{"id":"79e02076-e698-47b0-aa86-ee6641e3c847","slug":"crewai-saanvijay-pulseai","name":"PulseAI","description":"PulseAI is a multi-agent AI pipeline that turns any topic into a ready-to-publish article or a structured research paper draft — running entirely on local models via CrewAI + Ollama, with optional cloud model support for higher quality output.","canonicalUrl":"https://www.xpersona.co/skill/crewai-saanvijay-pulseai","sourceUrl":"https://github.com/saanvijay/PulseAI","homepage":null,"source":"GITHUB_REPOS","vendor":{"slug":"saanvijay","label":"Saanvijay","url":"https://github.com/saanvijay/PulseAI"},"protocols":["OPENCLEW"],"capabilities":["crewai","multi-agent"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-10-09T23:22:34.969Z","freshnessLabel":"Oct 9, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Oct 9, 2026"},{"label":"Vendor","value":"Saanvijay"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Saanvijay","href":"https://github.com/saanvijay/PulseAI","sourceUrl":"https://github.com/saanvijay/PulseAI","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T23:22:34.975Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/crewai-saanvijay-pulseai/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/crewai-saanvijay-pulseai/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-09T23:22:34.975Z","isPublic":true},{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official domain","href":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceUrl":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceType":"search_document","confidence":"medium","observedAt":"2026-04-15T05:03:46.393Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/crewai-saanvijay-pulseai/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/crewai-saanvijay-pulseai/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Trust evidence available"],"agentCard":{"name":"PulseAI","description":"PulseAI is a multi-agent AI pipeline that turns any topic into a ready-to-publish article or a structured research paper draft — running entirely on local models via CrewAI + Ollama, with optional cloud model support for higher quality output.","source":"GITHUB_REPOS","sourceId":"crewai:1183788927","repository":"https://github.com/saanvijay/PulseAI","documentation":"https://www.xpersona.co/skill/crewai-saanvijay-pulseai/agent/crewai-saanvijay-pulseai","protocols":["OPENCLEW"],"capabilities":["crewai","multi-agent"],"languages":["python"],"install":{"command":"git clone https://github.com/saanvijay/PulseAI.git","ecosystem":"git"},"examples":[{"kind":"example","language":"text","snippet":"Topic (manual / Trend Agent)\n         │\n         ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  Agent 1: Researcher                                            │\n│  Fetches articles via Google News RSS across configured sources │\n│  Scrapes full content for top 10 articles (BeautifulSoup)       │\n│  Retries failed fetches with exponential backoff                │\n└───────────────────────────┬─────────────────────────────────────┘\n                            │ researcher_output.json\n                            ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  Agent 2: Analyst                                               │\n│  CrewAI + Ollama reads full article content                     │\n│  → Produces a structured technical report (content-driven       │\n│    headings, not a fixed template)                              │\n└───────────────────────────┬─────────────────────────────────────┘\n                            │ analyst_output.json\n                            ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  Agent 3: Synthesizer                                           │\n│  Queries 5 local Ollama models IN PARALLEL:                     │\n│    Llama 3.2  ·  Mistral  ·  Qwen 2.5  ·  Phi-3  ·  Gemma 2   │\n│  → Consolidates all responses into one final summary            │\n└───────────────────────────┬─────────────────────────────────────┘\n                            │ synthesizer_output.json\n                            ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  Agent 4: Publisher                                             │\n│  → Displays the final article                                   │\n│  → Download as Markdown or plain text                           │\n│  → Ready to publish on LinkedIn, Medium, or any blog            │\n└─────────────────────────────────────────────────────────────────┘"},{"kind":"example","language":"text","snippet":"Research Gap Agent (optional broad area input)\n         │\n         ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  Research Gap Agent                                             │\n│  Scans recent papers across 5 categories in parallel:           │\n│    cs.AI  ·  cs.LG  ·  cs.CL  ·  cs.CV  ·  stat.ML            │\n│  → Identifies 5 genuine research gaps with descriptions         │\n│  User selects one gap topic                                     │\n└───────────────────────────┬─────────────────────────────────────┘\n                            │ (topic + gap selected)\n                            ▼\n            [Same Agents 1 → 2 → 3 as above]\n                            │ synthesizer_output.json\n                            ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  Agent 4: Paper Writer                                          │\n│                                                                 │\n│  LOCAL MODEL → compact draft (~2-3 pages, 6 sections)          │\n│    Abstract · Introduction · Related Work · Problem Statement   │\n│    Methodology · Discussion · Conclusion · References           │\n│                                                                 │\n│  CLOUD MODEL → full academic paper (~12-15 pages, 9 sections)  │\n│    Abstract · Keywords · Introduction · Background              │\n│    Related Work · Problem Formulation · Methodology             │\n│    Experimental Setup · Results · Discussion · Conclusion       │\n│    References (15-20 entries)                                   │\n│                                                                 │\n│  → A starting point — you do the real research & experiments    │\n│  → Download as Markdown or plain text                           │\n└─────────────────────────────────────────────────────────────────┘"}]}}