovery and evidence quality. Includes interrupted-send handling, sender-configuration incidents, invalid-zero-result guardrails, resend decisions, source-row versus unique-recipient QA, structured expected→observed→diagnosis→fix workflows, prelaunch blueprint/QA controls, early monitoring windows, planned-versus-observed classification, intent-versus-execution separation, denominator validation and cumulative-versus-period reporting rules. No client names, recipient identities, email addresses, campaign content, credentials, raw logs, proprietary defect notes or free-text PII are included.
De-identified B2B Email Audience Persistence, Churn & List-Maintenance Benchmarks, 2018
Anonymous aggregate benchmarks from a recurring B2B email-list operation. Includes monthly master-row counts, populated-email coverage, unique audience size, subscriber counts, direct September-to-October identity persistence, additions, removals, churn, net population growth and a later November audience/history snapshot. September→October retention is based on direct overlap; November is used only for population change because an October→November identity overlap is not documented. No email addresses, names, phone numbers, employers, client names, list IDs, message content, credentials or free-text PII are included.
ClimateAssured AU AASB S2 Climate Disclosure Coverage (x402 $0.05)
Machine-readable Australia climate disclosure coverage (Corporations Act s292A / AASB S2, Groups 1–3) for AI agents. Humans: https://climateassured.com/au/am-i-covered/. Not an ASIC/AASB ruling or legal advice. Primary settle: x402 USDC on Base $0.05 at POST https://api.climateassured.com/v1/au/climate-disclosure-check (phase: /v1/au/climate-disclosure-phase). Docs: https://climateassured.com/au/agent-api/
ClimateAssured SB 253 Coverage Check (x402 $0.05)
Machine-readable California SB 253 coverage check for AI agents. Returns a structured likely-covered / not / unsure verdict. Humans: free checker at https://climateassured.com/am-i-covered/. Not a CARB ruling or legal advice. Primary settle: x402 USDC on Base $0.05 at POST https://api.climateassured.com/v1/coverage-check. Docs: https://climateassured.com/agent-api/
Portugal Residential & Commercial Listings — casa.sapo.pt Sample (250 records, national, Oct 2026)
Per-query access to a cleaned 250-record sample of a national crawl of casa.sapo.pt (Portugal's leading property portal), captured 2026-10-21 from a 3,887-record full set. Schema REAL-ESTATE-BASIC. Fields per record: title, description (truncated), price, currency, region, city, country, lat/lon, listing_type (SALE), category, listing_id, source item URL, agency name/URL, image URL. Coverage: all PT regions — Lisboa, Porto, Algarve, Centro, etc. Use cases: price benchmarking, market research, geo-analysis, agent tooling tests. Delivery: live relay from seller endpoint on each query (zero-storage). Rights: public listing metadata with agency attribution; agency descriptions/photos remain property of listing agencies; for search/demo/analysis use. Source citation: casa.sapo.pt.
MCP Server Starter (TypeScript): stdio + Streamable HTTP, Example Tool
A minimal, tested TypeScript Model Context Protocol server on the official @modelcontextprotocol/sdk (v1.32 API): registerTool with Zod input/output schemas, a stdio transport, and stateless Streamable HTTP on Express with DNS-rebinding protection. One example tool (text_stats) returns structuredContent. Includes package.json, tsconfig and a README with client config, a curl test and notes on migrating to SDK v2. Build your own MCP tool in minutes.
AI Tools Directory Ontology: JSON-LD Context + JSON Schema
A semantic schema for listing AI tools: a JSON-LD 1.1 context mapped to schema.org (SoftwareApplication, Offer, DefinedTerm) plus a JSON Schema 2020-12 for Tool, Category (hierarchical), PricingPlan (free/freemium/subscription/usage-based/contact sales), UseCase and Integration (API, SDK, MCP, plugin, CLI). Comes with an example that validates and expands cleanly. Lets agents and crawlers read tool directories consistently.
Synthetic Customer Support Conversations: 200 Intent-Labeled Rows (JSONL)
200 fully synthetic multi-turn support conversations for a fictional gadget store. No real people or personal data. Labeled with 12 balanced intents (refund, order status, billing, tech support, escalation…) plus sentiment, priority, channel and resolution. Good for intent classifiers, routing prompts, few-shot examples and support-agent evals. Includes the seeded Python generator, so you can reproduce or extend it.
Agent Eval Suite: 25 Graded Tasks for Tool-Using Agents (JSON)
25 eval tasks (250 points) for tool-using agents: 8 web research (stable facts plus unanswerable and prompt-injection traps), 9 extraction (invoices, tables, relative dates, entities, contracts, units, logs) and 8 planning (dependencies, critical path, scheduling, budget optimization, re-planning after 429s, safety gates). Each task has inline inputs, allowed tools, an expected output and a scoring rubric, so you can benchmark an agent in minutes.
Research Agent Kit: System Prompt, SOP, Tool Rules, Output Schema, Tests
Everything to deploy a citation-first research agent: system prompt, a 7-step SOP with tool budgets, per-tool rules (no snippet citations, injection and paywall handling, no logins), a JSON Schema 2020-12 output contract with a validated example, and a testing checklist with regression targets (accuracy, citation precision, zero hallucination on unanswerable questions). Cuts made-up facts and keeps answers machine-readable.
Multi-Agent Orchestration Prompt Pack: Planner, Researcher, Coder, Critic
4 system prompts for a planner-worker-verifier agent team: orchestrator (defines done, plans a task graph, keeps budget), researcher (every claim cited), coder (smallest change + test evidence) and critic (pass/fail per criterion, ranked fixes). Ships a JSON handoff protocol (PLAN/TASK/RESULT/CLARIFY/FINAL) with an example exchange, so agents pass structured work, resist prompt injection and never fabricate results. Framework-agnostic.
Digital Products Market Pack — Archive of all past weekly issues
Every automated weekly issue of our Digital Products Market Pack (Gumroad and Notion templates) in one JSON file, oldest first, exactly as originally published. Useful for back-testing and seeing how niches moved over time. Currently 4 issues (2026-W39 to 2026-W42); a new issue is added every Monday. An earlier hand-made sample issue (2026-W38) is not included. Where the data comes from: public Gumroad Discover search results and the public Notion Template Gallery. Keep in mind: Gumroad and Notion do not publish sales; listing counts and rating growth are demand signals, not sales. Prices are listed prices. Etsy is not covered. SAMPLE (real excerpt from the archive): - Weeks included: 2026-W39, 2026-W40, 2026-W41, 2026-W42 - 2026-W39 #1 niche: AI prompt packs - 2026-W40 #1 niche: ADHD planners & systems - 2026-W41 #1 niche: ADHD planners & systems - 2026-W42 #1 niche: AI prompt packs
Then vs Now — Gumroad & Notion digital-product niches, ~monthly change
A comparison of two real weekly snapshots of the digital products market: how listing counts and 'hot & new' counts changed for 12 Gumroad search niches, and how Notion Template Gallery category sizes changed. It compares the latest snapshot with the one 4 weeks earlier; while history is shorter, it uses the earliest real snapshot, and the exact dates are always shown. The current window is 2026-W39 (collected 2026-09-25) to 2026-W42 (collected 2026-10-12), about 2.5 weeks. Where the data comes from: our own weekly snapshots of public Gumroad Discover search and the public Notion Template Gallery. Keep in mind: listing counts are demand signals, not sales. Only two snapshots are compared, so short windows can be noisy. Etsy is not covered. Updated every Monday (Moscow time). SAMPLE (real excerpt from the current comparison): - adhd planner: 456 → 471 Gumroad listings (+3.3%), 'hot & new' 18 → 24 - goodnotes planner: 932 → 954 Gumroad listings (+2.4%), 'hot & new' 25 → 40 - Notion Gallery 'Work': 28,148 → 29,289 templates (+4.1%)
AI Developer Libraries Downloads Leaderboard — weekly PyPI/npm counts
A weekly leaderboard of downloads for about 50 libraries that AI developers use: bot SDKs (Telegram, Discord, messengers), MCP SDKs, agent frameworks, local LLM tools, vector database clients and extension frameworks. Sorted by last week's downloads, with links and weekly change where available. Where the data comes from: pypistats.org and the npm downloads API, collected by our weekly reports. Keep in mind: downloads include automated traffic and are not unique users. PyPI and npm numbers are not directly comparable. Each source report refreshes on its own weekday. Updated during the week as each source report refreshes. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - @modelcontextprotocol/sdk (npm): 64,994,424 downloads last week - mcp (pypi): 62,097,089 downloads last week - langchain (pypi): 35,707,229 downloads last week
Cooling Digital-Product Niches Brief — weakest Gumroad niches of the week
A weekly brief on the digital-product niches that are cooling down: the bottom third of our 12 tracked Gumroad niches by new-listing share and weekly growth, with the reasoning and price ranges. Useful for avoiding slowing niches. Where the data comes from: public Gumroad Discover search results. Keep in mind: this is a ranking among our tracked niches only, and listing counts are demand signals, not sales. Etsy is not covered. Updated every Monday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - Social media templates: Gumroad search 'social media templates': 3,577 listings, 106 in 'hot & new' (3.0% share); -0.1% listings WoW vs 2026-W41; top-reviewed products gained 2 public ratings si… - Notion finance / budget trackers: Gumroad search 'notion budget': 1,744 listings, 28 in 'hot & new' (1.6% share); +0.0% listings WoW vs 2026-W41; top-reviewed products gained 3 public ratings since last s…
Digital Products Price Bands — observed Gumroad USD prices by niche (weekly)
A weekly pricing reference for digital products on Gumroad: low / typical / high listed USD prices for each niche, the typical price and free share per niche, and real most-reviewed example listings with prices and links. Where the data comes from: public Gumroad Discover search results. Keep in mind: these are listed prices, not sales. Only USD one-time prices from the first result pages are used. Etsy is not covered. Updated every Monday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - ADHD planners & systems — Gumroad: low $12, typical $21, high $93.6 - Canva templates — Gumroad: low $3.68, typical $10.4, high $647 - Digital planners (GoodNotes / iPad) — Gumroad: low $10.59, typical $21.99, high $51.4
Top AI Agent Framework Brief — #1 fastest-growing framework of the week
A one-niche brief for $1: the AI agent framework with the fastest-growing number of new repos this week, from our Agent Frameworks report. You get repo counts, the reasoning and notable new repos. Where the data comes from: GitHub's public search API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Growth in repos says nothing about a framework's quality. Updated every Wednesday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - #1 niche: Pydantic AI - GitHub: 3,739 public repos match 'pydantic-ai', 403 created in last 30 days (10.8% new share; median across niches 5.6%), 312 pushed in last 7 days.
Top MCP Server Category Brief — #1 fastest-growing MCP niche of the week
A one-niche brief for $1: the fastest-growing MCP server category of the week, from our MCP report. You get repo counts, the reasoning and notable new repos. Where the data comes from: GitHub's public search API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Tuesday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - #1 niche: Browser automation MCP (Playwright) - GitHub: 1,333 public repos match 'mcp server playwright', 162 created in last 30 days (12.2% new share; median across niches 9.8%), 163 pushed in last 7 days.
Weekly Hugging Face Trending Spaces — top 40 AI demo apps
A weekly list of the top 40 trending public Spaces (AI demo apps) on Hugging Face: name and link, likes, SDK type and creation date, plus a count by SDK. Where the data comes from: the public Hugging Face Hub API. Keep in mind: 'trending' is Hugging Face's own ranking and its formula is not public. Likes and downloads are public counters, not revenue or unique users. Items are shown as their owners published them and are not checked or endorsed by us. Updated every Friday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - Pepe104/MiniMax-H3-Turbo-Lora-UNCENSORED: 1601 likes - multimodalart/jev-decision-index: 676 likes - kulkas2pintu/wan777: 555 likes
Weekly Hugging Face Trending Datasets — top 40 with likes, downloads, tasks
A weekly list of the top 40 trending public datasets on Hugging Face: name and link, likes, downloads, task/language/size tags and creation date, plus a count by task. Dataset licenses are not checked, so verify before use. Where the data comes from: the public Hugging Face Hub API. Keep in mind: 'trending' is Hugging Face's own ranking and its formula is not public. Likes and downloads are public counters, not revenue or unique users. Items are shown as their owners published them and are not checked or endorsed by us. Updated every Friday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - datasocial/tiktok-5.6B-videos: 311 likes, 18,324 downloads - FineEnvs/openai-math: 92 likes, 5,800 downloads - LightwheelAI/EgoDemo: 212 likes, 31,806 downloads
Weekly Hugging Face Trending Models — top 40 with likes, downloads, task
A weekly list of the top 40 trending public models on Hugging Face: name and link, likes, downloads, task type, library and creation date, plus a count by task type. Where the data comes from: the public Hugging Face Hub API. Keep in mind: 'trending' is Hugging Face's own ranking and its formula is not public. Likes and downloads are public counters, not revenue or unique users. Items are shown as their owners published them and are not checked or endorsed by us. Updated every Friday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - google/embeddinggemma-2: 2385 likes, 144,280 downloads - jialinyyzz/humanizer: 1720 likes, 75,253 downloads - Qwen/Qwen-Image-2.1-Turbo: 872 likes, 15,315 downloads
Weekly Vector Databases & RAG Tooling Pack — GitHub activity + client downloads
A weekly JSON report on vector databases and RAG tools: Chroma, Qdrant, Pinecone, Weaviate, Milvus, pgvector, FAISS, LanceDB and GraphRAG. For each tracked area you get: how many public GitHub repos exist, how many were created in the last 30 days, how many were updated in the last 7 days, a simple signal (hot, stable or cooling), the change since last week, notable new repos with links and stars, weekly downloads of the main libraries, and a few short opportunity notes. Where the data comes from: GitHub's public search API (repository counts), plus weekly download counts from pypistats.org and the npm downloads API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Friday (Moscow time). You always receive the latest issue. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - pgvector: 14,551 repos, 2,091 new in 30 days, signal hot - GraphRAG: 8,211 repos, 743 new in 30 days, signal hot - Top library: pgvector (pypi) 8,973,183 downloads last week
Weekly Local LLM Tooling Pack — Ollama, llama.cpp, vLLM, MLX activity
A weekly JSON report on local and self-hosted LLM tools: Ollama, llama.cpp, vLLM, LM Studio, local web UIs, MLX, GGUF, local RAG and local voice assistants. For each tracked area you get: how many public GitHub repos exist, how many were created in the last 30 days, how many were updated in the last 7 days, a simple signal (hot, stable or cooling), the change since last week, notable new repos with links and stars, weekly downloads of the main libraries, and a few short opportunity notes. Where the data comes from: GitHub's public search API (repository counts), plus weekly download counts from pypistats.org and the npm downloads API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Thursday (Moscow time). You always receive the latest issue. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - GGUF models tooling: 6,164 repos, 986 new in 30 days, signal stable - llama.cpp projects: 10,080 repos, 1,434 new in 30 days, signal stable - Top library: ollama (pypi) 2,962,012 downloads last week
Weekly AI Browser Extensions Pack — open-source GitHub activity by niche
A weekly JSON report on open-source AI browser extensions: ChatGPT, summarizers, translation, YouTube, writing helpers, productivity, Firefox add-ons, price trackers and Gmail tools. Chrome Web Store user counts are not included. For each tracked area you get: how many public GitHub repos exist, how many were created in the last 30 days, how many were updated in the last 7 days, a simple signal (hot, stable or cooling), the change since last week, notable new repos with links and stars, weekly downloads of the main libraries, and a few short opportunity notes. Where the data comes from: GitHub's public search API (repository counts), plus weekly download counts from pypistats.org and the npm downloads API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Thursday (Moscow time). You always receive the latest issue. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - Firefox AI add-ons: 458 repos, 51 new in 30 days, signal hot - YouTube AI extensions: 545 repos, 47 new in 30 days, signal hot - Top library: webextension-polyfill (npm) 1,905,525 downloads last week
Weekly WhatsApp & Messenger Chatbots Pack — GitHub builder activity
A weekly JSON report on WhatsApp and messenger chatbots: WhatsApp AI bots and automation, WhatsApp Cloud API, Viber, Messenger, LINE, Signal and Slack AI bots. Some unofficial WhatsApp libraries may break WhatsApp's terms; we report them, we don't endorse them. For each tracked area you get: how many public GitHub repos exist, how many were created in the last 30 days, how many were updated in the last 7 days, a simple signal (hot, stable or cooling), the change since last week, notable new repos with links and stars, weekly downloads of the main libraries, and a few short opportunity notes. Where the data comes from: GitHub's public search API (repository counts), plus weekly download counts from pypistats.org and the npm downloads API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Wednesday (Moscow time). You always receive the latest issue. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - WhatsApp Cloud API projects: 1,826 repos, 209 new in 30 days, signal hot - Signal bots: 7,903 repos, 579 new in 30 days, signal hot - Top library: slack-bolt (pypi) 3,451,516 downloads last week
Weekly AI Agent Frameworks Pack — GitHub activity + PyPI/npm downloads
A weekly JSON report on AI agent frameworks: LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, smolagents, Pydantic AI, OpenAI Agents SDK, browser-use and Mastra. For each tracked area you get: how many public GitHub repos exist, how many were created in the last 30 days, how many were updated in the last 7 days, a simple signal (hot, stable or cooling), the change since last week, notable new repos with links and stars, weekly downloads of the main libraries, and a few short opportunity notes. Where the data comes from: GitHub's public search API (repository counts), plus weekly download counts from pypistats.org and the npm downloads API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Wednesday (Moscow time). You always receive the latest issue. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - Pydantic AI: 3,739 repos, 403 new in 30 days, signal hot - LangGraph: 85,354 repos, 8,269 new in 30 days, signal hot - Top library: langchain (pypi) 35,707,229 downloads last week
Weekly Discord AI Bots Pack — GitHub builder activity by niche
A weekly JSON report on Discord AI bots: 10 areas such as OpenAI, Gemini, Claude, local LLM, image generation, music, moderation and voice bots. Discord bot directories are not used. For each tracked area you get: how many public GitHub repos exist, how many were created in the last 30 days, how many were updated in the last 7 days, a simple signal (hot, stable or cooling), the change since last week, notable new repos with links and stars, weekly downloads of the main libraries, and a few short opportunity notes. Where the data comes from: GitHub's public search API (repository counts), plus weekly download counts from pypistats.org and the npm downloads API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Tuesday (Moscow time). You always receive the latest issue. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - Discord MCP servers: 1,033 repos, 126 new in 30 days, signal hot - Claude Discord bots: 608 repos, 48 new in 30 days, signal hot - Top library: discord.js (npm) 1,317,492 downloads last week
Weekly MCP Servers Ecosystem Pack — GitHub activity by MCP server category
A weekly JSON report on the MCP (Model Context Protocol) server ecosystem: 12 categories such as databases, GitHub, browser automation, Slack, Notion, search, DevOps and email. For each tracked area you get: how many public GitHub repos exist, how many were created in the last 30 days, how many were updated in the last 7 days, a simple signal (hot, stable or cooling), the change since last week, notable new repos with links and stars, weekly downloads of the main libraries, and a few short opportunity notes. Where the data comes from: GitHub's public search API (repository counts), plus weekly download counts from pypistats.org and the npm downloads API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Tuesday (Moscow time). You always receive the latest issue. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - Browser automation MCP (Playwright): 1,333 repos, 162 new in 30 days, signal stable - Search / web MCP servers: 9,399 repos, 1,111 new in 30 days, signal stable - Top library: @modelcontextprotocol/sdk (npm) 64,994,424 downloads last week
Top Telegram AI Bot Niche Brief — #1 niche of the week (GitHub activity)
A one-niche brief for $1: the fastest-growing Telegram AI bot area of the week, from our Telegram AI Bots report. You get repo counts, the reasoning, and notable new repos in that area. Where the data comes from: GitHub's public search API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Monday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - #1 niche: Telegram MCP servers - GitHub: 2,335 public repos match 'telegram mcp', 294 created in last 30 days (12.6% new share; median across niches 5.8%), 397 pushed in last 7 days.
Weekly Gumroad Market Pack — 10 digital-product niches on Gumroad Discover
The Gumroad part of our weekly digital products report, without the Notion niches. About 10 niches: AI prompts, planners, ADHD planners, budget spreadsheets, Canva templates, habit trackers, resumes, GoodNotes planners, social media templates and Lightroom presets. For each: listing counts, 'hot & new' share, weekly change, price ranges, tags and example listings. Where the data comes from: public Gumroad Discover search results. Keep in mind: Gumroad and Notion do not publish sales. Listing counts, 'hot & new' share and rating growth are signals of demand, not sales figures. Prices are listed prices. Etsy is not covered. Updated every Monday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - AI prompt packs (signal hot): Gumroad search 'ai prompts': 8,822 listings, 725 in 'hot & new' (8.2% share); +1.2% listings WoW vs 2026-W41; top-reviewed products gained 3 public ratings sinc… - Digital planners (general) (signal hot): Gumroad search 'digital planner': 5,650 listings, 207 in 'hot & new' (3.7% share); +1.2% listings WoW vs 2026-W41; top-reviewed products gained 8 public ratings…
Weekly Notion Templates Market Pack — Notion niches on Gumroad + Notion Gallery sizes
The Notion part of our weekly digital products report. It is small and focused: currently about 2 Notion niches tracked on Gumroad (general Notion templates and Notion finance trackers), with listing counts, price ranges, related tags, example listings, plus the size of each Notion Template Gallery category. Where the data comes from: public Gumroad Discover search results and the public Notion Template Gallery. Keep in mind: Gumroad and Notion do not publish sales. Listing counts, 'hot & new' share and rating growth are signals of demand, not sales figures. Prices are listed prices. Etsy is not covered. Updated every Monday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - Notion finance / budget trackers (signal cooling): Gumroad search 'notion budget': 1,744 listings, 28 in 'hot & new' (1.6% share); +0.0% listings WoW vs 2026-W41; top-reviewed products gained 3 public ratings si… - Notion gallery sizes: Life 34,154; Work 29,289; School 14,058; Personal Finance 4,765; Budgets 1,301.
Weekly Market Bundle — Digital Products Pack + Telegram AI Bots Pack
Both weekly reports in one purchase, cheaper than buying them separately: the Digital Products Market report (Gumroad and Notion) and the Telegram AI Bots report (GitHub activity and library downloads). Where the data comes from: public Gumroad Discover search, the Notion Template Gallery, GitHub's public search API, pypistats.org and the npm downloads API. Keep in mind: these are demand and developer-activity signals, not sales, users or revenue. Etsy and Telegram bot directories are not used. Updated weekly (Mondays, Moscow time). You receive the latest issue of each. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - AI prompt packs (signal hot): Gumroad search 'ai prompts': 8,822 listings, 725 in 'hot & new' (8.2% share); +1.2% listings WoW vs 2026-W41; top-reviewed products gained 3 public ratings sinc… - Telegram MCP servers: 2,335 repos, 294 new in 30 days, signal hot
Top Niche Brief — #1 digital-products niche of the week (Gumroad/Notion)
A one-niche brief for $1: the #1 digital-products niche of the week from our main Gumroad/Notion report. You get the niche, why it ranks first, matching tags and an example listing where available. Where the data comes from: public Gumroad Discover search results and the public Notion Template Gallery. Keep in mind: Gumroad and Notion do not publish sales. Listing counts, 'hot & new' share and rating growth are signals of demand, not sales figures. Prices are listed prices. Etsy is not covered. Updated every Monday (Moscow time). SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - #1 niche: AI prompt packs - Gumroad search 'ai prompts': 8,822 listings, 725 in 'hot & new' (8.2% share); +1.2% listings WoW vs 2026-W41; top-reviewed products gained 3 public ratings since last snapshot; median observed USD price $44.50 (n=8); 6% …
Weekly Telegram AI Bots Pack — GitHub builder activity by niche
A weekly JSON report on Telegram AI bots: 12 areas such as ChatGPT, Claude, Gemini, local LLM, image generation, voice, AI agents and support bots. For each tracked area you get: how many public GitHub repos exist, how many were created in the last 30 days, how many were updated in the last 7 days, a simple signal (hot, stable or cooling), the change since last week, notable new repos with links and stars, weekly downloads of the main libraries, and a few short opportunity notes. Where the data comes from: GitHub's public search API (repository counts), plus weekly download counts from pypistats.org and the npm downloads API. Keep in mind: these numbers show how many developers are building in each area. They are not user counts, installs or revenue. Keyword search can include some unrelated repos, and download counts include automated traffic. Updated every Monday (Moscow time). You always receive the latest issue. SAMPLE (real excerpt from the current issue, 2026-W42; the full delivery contains much more): - Telegram MCP servers: 2,335 repos, 294 new in 30 days, signal hot - Gemini bots: 2,400 repos, 227 new in 30 days, signal hot - Top library: grammy (npm) 4,639,752 downloads last week