{"id":"0a543bdb-d6e9-49c4-ac8e-5d64310b2fd8","entityType":"agent","slug":"crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa","name":"Business-Analytics-Crew-Multi-Agent-Sales-Analysis-CrewAI","canonicalUrl":"https://www.xpersona.co/agent/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa","canonicalPath":"/agent/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa","generatedAt":"2026-10-10T01:03:50.483Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T19:05:27.400Z","emptyReason":null},"description":"Five-agent CrewAI pipeline that analyzes retail weekly sales — Python computes every figure, the agents narrate. Includes a store-vs-macro driver regression and an honest, data-backed finding. Business Analytics Crew — Multi-Agent Sales Analysis (CrewAI) Overview A multi-agent system, built on CrewAI, that turns raw retail sales data into a structured business report. Five specialised agents work in sequence — validating the data, computing the figures, interpreting them, proposing actions, and compiling the final report — to answer one concrete question: **what actually drives a large retailer's weekly sa","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/EmeraldRiverLanga/Business-Analytics-Crew-Multi-Agent-Sales-Analysis-CrewAI","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/EmeraldRiverLanga/Business-Analytics-Crew-Multi-Agent-Sales-Analysis-CrewAI","kind":"source"}],"safetyScore":66,"overallRank":18.4,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Five-agent CrewAI pipeline that analyzes retail weekly sales — Python computes every figure, the agents narrate. Includes a store-vs-macro driver regression and"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T19:05:27.400Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"crewai","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"multi-agent","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T19:05:27.400Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T19:05:27.394Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T19:05:27.400Z","lastCrawledAt":"2026-10-09T19:05:27.394Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T19:05:27.394Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-10T01:03:50.483Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-emeraldriverlanga-business-analytics-crew-multi-agent-sa/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T19:05:27.400Z","emptyReason":null},"readme":"# Business Analytics Crew — Multi-Agent Sales Analysis (CrewAI)\n\n## Overview\n\nA multi-agent system, built on CrewAI, that turns raw retail sales data into a\nstructured business report. Five specialised agents work in sequence —\nvalidating the data, computing the figures, interpreting them, proposing\nactions, and compiling the final report — to answer one concrete question:\n**what actually drives a large retailer's weekly sales?**\n\nThe project has one governing idea **the agents narrate and reason; they never\ncalculate.** Every figure — KPIs, seasonality, correlations, regression — is\nproduced by deterministic Python (Pandas and scikit-learn) inside tools the\nagents call. The model only puts those exact numbers into words. This keeps the\noutput auditable, the figures cannot drift between runs, and every claim traces\nback to code rather than to the model's arithmetic.\n\n![The deterministic analytics core — the exact figures the agents later narrate, produced by Python before any agent runs.](screenshots/analytics_core_output.PNG)\n\n## Technologies Used\n\n- **Python** — core language\n- **CrewAI** — multi-agent orchestration (Agents, Tasks, Crew)\n- **Pandas / NumPy** — data loading, aggregation, KPIs\n- **scikit-learn** — linear regression for the driver analysis\n- **python-dotenv** — environment-based configuration\n- **OpenRouter** — LLM backend for the agents\n- **VS Code** — development environment\n\n## Setup\n\n### Requirements\n- Python 3.11 or 3.12\n- An OpenRouter API key (free key available at openrouter.ai)\n- The Walmart sales dataset saved as `data/Walmart_Sales.csv`\n\n### Install dependencies\n```bash\npython -m venv .venv\n.venv\\Scripts\\activate          # Windows\npip install -r requirements.txt\n```\n\n### Add your API key\nCopy `.env.example` to `.env` and set your key and model:\n```\nOPENROUTER_API_KEY=your-openrouter-api-key-here\nOPENROUTER_MODEL=openrouter/openai/gpt-4o-mini\n```\n`.env` is listed in `.gitignore`, so the key never reaches the repository. The\nmodel is read from the environment too, so it can be swapped without touching\nthe code.\n\n### Run\n```bash\npython -m src.main\n```\nThe crew runs end to end and writes the report to `output/final_report.md`. The\nexact computed figures are saved separately to `output/analysis.json`.\n\n## Dataset\n\nThe analysis uses the Walmart sales dataset from Kaggle:\nhttps://www.kaggle.com/datasets/9592bb3b3c89493fabab56b4317ae10dbd70e6b66d2d464fb7f08c6a5903556d\n\nIt covers 45 stores across 143 weekly periods (February 2010 – October 2012),\nwith weekly sales alongside store-level temperature, fuel price, CPI,\nunemployment and a holiday flag. Download it and save it as\n`data/Walmart_Sales.csv`.\n\n## Project Structure\n\n```\nbusiness-analytics-crew/\n├── src/\n│   ├── __init__.py\n│   ├── data_loader.py      # Load and validate the CSV\n│   ├── analytics.py        # KPIs, seasonality, holidays, correlations, regression (pure functions)\n│   ├── tools.py            # CrewAI tools wrapping the analytics\n│   ├── agents.py           # The five agents\n│   ├── tasks.py            # The five tasks, wired with context\n│   ├── crew.py             # Assembles the crew\n│   ├── llm.py              # OpenRouter LLM configuration\n│   └── main.py             # Entry point\n├── data/\n│   └── Walmart_Sales.csv   # Dataset (from Kaggle)\n├── output/                 # Generated report + figures (created on run)\n├── screenshots/\n├── .env.example\n├── .gitignore\n├── test_analytics.py       # Unit tests for the analytics functions\n├── requirements.txt\n└── README.md\n```\n\n## How the Pipeline Works\n\nThe five agents run sequentially. Each task passes its result forward through an\nexplicit `context`, so every agent builds on the previous ones' output rather\nthan starting from scratch.\n\n```\n        Walmart_Sales.csv\n               │\n               ▼\n┌──────────────────────────┐\n│ 1. Data Quality Analyst  │  validates structure, reports verified facts\n└────────────┬─────────────┘\n             ▼\n┌──────────────────────────┐   calls the sales_analysis tool\n│ 2. Quantitative Analyst  │   → figures computed in Python, not by the model\n└────────────┬─────────────┘\n             ▼\n┌──────────────────────────┐\n│ 3. Business Insight      │  explains WHY the numbers look as they do\n└────────────┬─────────────┘\n             ▼\n┌──────────────────────────┐\n│ 4. Recommendations       │  turns insights into concrete, realistic actions\n└────────────┬─────────────┘\n             ▼\n┌──────────────────────────┐\n│ 5. Analytics Lead        │  compiles one structured final report\n└──────────────────────────┘\n```\n\n| Agent | Tool | Responsibility |\n|---|---|---|\n| Data Quality Analyst | `data_validation` | Confirm structure and report verified facts before analysis |\n| Quantitative Analyst | `sales_analysis` | Compute every figure - KPIs, seasonality, correlations, regression |\n| Business Insight Specialist | — | Explain why the numbers look the way they do |\n| Recommendations Advisor | — | Turn insights into prioritised, realistic actions |\n| Analytics Lead | — | Compile the validated facts, figures, insights and recommendations |\n\n## Key Design Decisions\n\n### 1. The agents narrate, Python computes\nThe analysis tools run Pandas and scikit-learn and return finished numbers as\nJSON. The agents are instructed never to calculate — they only phrase those\nnumbers and reason about them. This guarantees the figures are exact and that\nevery statement in the report is backed by code, not by the model's arithmetic.\n\n### 2. Five agents, sequential, with explicit context\nEach task declares which prior outputs it depends on via `context=[...]`. The\ninsight agent reasons over the analyst's figures; the coordinator compiles all\nfour upstream results. The flow is deterministic and easy to follow, and the\nhand-off between agents is explicit rather than implicit.\n\n### 3. A driver analysis, not just KPIs\nThe core question is *what drives sales*, so the analytics include a linear\nregression of weekly sales on the external factors — and, separately, on store\nidentity. Reporting the R² of each model is what makes the conclusion defensible\nrather than anecdotal, and the same conclusion is stress-tested with a non-linear\nmodel and with per-store regressions rather than asserted from a single fit.\n\n### 4. Configuration via environment variables\nThe API key and the model name are read from `.env`, never hard-coded. A\ncommitted `.env.example` documents the required structure.\n\n### 5. Pure, testable analytics, separate from the agent layer\nAll computation lives in `analytics.py` as plain functions that take a\nDataFrame and return dictionaries. They can be run and verified without any\nmodel or network — a single source of truth that the agent tools simply wrap.\n\n## Testing\n\nBecause the analytics are pure functions, they are covered by unit tests\n(`test_analytics.py`, run with `pytest`). Deterministic results — totals,\nseasonality, the per-holiday breakdown, the week-by-week Christmas trajectory —\nare asserted against hand-calculated values on a small fixture; the regression\nand per-store functions are checked structurally (correct keys, values in valid\nranges). The suite needs no model or network and runs in seconds.\n\n```bash\npython -m pytest -v\n```\n\n## What the Analysis Found\n\nThe result is the most interesting part, and it runs against the obvious\nhypothesis:\n\n- **Store identity dominates.** A regression on the external factors\n  (temperature, fuel price, CPI, unemployment, holiday flag) explains only\n  **~2.5%** of the variance in weekly sales (R² = 0.025). Adding store identity\n  raises that to **~92%** (R² = 0.92). The conclusion held up under two further\n  checks — a non-linear model and a separate regression within each individual\n  store — where the external factors explained, on average, only about a fifth\n  of the within-store variance, and very unevenly (from a few percent in some\n  stores to over 80% in others). Which store it is matters far more than any\n  economic condition measured here.\n- **Clear Q4 seasonality.** December averages ~$1.28M per store-week versus\n  ~$0.92M in January — about 39% higher.\n- **The holiday \"uplift\" is really one holiday, and the flag misses Christmas.**\n  The headline +7.84% holiday lift is almost entirely Thanksgiving — the Black\n  Friday week, ~+41% over a normal week. The other flagged holidays are flat or\n  negative, and the flagged *Christmas* week actually sells **below** an average\n  week. Breaking the weeks around Christmas down individually explains why: sales\n  build every week to a peak in the un-flagged week ending around 24 December\n  (the single highest week in the data), then fall in the flagged week after\n  Christmas. Relying on the holiday flag alone would miss the biggest sales event\n  of the year entirely.\n\n**Honest caveats.** \"Store identity\" is a proxy for things the dataset does not\ncontain — store size, location, format, catchment. The model shows *that* stores\ndiffer enormously, not *why*; the analysis is associational, not causal. The\nper-holiday figures for Thanksgiving and Christmas rest on only two years (the\ndata ends in October 2012), so they are less robust than the rest.\n\nThe full report generated by the crew is committed at\n[`output/final_report.md`](output/final_report.md).\n\n## Challenges & Solutions\n\n| Problem | Solution |\n|---|---|\n| Dates stored as `DD-MM-YYYY` were parsed incorrectly | Added `dayfirst=True` to `pd.to_datetime()` to prevent a silent day/month swap |\n| Factors on very different scales (CPI ~200, fuel ~3) made coefficients incomparable | Standardised the features so each coefficient is expressed per standard deviation |\n| Risk of the model inventing or mis-computing figures | Tools return computed JSON; agents are instructed to call the tool and never calculate |\n| A single \"holiday uplift\" average hid opposite effects across holidays | Broke holiday weeks down by holiday, then week-by-week around Christmas, revealing the flag lands *after* the real pre-Christmas peak |\n| The coordinator first dropped the Insights and Recommendations sections | The instruction \"introduce no new claims\" was too literal; the task was clarified to require all four sections while still not inventing new numbers |\n\n## Scope and Limitations\n\n- **Linear regression only.** A straight-line model can miss non-linear effects\n  and factor interactions; a factor with little linear signal could still matter\n  in a more complex model.\n- **\"Store identity\" is a proxy, not an explanation.** Without store metadata,\n  the model cannot say what about a store drives its performance.\n- **Associational, not causal.** Correlation and regression describe\n  association; they do not establish cause.\n- **Narration depends on the model.** Phrasing quality varies with the chosen\n  LLM, and free models may rate-limit during a multi-agent run, which is why a\n  cheap, reliable model is the default.\n\n## Key Concepts Demonstrated\n\n- **Multi-agent orchestration** — Agents, Tasks and a sequential Crew with\n  explicit context passing\n- **Separation of computation and narration** — deterministic Python decides the\n  numbers, the LLM only phrases them\n- **Auditable analytics** — every figure traces to code and is saved as JSON\n- **Driver analysis** — a store-vs-macro R² comparison, stress-tested with\n  non-linear and per-store models, not just descriptive KPIs\n- **Configuration via environment variables** — no secrets in source\n- **Honest scoping** — stating clearly what the analysis does and does not\n  establish\n\n## Possible Improvements\n\n- Switch to a hierarchical process with the Analytics Lead as a true manager\n  that delegates dynamically\n- Model the pre-holiday build-up directly with a \"weeks-to-holiday\" feature,\n  instead of relying on the single-week holiday flag\n- Bring in richer store metadata (size, region, format) to explain the 92%\n- Add a small UI to browse the generated report\n","readmeExcerpt":"Business Analytics Crew — Multi-Agent Sales Analysis (CrewAI) Overview A multi-agent system, built on CrewAI, that turns raw retail sales data into a structured business report. Five specialised agents work in sequence — validating the data, computing the figures, interpreting them, proposing actions, and compiling the final report — to answer one concrete question: **what actually drives a large retailer's weekly sa","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"python -m venv .venv\n.venv\\Scripts\\activate          # Windows\npip install -r requirements.txt"},{"language":"text","snippet":"OPENROUTER_API_KEY=your-openrouter-api-key-here\nOPENROUTER_MODEL=openrouter/openai/gpt-4o-mini"},{"language":"bash","snippet":"python -m src.main"},{"language":"text","snippet":"business-analytics-crew/\n├── src/\n│   ├── __init__.py\n│   ├── data_loader.py      # Load and validate the CSV\n│   ├── analytics.py        # KPIs, seasonality, holidays, correlations, regression (pure functions)\n│   ├── tools.py            # CrewAI tools wrapping the analytics\n│   ├── agents.py           # The five agents\n│   ├── tasks.py            # The five tasks, wired with context\n│   ├── crew.py             # Assembles the crew\n│   ├── llm.py              # OpenRouter LLM configuration\n│   └── main.py             # Entry point\n├── data/\n│   └── Walmart_Sales.csv   # Dataset (from Kaggle)\n├── output/                 # Generated report + figures (created on run)\n├── screenshots/\n├── .env.example\n├── .gitignore\n├── test_analytics.py       # Unit tests for the analytics functions\n├── requirements.txt\n└── README.md"},{"language":"text","snippet":"Walmart_Sales.csv\n               │\n               ▼\n┌──────────────────────────┐\n│ 1. Data Quality Analyst  │  validates structure, reports verified facts\n└────────────┬─────────────┘\n             ▼\n┌──────────────────────────┐   calls the sales_analysis tool\n│ 2. Quantitative Analyst  │   → figures computed in Python, not by the model\n└────────────┬─────────────┘\n             ▼\n┌──────────────────────────┐\n│ 3. Business Insight      │  explains WHY the numbers look as they do\n└────────────┬─────────────┘\n             ▼\n┌──────────────────────────┐\n│ 4. Recommendations       │  turns insights into concrete, realistic actions\n└────────────┬─────────────┘\n             ▼\n┌──────────────────────────┐\n│ 5. Analytics Lead        │  compiles one structured final report\n└──────────────────────────┘"},{"language":"bash","snippet":"python -m pytest -v"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"Five-agent CrewAI pipeline that analyzes retail weekly sales — Python computes every figure, the agents narrate. Includes a store-vs-macro driver regression and an honest, data-backed finding. Business Analytics Crew — Multi-Agent Sales Analysis (CrewAI) Overview A multi-agent system, built on CrewAI, that turns raw retail sales data into a structured business report. Five specialised agents work in sequence — validating the data, computing the figures, interpreting them, proposing actions, and compiling the final report — to answer one concrete question: **what actually drives a large retailer's weekly sa","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":455,"uniquenessScore":59,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T19:05:27.400Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T19:05:27.400Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T01:03:50.483Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}