{"id":40890947,"url":"https://github.com/vericle/intellyweave","last_synced_at":"2026-01-31T05:00:46.059Z","repository":{"id":332238510,"uuid":"1114933928","full_name":"vericle/intellyweave","owner":"vericle","description":"AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.","archived":false,"fork":false,"pushed_at":"2026-01-12T14:58:35.000Z","size":37980,"stargazers_count":0,"open_issues_count":11,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-13T04:47:26.557Z","etag":null,"topics":["ai-agents","archival-research","document-processing","dspy","entity-extraction","fastapi","geospatial-visualization","gliner","historical-research","intelligence-analysis","knowledge-graph","mapbox","network-analysis","nextjs","osint","python","rag","typescript","vector-database","weaviate"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vericle.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":"SUPPORT.md","governance":"docs/GOVERNANCE.md","roadmap":"docs/ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":"docs/MAINTAINERS.md","copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-12T05:18:30.000Z","updated_at":"2026-01-12T15:12:29.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/vericle/intellyweave","commit_stats":null,"previous_names":["vericle/intellyweave"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/vericle/intellyweave","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vericle%2Fintellyweave","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vericle%2Fintellyweave/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vericle%2Fintellyweave/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vericle%2Fintellyweave/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vericle","download_url":"https://codeload.github.com/vericle/intellyweave/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vericle%2Fintellyweave/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28929862,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-31T04:05:25.756Z","status":"ssl_error","status_checked_at":"2026-01-31T04:02:35.005Z","response_time":128,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","archival-research","document-processing","dspy","entity-extraction","fastapi","geospatial-visualization","gliner","historical-research","intelligence-analysis","knowledge-graph","mapbox","network-analysis","nextjs","osint","python","rag","typescript","vector-database","weaviate"],"created_at":"2026-01-22T02:00:21.651Z","updated_at":"2026-01-31T05:00:46.051Z","avatar_url":"https://github.com/vericle.png","language":"Python","funding_links":[],"categories":["[↑](#-table-of-contents) Other Tools","Data Analysis"],"sub_categories":["[↑](#-table-of-contents) GitHub"],"readme":"# IntellyWeave\n\n\u003cdiv align=\"center\"\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/demos/rat-lines/images/header.png\" alt=\"IntellyWeave - OSINT Intelligence Platform\" width=\"600\"\u003e\n\u003c/p\u003e\n\n[![License](https://img.shields.io/badge/License-BSD_3--Clause-blue.svg)](LICENSE)\n![Project Status](https://img.shields.io/badge/status-beta-orange)\n[![Built on Elysia](https://img.shields.io/badge/built%20on-Weaviate%20Elysia-green)](https://github.com/weaviate/elysia)\n[![GitHub stars](https://img.shields.io/github/stars/vericle/intellyweave.svg?style=social\u0026label=Star)](https://github.com/vericle/intellyweave)\n\n\u003c/div\u003e\n\n**AI-powered OSINT platform that transforms document chaos into actionable intelligence through entity extraction, geospatial analysis, archive discovery, and hypothesis-driven investigation.**\n\n---\n\n[Quick Start](docs/getting-started/index.md) | [Installation](docs/getting-started/installation.md) | [Feature Guides](docs/guides/entity-extraction/index.md) | [Live Demo](https://app.supademo.com/embed/cmizklvt10rwr14g48e8zgl73)\n\n---\n\n## What is IntellyWeave?\n\nIntellyWeave is an **Open-Source Intelligence (OSINT) analysis platform** that automatically extracts entities from documents, visualizes relationships on maps and network graphs, and employs multiple AI agents that debate complex questions to deliver well-reasoned answers with source citations.\n\nUpload your documents. Ask questions in natural language. Get intelligence.\n\n## Mission\n\nIntellyWeave democratizes intelligence analysis by making professional-grade OSINT workflows accessible through AI automation. We eliminate the manual labor of entity extraction, relationship mapping, and geographic analysis—transforming months of work into minutes.\n\n## Who Should Use This?\n\n**IntellyWeave is for teams who need to:**\n\n- **Intelligence Analysts** — Conduct OSINT research, connect disparate sources, build comprehensive assessments\n- **Historical Researchers** — Explore archives, declassified documents, and primary sources for patterns and narratives\n- **Investigators** — Track entities across documents, piece together evidence, build case narratives\n- **Research Professionals** — Extract structured data from unstructured sources, discover non-obvious relationships\n\n## Scope\n\n### In Scope\n\n- Automatic entity extraction (persons, organizations, locations, dates, events, laws, cryptonyms)\n- Geospatial visualization with interactive 3D maps\n- Network relationship analysis and graph visualization\n- Archive discovery and hypothesis-driven investigation (Quartermaster + Case Officer)\n- Multi-agent reasoning for complex analytical questions\n- Multi-format document processing (PDF, DOCX, TXT, Markdown)\n- Multi-provider LLM support (OpenAI, Anthropic, Google, local models)\n\n### Out of Scope\n\n- Legal case analysis (that's [Spectre's](https://github.com/Siddharth-Khattar/specter-backend) domain)\n- Real-time surveillance or monitoring\n- Automated decision-making without human review\n\n## Key Features\n\n### Entity Extraction (GLiNER)\n\nAutomatic identification of 7 entity types from multilingual documents using zero-shot recognition. No training required.\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/guides/entity-extraction/images/01_intelligence_entity_extractor.png\" alt=\"Entity Extractor - GLiNER Analysis\" width=\"700\"\u003e\n\u003c/p\u003e\n\n*Entity Extractor identifying key persons with 92% confidence, enriched with contextual analysis and follow-up suggestions.*\n\n| Entity Type | Examples |\n|-------------|----------|\n| Persons | Klaus Barbie, Josef Mengele |\n| Organizations | Vatican, CIA, ODESSA |\n| Locations | Buenos Aires, Rome, Damascus |\n| Dates | May 1945, 1960s |\n| Events | Nuremberg Trials |\n| Laws | Decreto-Lei 7967/1945 |\n| Cryptonyms | Operation Paperclip |\n\n[Entity Extraction Guide](docs/guides/entity-extraction/index.md)\n\n### Geospatial Intelligence\n\nInteractive 3D maps powered by Mapbox GL. Plot extracted locations, visualize routes, explore geographic patterns.\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/guides/geospatial-mapping/images/03_intelligence_geospatial_analyst.png\" alt=\"Geospatial Analyst - Location Intelligence\" width=\"700\"\u003e\n\u003c/p\u003e\n\n*Geospatial Analyst extracting operational locations with coordinates, route data, and strategic intelligence assessments.*\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/guides/geospatial-mapping/images/mapbox-view.png\" alt=\"Mapbox Heatmap Visualization\" width=\"700\"\u003e\n\u003c/p\u003e\n\n*Interactive Mapbox heatmap showing location intensity across Italy—key embarkation points for transatlantic escape routes.*\n\n[Geospatial Mapping Guide](docs/guides/geospatial-mapping/index.md)\n\n### Network Analysis\n\nRelationship graphs with physics-based layouts using vis-network. Discover hidden connections between entities.\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/guides/network-analysis/images/network-fullscreen.png\" alt=\"Network Graph - Relationship Visualization\" width=\"700\"\u003e\n\u003c/p\u003e\n\n*Force-directed network graph revealing the rat lines organization: persons (orange), organizations (green), and locations (blue) with documented relationship edges.*\n\n[Network Analysis Guide](docs/guides/network-analysis/index.md)\n\n### Archive Research\n\nTwo-agent investigative system for archival discovery and hypothesis-driven research:\n\n| Agent | Role |\n|-------|------|\n| **Quartermaster** | Maps the information landscape—discovers archives, classifies access levels, identifies digitization status |\n| **Case Officer** | Conducts the investigation—tests hypotheses, gathers evidence, synthesizes reports with actionable next steps |\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/guides/archive-research/images/hypotheses-list.png\" alt=\"Archive Research - Hypothesis Testing\" width=\"700\"\u003e\n\u003c/p\u003e\n\n*Case Officer generates structured hypotheses with evidence tracking: Confirmed (85%), Indeterminate (45%), Pending, or Refuted—each with supporting and contradicting evidence.*\n\n**Key capabilities:**\n- Curated archive sources (30+ institutions across 10 geographic regions)\n- Access level classification (Public, Subscription, Physical-Only, Restricted)\n- Hypothesis generation with confidence scoring and evidence citations\n- Step-by-step access instructions for restricted archives\n- Intelligent PDF preview with AI-inferred schema\n- Documents flagged for manual review with rich metadata for follow-up\n\n[Archive Research Guide](docs/guides/archive-research/index.md) | [Configuration Guide](docs/guides/archive-research/configuration.md)\n\n### Intelligence Orchestrator\n\nAutomated 6-phase analysis pipeline that transforms uploaded documents into comprehensive intelligence assessments with actionable follow-up tasks:\n\n| Phase | Agent | Output |\n|-------|-------|--------|\n| **1. Extraction** | Entity Extractor | Persons, organizations, locations, dates, events, laws, cryptonyms |\n| **2. Mapping** | Relationship Mapper | Entity connections with relationship types and confidence scores |\n| **3. Geospatial** | Geospatial Analyst | Location coordinates, routes, movement patterns |\n| **4. Network** | Network Analyst | Graph structures, centrality metrics, cluster detection |\n| **5. Patterns** | Pattern Detector | Cross-document correlations, temporal sequences, anomalies |\n| **6. Synthesis** | Synthesizer | Executive summary, key findings, unresolved questions |\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/guides/ticket-display/images/task-list-overview.png\" alt=\"Intelligence Orchestrator - Task Generation\" width=\"700\"\u003e\n\u003c/p\u003e\n\n*Intelligence Orchestrator generates follow-up investigation tasks from each analysis phase—color-coded by originating agent with priority indicators (High, Medium) and status tracking.*\n\n**Key capabilities:**\n- Automatic task generation from each analysis phase\n- Priority-weighted investigation queue\n- Provenance tracking (which agent generated each finding)\n- Confidence accumulation across phases\n- Executive summary with evidence citations\n\n[Intelligence Analysis Guide](docs/guides/intelligence-analysis/index.md) | [Ticket Display Guide](docs/guides/ticket-display/index.md)\n\n### LLM Support\n\nMulti-provider support including OpenAI, Anthropic Claude, Google Gemini, and local models via Ollama. Configurable reasoning effort controls for complex analysis tasks.\n\n[LLM Configuration Guide](docs/guides/llm-configuration/index.md)\n\n### IntellyWeave CLI\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/architecture/images/ai-powered-cli.jpg\" alt=\"IntellyWeave CLI - AI-Powered Operations\" width=\"700\"\u003e\n\u003c/p\u003e\n\n**Operations backbone for IntellyWeave**—manage Weaviate databases, migrate data, configure archives, and query with AI from the command line.\n\n| Capability | Description |\n|------------|-------------|\n| **Weaviate Management** | Collections, objects, hybrid search, stats |\n| **Data Migration** | Export/import with mutation safety (`--live` flag) |\n| **Archive Configuration** | Add sources for [Quartermaster](docs/guides/archive-research/configuration.md) |\n| **AI Shell** | Natural language queries with Claude + MCP integration |\n\n```bash\n# Clone and start interactive shell\ngit clone https://github.com/vericle/intellyweave-cli.git\ncd intellyweave-cli \u0026\u0026 npm install \u0026\u0026 npm run dev shell\n```\n\n[CLI Documentation](docs/architecture/cli.md) | [GitHub Repository](https://github.com/vericle/intellyweave-cli)\n\n---\n\n## See It In Action\n\n### Nazi Rat Lines Demo\n\nExplore how IntellyWeave analyzes 17 historical documents to uncover Nazi escape networks to South America (1945-1962).\n\n[![Launch Demo](docs/demos/rat-lines/images/header.png)](https://app.supademo.com/embed/cmizklvt10rwr14g48e8zgl73)\n\n**[Launch Interactive Demo](https://app.supademo.com/embed/cmizklvt10rwr14g48e8zgl73)** — Click through a guided tour without installing anything.\n\n**What you'll discover:**\n- How a single name (Father Draganovic) unravels an entire network\n- Three distinct escape routes from Europe to South America\n- A courthouse debate on whether Brazilian immigration law was exploited\n\n[Full Demo Documentation](docs/demos/rat-lines/index.md) | [Step-by-Step Walkthrough](docs/demos/rat-lines/walkthrough.md)\n\n---\n\n## Quick Start\n\n```bash\n# 1. Start local Weaviate\ndocker compose up -d weaviate\n\n# 2. Setup dependencies\nscripts/setup.sh\n\n# 3. Configure API keys\ncp backend/.env.example backend/.env\n# Edit backend/.env with your LLM provider key\n\n# 4. Launch\ncd backend \u0026\u0026 source .venv/bin/activate \u0026\u0026 elysia start\n\n# 5. Open http://localhost:8000\n```\n\n[Detailed Installation Guide](docs/getting-started/installation.md) | [First Query Guide](docs/getting-started/first-query.md)\n\n### Enable Entity Extraction\n\n```bash\ncd backend \u0026\u0026 source .venv/bin/activate\npip install torch --index-url https://download.pytorch.org/whl/cpu\npip install -e \".[ner]\"\n```\n\n---\n\n## Documentation\n\n### Getting Started\n\n| Guide | Description |\n|-------|-------------|\n| [Quick Start](docs/getting-started/index.md) | 5-minute setup |\n| [Installation](docs/getting-started/installation.md) | Detailed configuration |\n| [First Query](docs/getting-started/first-query.md) | Your first analysis |\n\n### Feature Guides\n\n| Guide | Description |\n|-------|-------------|\n| [Entity Extraction](docs/guides/entity-extraction/index.md) | GLiNER (7 entity types) |\n| [Geospatial Mapping](docs/guides/geospatial-mapping/index.md) | Mapbox 3D maps |\n| [Network Analysis](docs/guides/network-analysis/index.md) | vis-network graphs |\n| [Archive Research](docs/guides/archive-research/index.md) | Quartermaster + Case Officer |\n| [Document Processing](docs/guides/document-processing/index.md) | Pipeline \u0026 watchdog |\n| [Courthouse Debate](docs/guides/courthouse-debate/index.md) | Multi-agent reasoning |\n| [Intelligence Analysis](docs/guides/intelligence-analysis/index.md) | 6-phase orchestrator |\n| [LLM Configuration](docs/guides/llm-configuration/index.md) | Multi-provider support |\n| [Agents](docs/guides/agents/index.md) | Domain routing, custom agents |\n\n### Reference\n\n| Document | Description |\n|----------|-------------|\n| [Architecture](docs/architecture/index.md) | System design |\n| [API Endpoints](docs/reference/api-endpoints.md) | REST API |\n| [Environment Variables](docs/reference/environment-variables.md) | Configuration |\n| [CLI Commands](docs/reference/cli-commands.md) | Command line |\n\n---\n\n## Technical Stack\n\n| Layer | Technology |\n|-------|------------|\n| **Backend** | Python 3.12, FastAPI, Weaviate, DSPy, LiteLLM |\n| **Frontend** | Next.js 15, React 18, TypeScript, Tailwind CSS |\n| **CLI** | TypeScript, Commander.js, Vercel AI SDK, MCP |\n| **Entity Extraction** | GLiNER multi-v2.1 (zero-shot NER) |\n| **Geospatial** | Mapbox GL 3.16 with 3D controls |\n| **Network Graphs** | vis-network 10.0.2 with ForceAtlas2 |\n| **LLM Providers** | OpenAI, Anthropic, Google, Ollama |\n\n---\n\n## Support\n\n- **[GitHub Issues](https://github.com/vericle/intellyweave/issues)** — Bug reports and feature requests\n- **[GitHub Discussions](https://github.com/vericle/intellyweave/discussions)** — Questions and community discussion\n\n## Contributing \u0026 Governance\n\n| Document | Description |\n|----------|-------------|\n| [Contributing Guide](CONTRIBUTING.md) | How to contribute |\n| [Code of Conduct](CODE_OF_CONDUCT.md) | Community standards |\n| [Security Policy](SECURITY.md) | Vulnerability reporting |\n| [Governance](docs/GOVERNANCE.md) | Decision-making process |\n| [Maintainers](docs/MAINTAINERS.md) | Project maintainers |\n| [Roadmap](docs/ROADMAP.md) | Project direction |\n\n---\n\n## License\n\nBSD 3-Clause License — see [LICENSE](LICENSE) for details.\n\n## Acknowledgments\n\nIntellyWeave is built on:\n\n- **[Weaviate Elysia](https://github.com/weaviate/elysia)** — Agentic AI framework with decision tree architecture\n- **[Weaviate](https://weaviate.io/)** — Vector database for semantic search\n- **[Spectre](https://github.com/Siddharth-Khattar/specter-backend)** — Agentic Legal AI system (based on Elysia)\n- **[new/s/leak](https://github.com/uhh-lt/newsleak)** — Open-source investigative journalism platform (Hamburg University, TU Darmstadt, Der Spiegel) — the original inspiration and foundation for IntellyWeave's document analysis capabilities\n- **[GLiNER](https://github.com/urchade/GLiNER)** — Zero-shot named entity recognition\n- **[Mapbox GL](https://www.mapbox.com/)** — Interactive 3D mapping\n- **[vis-network](https://visjs.github.io/vis-network/docs/network/)** — Network graph visualization\n\n---\n\n**IntellyWeave** — Where intelligence meets insight.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvericle%2Fintellyweave","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvericle%2Fintellyweave","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvericle%2Fintellyweave/lists"}