Skip to content

Add GitHub Pages documentation (docs site)#1

Closed
Copilot wants to merge 28 commits into
mainfrom
copilot/add-github-pages-documentation
Closed

Add GitHub Pages documentation (docs site)#1
Copilot wants to merge 28 commits into
mainfrom
copilot/add-github-pages-documentation

Conversation

Copy link
Copy Markdown

Copilot AI commented Oct 8, 2025 •
edited
Loading

Overview

This PR adds comprehensive GitHub Pages documentation for TinyBrain using a docs/ directory structure, enabling the repository owner to easily activate GitHub Pages from the repository settings.

What's Included

Complete Documentation Site (20 Pages)

Core Documentation:

  • Landing Page (docs/index.md) - Project overview, key features, quick start, and navigation guide
  • Getting Started (docs/getting-started.md) - Three installation methods, MCP client configuration, and troubleshooting from README
  • Configuration (docs/configuration.md) - Environment variables (TINYBRAIN_DB_PATH, TINYBRAIN_LOG_LEVEL), database settings (WAL, FTS5, foreign keys), and all Makefile helper targets
  • Architecture (docs/architecture.md) - Complete database schema (10 tables, 3 views), key design principles, server initialization flow from cmd/server/main.go, and performance characteristics
  • Memory Model (docs/memory-model.md) - All memory entry fields, 12 security categories, 10 relationship types, priority/confidence semantics, access tracking, and cleanup operations with parameters

API Documentation:

  • API Overview (docs/api/overview.md) - All 40 MCP tools organized into 8 categories exactly as enumerated in README, with MCP protocol explanation
  • API Examples (docs/api/examples.md) - Curated JSON examples for all major operations sourced from examples/basic_usage.md

Workflow Guides:

  • Security Assessment (docs/workflows/security-assessment.md) - Complete code review workflow with session creation, finding storage, relationship mapping, and progress tracking
  • Penetration Testing (docs/workflows/penetration-testing.md) - Pen-test workflow covering reconnaissance, exploitation, and post-exploitation using repository examples
  • Exploit Development (docs/workflows/exploit-development.md) - Buffer overflow and ROP chain development examples from examples/basic_usage.md

Dataset Documentation:

  • Datasets Index (docs/datasets/index.md) - Enumerates all 7 security datasets (SECURITY_CODE_REVIEW_DATASET.md, MULTI_LANGUAGE_SECURITY_PATTERNS.md, CWE_SECURITY_PATTERNS.md, CWE_LLM_DATASET.json, CWE_TINYBRAIN_INTEGRATION.md, TINYBRAIN_SECURITY_TEMPLATES.md, ENHANCED_LANGUAGE_LIBRARY_PATTERNS.md)
  • CWE Integration (docs/datasets/cwe-integration.md) - Commands and mapping examples from CWE_TINYBRAIN_INTEGRATION.md (load, search, standards mapping)
  • Security Templates (docs/datasets/security-templates.md) - Template usage and commands from TINYBRAIN_SECURITY_TEMPLATES.md

Advanced Features:

  • Advanced Features (docs/advanced-features.md) - Context snapshots, task progress tracking, enhanced memory summarization from ADVANCED_FEATURES.md with performance metrics and future enhancements list

Integration Guides:

  • Cursor Setup (docs/integrations/cursor.md) - Setup steps from CURSOR_SETUP.md (copy rules, configure MCP servers, troubleshooting)
  • AI Assistants (docs/integrations/ai-assistants.md) - Integration phases from AI_ASSISTANT_INTEGRATION.md for Cursor, Cline, and Roo

Contributing & Roadmap:

  • Contributing (docs/contributing.md) - Development setup, code standards, testing requirements from README
  • Roadmap (docs/roadmap.md) - Roadmap checklist items exactly as in README
  • FAQ (docs/faq.md) - Common questions with answers strictly derivable from repository content

Jekyll Configuration

_config.yml - Configured with:

  • just-the-docs theme for clean, professional navigation
  • Logical page ordering: Home → Getting Started → Configuration → Architecture → Memory Model → API → Workflows → Datasets → Advanced Features → Integrations → Contributing → Roadmap → FAQ
  • SEO optimization and GitHub integration

Content Accuracy Guarantees

All content is strictly derived from existing repository materials with no speculative or unverified claims:

✅ Performance Metrics: Only those listed in README (1000 entries/sec creation, 100 searches/sec, 500 relationship queries/sec, 1MB per 10K entries) - clearly marked as "current benchmark figures"

✅ Feature Accuracy:

  • All 40 tools enumerated exactly as in README
  • Embedding generation explicitly labeled as "hash-based placeholder" per repository code comments
  • Test coverage stated as "90%+ test coverage" with advisory note to run go test -cover to verify

✅ No Unverified Claims:

  • No authentication features (noted as future roadmap item only)
  • No multi-user access (noted as future roadmap item only)
  • No encryption claims beyond what's documented
  • No external model integrations beyond "foundation/placeholder" status

✅ Source Verification:

  • README.md - Features, installation, benchmarks, tools
  • ADVANCED_FEATURES.md - Context snapshots, task tracking, performance
  • examples/basic_usage.md - JSON examples, workflows
  • CWE_TINYBRAIN_INTEGRATION.md - CWE integration commands
  • TINYBRAIN_SECURITY_TEMPLATES.md - Security templates
  • CURSOR_SETUP.md - Cursor configuration
  • AI_ASSISTANT_INTEGRATION.md - AI assistant workflows
  • cmd/server/main.go - Server initialization, tool definitions
  • internal/database/database.go - Database schema

How to Enable GitHub Pages

After merging this PR:

  1. Go to Repository Settings → Pages
  2. Under "Build and deployment", select:
    • Source: Deploy from a branch
    • Branch: main
    • Folder: /docs
  3. Click Save

GitHub Pages will automatically build and deploy the documentation. The site will be available at: https://rainmana.github.io/tinybrain

Styling & Structure

  • Consistent Layout: Level-1 heading per page, Table of Contents blocks
  • Code Examples: JSON examples properly fenced with ```json
  • Lists: Bullet lists preferred for readability
  • Standard Markdown: No unsupported embellishments, GitHub-flavored markdown only
  • Navigation: Clean hierarchy with logical grouping

Testing

  • ✅ All files are valid markdown
  • ✅ No existing repository files modified
  • ✅ 20 files created totaling ~6,500 lines
  • ✅ Jekyll configuration validated
  • ✅ Content cross-referenced against source files

Files Changed

_config.yml (new)
docs/index.md (new)
docs/getting-started.md (new)
docs/configuration.md (new)
docs/architecture.md (new)
docs/memory-model.md (new)
docs/advanced-features.md (new)
docs/contributing.md (new)
docs/roadmap.md (new)
docs/faq.md (new)
docs/api/overview.md (new)
docs/api/examples.md (new)
docs/workflows/security-assessment.md (new)
docs/workflows/penetration-testing.md (new)
docs/workflows/exploit-development.md (new)
docs/datasets/index.md (new)
docs/datasets/cwe-integration.md (new)
docs/datasets/security-templates.md (new)
docs/integrations/ai-assistants.md (new)
docs/integrations/cursor.md (new)

Total: 20 files, 6,511 insertions, 0 deletions

This documentation provides a comprehensive, professional resource for TinyBrain users while maintaining strict accuracy by deriving all content from existing repository materials.

Original prompt

Create a comprehensive, modern GitHub Pages documentation ("wiki") for TinyBrain using a docs/ directory so the repository owner can enable GitHub Pages (docs folder) in settings. All content must be strictly derived from existing repository materials (README.md, ADVANCED_FEATURES.md, examples/, datasets, integration guides, Makefile, code comments) without introducing unverified claims.

Deliverables (new files):

  1. _config.yml (root) – Jekyll config using a supported theme (just-the-docs) for clean navigation.
  2. docs/index.md – Landing page: concise overview, key features (as in README), quick start, navigation pointers.
  3. docs/getting-started.md – Installation methods (3 methods from README), basic usage, MCP client configuration, troubleshooting section from README.
  4. docs/configuration.md – Environment variables (TINYBRAIN_DB_PATH, TINYBRAIN_LOG_LEVEL), database notes (WAL, FTS5, foreign keys), Makefile helper targets (dev-setup, db-init, db-reset, docker-build, docker-run, docs, security).
  5. docs/architecture.md – Database schema (tables & views exactly as listed), key design principles, high-level server initialization flow (from cmd/server/main.go), performance considerations (only those stated: creation/search rates & optimization features).
  6. docs/memory-model.md – Memory entry fields (derive from tool usage examples), categories list, relationship types, priority/confidence semantics, access tracking & cleanup operations (cleanup_old/low_priority/unused with parameters inferred from code snippet – do not invent extras).
  7. docs/api/overview.md – Explain MCP conceptually (brief), list all 40 tools EXACTLY as enumerated in README grouped by category.
  8. docs/api/examples.md – Curated JSON examples (create_session, store_memory, search_memories, create_relationship, get_context_summary, cleanup_unused_memories dry-run example, health_check, get_database_stats) sourced from README/examples.
  9. docs/workflows/security-assessment.md – Security code review workflow using examples from examples/basic_usage.md and test_scenarios/*. Emphasize session creation, templates, relationships, progress tracking.
  10. docs/workflows/penetration-testing.md – Pen-test workflow (recon, technique, payload, relationships) using examples already present.
  11. docs/workflows/exploit-development.md – Buffer overflow / ROP chain examples as in examples/basic_usage.md.
  12. docs/datasets/index.md – Enumerate security datasets & template files (SECURITY_CODE_REVIEW_DATASET.md, MULTI_LANGUAGE_SECURITY_PATTERNS.md, CWE_SECURITY_PATTERNS.md, CWE_LLM_DATASET.json, CWE_TINYBRAIN_INTEGRATION.md, TINYBRAIN_SECURITY_TEMPLATES.md, ENHANCED_LANGUAGE_LIBRARY_PATTERNS.md) with one-line descriptions copied/adapted from README lines.
  13. docs/datasets/cwe-integration.md – Pull content (commands & mapping examples) from CWE_TINYBRAIN_INTEGRATION.md (load, search, standards mapping, compliance generation) verbatim where needed.
  14. docs/datasets/security-templates.md – Summaries of template usage & example commands from TINYBRAIN_SECURITY_TEMPLATES.md (session init, storing vulnerabilities/exploits/patterns/recommendations, relationships, report generation, pattern recognition workflow).
  15. docs/advanced-features.md – Context snapshots, task progress tracking, enhanced memory summarization (detailed bullet points from ADVANCED_FEATURES.md), performance section, future enhancements list EXACTLY as in that file (do not add unimplemented claims beyond placeholder embedding mention already in README).
  16. docs/integrations/cursor.md – Setup steps from CURSOR_SETUP.md (copy rules, user template, configure MCP servers, enforced usage, troubleshooting) trimmed for clarity but faithful.
  17. docs/integrations/ai-assistants.md – Consolidate AI assistant integration phases from AI_ASSISTANT_INTEGRATION.md (Cursor, Cline, Roo) and usage commands from AI assistant sections.
  18. docs/contributing.md – Contribution steps and development setup taken from README, plus mention of security/lint/test targets.
  19. docs/roadmap.md – Copy roadmap checklist items exactly as in README.
  20. docs/faq.md – Provide a short FAQ with answers strictly derivable (e.g., Where is data stored? (default path), How to reset DB? (db-reset), How to check health? (health_check), Is semantic search fully implemented? (embedding generation is a placeholder per repository code comment)).

Accuracy Constraints:

  • Performance metrics: only those listed (creation/search/relationship queries & size estimates). Mark clearly as current benchmark figures from README.
  • Do NOT add claims about authentication, multi-user access (future item only appears in roadmap), encryption, or external model integrations beyond “foundation” / “placeholder” as stated.
  • Embedding generation: clearly label as placeholder (hash-based) referencing repository code comment.
  • Test coverage: README states “90%+ test coverage”; include that phrasing but italicize an advisory note suggesting users run `go te...
*This pull request was created as a result of the following prompt from Copilot chat.* > Create a comprehensive, modern GitHub Pages documentation ("wiki") for TinyBrain using a docs/ directory so the repository owner can enable GitHub Pages (docs folder) in settings. All content must be strictly derived from existing repository materials (README.md, ADVANCED_FEATURES.md, examples/, datasets, integration guides, Makefile, code comments) without introducing unverified claims. > > Deliverables (new files): > > 1. _config.yml (root) – Jekyll config using a supported theme (just-the-docs) for clean navigation. > 2. docs/index.md – Landing page: concise overview, key features (as in README), quick start, navigation pointers. > 3. docs/getting-started.md – Installation methods (3 methods from README), basic usage, MCP client configuration, troubleshooting section from README. > 4. docs/configuration.md – Environment variables (TINYBRAIN_DB_PATH, TINYBRAIN_LOG_LEVEL), database notes (WAL, FTS5, foreign keys), Makefile helper targets (dev-setup, db-init, db-reset, docker-build, docker-run, docs, security). > 5. docs/architecture.md – Database schema (tables & views exactly as listed), key design principles, high-level server initialization flow (from cmd/server/main.go), performance considerations (only those stated: creation/search rates & optimization features). > 6. docs/memory-model.md – Memory entry fields (derive from tool usage examples), categories list, relationship types, priority/confidence semantics, access tracking & cleanup operations (cleanup_old/low_priority/unused with parameters inferred from code snippet – do not invent extras). > 7. docs/api/overview.md – Explain MCP conceptually (brief), list all 40 tools EXACTLY as enumerated in README grouped by category. > 8. docs/api/examples.md – Curated JSON examples (create_session, store_memory, search_memories, create_relationship, get_context_summary, cleanup_unused_memories dry-run example, health_check, get_database_stats) sourced from README/examples. > 9. docs/workflows/security-assessment.md – Security code review workflow using examples from examples/basic_usage.md and test_scenarios/*. Emphasize session creation, templates, relationships, progress tracking. > 10. docs/workflows/penetration-testing.md – Pen-test workflow (recon, technique, payload, relationships) using examples already present. > 11. docs/workflows/exploit-development.md – Buffer overflow / ROP chain examples as in examples/basic_usage.md. > 12. docs/datasets/index.md – Enumerate security datasets & template files (SECURITY_CODE_REVIEW_DATASET.md, MULTI_LANGUAGE_SECURITY_PATTERNS.md, CWE_SECURITY_PATTERNS.md, CWE_LLM_DATASET.json, CWE_TINYBRAIN_INTEGRATION.md, TINYBRAIN_SECURITY_TEMPLATES.md, ENHANCED_LANGUAGE_LIBRARY_PATTERNS.md) with one-line descriptions copied/adapted from README lines. > 13. docs/datasets/cwe-integration.md – Pull content (commands & mapping examples) from CWE_TINYBRAIN_INTEGRATION.md (load, search, standards mapping, compliance generation) verbatim where needed. > 14. docs/datasets/security-templates.md – Summaries of template usage & example commands from TINYBRAIN_SECURITY_TEMPLATES.md (session init, storing vulnerabilities/exploits/patterns/recommendations, relationships, report generation, pattern recognition workflow). > 15. docs/advanced-features.md – Context snapshots, task progress tracking, enhanced memory summarization (detailed bullet points from ADVANCED_FEATURES.md), performance section, future enhancements list EXACTLY as in that file (do not add unimplemented claims beyond placeholder embedding mention already in README). > 16. docs/integrations/cursor.md – Setup steps from CURSOR_SETUP.md (copy rules, user template, configure MCP servers, enforced usage, troubleshooting) trimmed for clarity but faithful. > 17. docs/integrations/ai-assistants.md – Consolidate AI assistant integration phases from AI_ASSISTANT_INTEGRATION.md (Cursor, Cline, Roo) and usage commands from AI assistant sections. > 18. docs/contributing.md – Contribution steps and development setup taken from README, plus mention of security/lint/test targets. > 19. docs/roadmap.md – Copy roadmap checklist items exactly as in README. > 20. docs/faq.md – Provide a short FAQ with answers strictly derivable (e.g., Where is data stored? (default path), How to reset DB? (db-reset), How to check health? (health_check), Is semantic search fully implemented? (embedding generation is a placeholder per repository code comment)). > > Accuracy Constraints: > - Performance metrics: only those listed (creation/search/relationship queries & size estimates). Mark clearly as current benchmark figures from README. > - Do NOT add claims about authentication, multi-user access (future item only appears in roadmap), encryption, or external model integrations beyond “foundation” / “placeholder” as stated. > - Embedding generation: clearly label as placeholder (hash-based) referencing repository code comment. > - Test coverage: README states “90%+ test coverage”; include that phrasing but italicize an advisory note suggesting users run `go test -cover` to verify. > > Styling Guidelines: > - Use level-1 heading per page (# Title) and consistent Table of Contents blocks where helpful. > - Prefer bullet lists; keep JSON examples fenced with ```json. > - No unsupported embellishments beyond standard GitHub Markdown. > > Navigation: > - In _config.yml configure just-the-docs theme with a primary nav order matching: Home, Getting Started, Configuration, Architecture, Memory Model, API, Workflows, Datasets, Advanced Features, Integrations, Contributing, Roadmap, FAQ. > > After adding files, ensure no existing files are modified except adding _config.yml. Do not remove or alter README.md. > > Acceptance Criteria: > - Build should pass (pure markdown additions + one YAML file). > - All tool names and examples match repository content. > - No speculative content beyond what source materials confirm. > > Implement these additions on a new branch named docs-site and open a pull request titled: "Add GitHub Pages documentation (docs site)" with a summary describing the new documentation structure and how to enable Pages (Settings -> Pages -> Build from /docs). >

💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.

rainmana and others added 25 commits October 7, 2025 21:12
@rainmana
Initial commit: TinyBrain LLM Memory Storage MCP Server
f9ee9e0 
- Complete MCP server implementation for security-focused LLM memory management
- SQLite backend with comprehensive schema for sessions, memories, relationships
- 19 MCP tools for session management, memory operations, context snapshots, task tracking
- Advanced features: context snapshots, memory summarization, task progress tracking
- Comprehensive test suite with unit tests, integration tests, and end-to-end tests
- Production-ready with error handling, logging, health checks, and statistics
- Security-focused design optimized for code reviews, penetration testing, exploit development
- Full documentation, examples, and configuration files
- Docker support and Makefile for easy building and deployment

Features:
- Session management for security assessments
- Memory storage with security categorization (vulnerabilities, findings, exploits, etc.)
- Advanced search with multiple strategies (semantic, exact, fuzzy, tag-based)
- Relationship mapping between related security issues
- Context snapshots with automatic memory summarization
- Multi-stage task progress tracking
- Access tracking and usage statistics
- Database health monitoring and comprehensive statistics
- Graceful FTS5 fallback for search functionality
- JSON-RPC 2.0 compliant MCP protocol implementation

Ready for VS Code integration and production use.
@rainmana
Update .gitignore to exclude server and tinybrain directories
a3d1cbf
@rainmana
Update repository references to use rainmana GitHub username
e9371a6 
- Updated README.md installation instructions to use github.com/rainmana/tinybrain
- Updated go.mod module path to github.com/rainmana/tinybrain
- Fixed all GitHub repository references to match the actual repository location
@rainmana
Add v1.0.0 release tag and improve installation instructions
4a60330 
- Added v1.0.0 Git tag for proper Go module versioning
- Updated README with multiple installation methods
- Added troubleshooting section for common installation issues
- Provided direct clone method as recommended approach
- Added solutions for authentication and module proxy issues
@rainmana
Fix all import paths to use rainmana GitHub username
986a299 
- Updated all import statements from github.com/alec/tinybrain to github.com/rainmana/tinybrain
- Fixed imports in cmd/server/main.go
- Fixed imports in all repository test files
- Fixed imports in memory_repository.go
- This resolves build issues when cloning the repository
@rainmana
Implement task progress update functionality in TinyBrainServer
f6e807e 
- Enhanced handleUpdateTaskProgress method to validate input parameters: session_id, task_name, stage, and status.
- Added logic to retrieve task ID based on session and task name.
- Integrated repository calls to update task progress and return the updated progress information.
- Improved error handling for missing parameters and task retrieval failures.
- Updated response format to provide meaningful feedback on task progress updates.
@rainmana
Add memory deduplication and similarity detection features
398a626 
- Implemented FindSimilarMemories method for finding similar content
- Implemented CheckForDuplicates method for duplicate detection
- Added find_similar_memories MCP tool with threshold parameter
- Added check_duplicates MCP tool for duplicate checking
- Fixed update_task_progress handler implementation
- Improved JSON response formatting in MCP server
- Added comprehensive duplicate detection with title, content, and partial matching
- Enhanced memory repository with similarity search capabilities

Features:
- Duplicate detection by exact title/content match
- Similarity search with configurable threshold
- Partial content matching for longer entries
- Priority and confidence-based ranking
- Session-scoped duplicate checking
@rainmana
Add export/import functionality and security templates
d42700a 
- Implemented ExportSessionData for complete session backup
- Implemented ImportSessionData for session restoration
- Added comprehensive security templates for common patterns:
  - Vulnerability templates (SQL injection, XSS, auth bypass, privilege escalation)
  - Exploit templates (SQL injection exploit, XSS exploit)
  - Technique templates (reconnaissance, enumeration)
  - Tool templates (vulnerability scanner, manual testing)
- Added CreateMemoryFromTemplate with placeholder replacement
- Added MCP tools for export/import and template functionality
- Fixed compilation errors and unused variables
- Enhanced memory repository with template-based memory creation

Features:
- Complete session data export/import with relationships and snapshots
- Predefined security templates with configurable placeholders
- Template-based memory creation for consistent documentation
- JSON-based data portability for backup and migration
@rainmana
Fix template creation type conversion error
7ff3578 
- Fixed interface conversion panic in CreateMemoryFromTemplate
- Added proper type handling for priority and confidence fields
- Template creation now works with both int and float64 types
- Successfully tested SQL injection template with placeholder replacement
- Export functionality working perfectly with complete session data
@rainmana
Implement comprehensive batch operations for bulk memory management
c3d634e 
- Added BatchCreateMemoryEntries for creating multiple memories in single transaction
- Added BatchUpdateMemoryEntries for updating multiple memories atomically
- Added BatchDeleteMemoryEntries for deleting multiple memories efficiently
- Added MCP tools: batch_create_memories, batch_update_memories, batch_delete_memories
- Fixed content_type constraint issues with proper defaults
- Enhanced transaction safety with proper rollback handling
- Added comprehensive logging for batch operations
- Now supports 27 total MCP tools for complete memory management

Features:
- Atomic batch operations with transaction safety
- Efficient bulk memory creation, updates, and deletion
- JSON-based batch request/response format
- Proper error handling and rollback on failures
- Comprehensive logging for audit trails
@rainmana
Implement comprehensive memory aging and cleanup policies
b2a2663 
- Added CleanupOldMemories for age-based memory removal
- Added CleanupLowPriorityMemories for priority/confidence-based cleanup
- Added CleanupUnusedMemories for access-based cleanup
- Added GetMemoryStats for comprehensive memory analytics
- Added MCP tools: cleanup_old_memories, cleanup_low_priority_memories, cleanup_unused_memories, get_memory_stats
- Implemented dry-run functionality for safe cleanup testing
- Added batch deletion with transaction safety
- Enhanced logging for cleanup operations
- Now supports 31 total MCP tools for complete memory lifecycle management

Features:
- Age-based cleanup (remove memories older than X days)
- Priority/confidence-based cleanup (remove low-value memories)
- Access-based cleanup (remove unused memories)
- Comprehensive memory statistics and analytics
- Safe dry-run mode for testing cleanup policies
- Batch processing for efficient large-scale cleanup
- Detailed logging and audit trails
@rainmana
Fix FTS5 warning by checking availability before initialization
8db53ec 
- Added FTS5 availability check using pragma_compile_options
- Changed warning to info message when FTS5 is not available
- Prevents unnecessary error logging for expected behavior
- Cleaner startup logs without confusing warnings
@rainmana
Implement comprehensive logging and debugging capabilities
efad40b 
- Added GetDetailedMemoryInfo for deep memory entry analysis
- Added GetSystemDiagnostics for comprehensive system health monitoring
- Added MCP tools: get_detailed_memory_info, get_system_diagnostics
- Enhanced debugging with relationship analysis and access patterns
- Added comprehensive system statistics and health monitoring
- Now supports 33 total MCP tools for complete system observability

Features:
- Detailed memory entry debugging with relationships and access patterns
- Comprehensive system diagnostics and health monitoring
- Database connection and performance statistics
- Memory usage analytics and aging information
- Session, relationship, and task statistics
- Recent activity monitoring and system info
- Complete observability for production debugging
@rainmana
Implement semantic search with embeddings support (placeholder)
a78b09b 
- Added SemanticSearch for AI-powered memory search capabilities
- Added GenerateEmbedding with hash-based placeholder implementation
- Added CalculateSemanticSimilarity with cosine similarity calculation
- Added StoreEmbedding for future vector database integration
- Added MCP tools: semantic_search, generate_embedding, calculate_similarity
- Now supports 36 total MCP tools for complete AI-enhanced memory management

Features:
- Semantic search using embeddings for conceptual similarity
- Embedding generation with placeholder hash-based implementation
- Cosine similarity calculation between embeddings
- Future-ready architecture for real AI model integration
- Complete foundation for OpenAI, Cohere, or local model integration
- Enhanced search capabilities beyond keyword matching
@rainmana
Complete TinyBrain with real-time notifications and comprehensive doc…
80d17c3 
…umentation

🎉 MAJOR MILESTONE: TinyBrain is now a complete, production-ready LLM memory system!

✅ Real-Time Notifications & Alerts System:
- Added notifications table with priority-based alerting
- High-priority memory alerts (priority ≥8, confidence ≥0.8)
- Duplicate detection notifications with similarity scores
- Cleanup operation notifications
- Notification management (mark as read, filter by session)
- 4 new MCP tools for notification handling

✅ Complete Documentation Update:
- Updated README with all 40 MCP tools organized by category
- Added AI-Enhanced Search & Intelligence section
- Added Real-Time Notifications & Alerts section
- Complete MCP tool reference with descriptions
- Comprehensive feature documentation

🏆 FINAL ACHIEVEMENT: 40 MCP Tools Total
- Core Memory Operations: 8 tools
- Session & Task Management: 6 tools
- Advanced Memory Features: 8 tools
- Security Templates & Batch Operations: 6 tools
- Memory Lifecycle & Cleanup: 4 tools
- AI-Enhanced Search: 3 tools
- Real-Time Notifications: 4 tools
- System Monitoring: 1 tool

TinyBrain is now a complete, enterprise-grade, AI-enhanced LLM memory management platform with real-time notifications, semantic search, comprehensive analytics, and production-ready features!
@rainmana
Add TinyBrain security assessment rules and user configuration templates
c142a92 
- Introduced comprehensive security assessment rules for TinyBrain usage, detailing mandatory practices for security code reviews, exploit development, penetration testing, and vulnerability research.
- Added user configuration template for customizing MCP server requirements, security assessment preferences, workflow preferences, and quality standards.
- Included a setup guide for initializing TinyBrain sessions and configuring MCP servers.
- Created test scenarios and prompt templates to facilitate effective security assessments using TinyBrain.

This update enhances the framework for conducting security assessments, ensuring consistent application of best practices and streamlined workflows.
@rainmana
Enhance authorization language with research-backed improvements
800cfec 
- Add professional credentials (CISSP, CEH, OSCP) to all configurations
- Include industry standards (NIST, ISO, OWASP, PTES) references
- Strengthen legal compliance and professional liability language
- Add defensive measures against prompt manipulation
- Create comprehensive authorization templates based on latest research
- Update all AI assistant configurations with enhanced convincing language
- Add professional context and ethical guidelines throughout

Based on research into AI prompt engineering for security assessments,
these enhancements should be significantly more convincing to LLMs
for legitimate security testing activities.
@rainmana
Add comprehensive security code review dataset and TinyBrain templates
e8e9052 
- Create SECURITY_CODE_REVIEW_DATASET.md with OWASP Top 10 2021 patterns
- Include CWE vulnerability patterns and exploitation techniques
- Add code smells, anti-patterns, and security testing templates
- Create TINYBRAIN_SECURITY_TEMPLATES.md with pre-configured memory templates
- Include OWASP and CWE-specific templates for consistent categorization
- Add TinyBrain integration commands and workflow examples
- Provide pattern recognition and relationship mapping capabilities
- Include authorization language throughout for legitimate security testing

This dataset provides comprehensive vulnerability patterns, exploitation techniques,
and security standards for professional security assessments using TinyBrain.
@rainmana
Add comprehensive multi-language security patterns
00154ed 
- Create MULTI_LANGUAGE_SECURITY_PATTERNS.md with 10 programming languages
- Include Java, C#, PHP, Ruby, Go, C/C++, TypeScript, and Rust patterns
- Add language-specific vulnerability patterns and exploitation techniques
- Provide TinyBrain integration templates for each language
- Cover SQL injection, authentication, deserialization, and memory safety issues
- Include both vulnerable and secure code examples for each pattern
- Add language-specific TinyBrain memory templates for consistent storage

This expands the security dataset to cover major programming languages
for comprehensive multi-language security assessments.
@rainmana
Update README.md with comprehensive security standards and source att…
7e7eccd 
…ribution

- Add Security Standards & Source Attribution section with OWASP, CWE, NIST, ISO compliance
- Include direct links to OWASP Code Review Guide and Secure Coding Dojo
- Add Security Datasets & Templates section with links to all security pattern files
- Document multi-language coverage for 10 programming languages
- Add comprehensive AI Assistant Configurations section
- Update Acknowledgments with security standards sources and technical dependencies
- Provide clear attribution to authoritative security sources and standards

This ensures proper attribution to OWASP, CWE, NIST, and other security standards
while providing clear links to source materials and comprehensive documentation.
@rainmana
Add comprehensive CWE security patterns dataset
0d8ee26 
- Create CWE_SECURITY_PATTERNS.md with CWE Top 25 Most Dangerous Software Errors
- Include 25+ critical CWE patterns with vulnerable and secure code examples
- Cover CWE-787 (Out-of-bounds Write), CWE-79 (XSS), CWE-20 (Input Validation)
- Add CWE-125 (Out-of-bounds Read), CWE-78 (Command Injection), CWE-89 (SQL Injection)
- Include CWE-416 (Use After Free), CWE-190 (Integer Overflow), CWE-352 (CSRF)
- Add CWE-22 (Path Traversal), CWE-494 (Code Download), CWE-362 (Race Conditions)
- Cover CWE-918 (SSRF), CWE-311 (Missing Encryption), CWE-74 (Injection)
- Include CWE-434 (File Upload), CWE-807 (Untrusted Input), CWE-250 (Privileges)
- Add CWE-863 (Incorrect Authorization), CWE-639 (Authorization Bypass)
- Include CWE-327 (Weak Crypto), CWE-306 (Missing Auth), CWE-862 (Missing Auth)
- Add CWE-732 (Incorrect Permissions), CWE-502 (Deserialization), CWE-798 (Hard-coded Creds)
- Include CWE-330 (Insufficient Randomness) and additional critical CWEs
- Provide TinyBrain integration templates for CWE-based vulnerability storage
- Include multi-language code examples (C, C++, Java, Python, JavaScript, PHP)
- Add both vulnerable and secure code patterns for each CWE
- Include severity ratings, exploitation techniques, and remediation guidance

This comprehensive CWE dataset provides complete coverage of the most dangerous
software errors for professional security assessments using TinyBrain.
@rainmana
Add LLM-optimized CWE dataset and integration guide
bb13082 
- Create CWE_LLM_DATASET.json with structured JSON format for LLM consumption
- Include CWE Top 25 Most Dangerous Software Errors with searchable indexes
- Add CWE_TINYBRAIN_INTEGRATION.md with efficient integration workflows
- Optimize for context window efficiency with severity, language, and category indexes
- Provide TinyBrain-ready templates and commands for CWE pattern storage
- Include correlation capabilities for pattern matching and standards mapping
- Add performance optimization strategies for memory management
- Update README.md with new CWE dataset links and descriptions

This LLM-optimized CWE dataset provides efficient, searchable, and context-aware
vulnerability patterns for professional security assessments using TinyBrain.
@rainmana
Implement enhanced language/library patterns and CVE mapping infrastr…
db011c3 
…ucture

- Create ENHANCED_LANGUAGE_LIBRARY_PATTERNS.md with framework-specific vulnerability patterns
- Add FRAMEWORK_LIBRARY_PATTERNS.json for LLM-optimized consumption
- Include 8 frameworks (Django, Flask, Express.js, React, Spring, ASP.NET Core, Laravel)
- Add 5 libraries (subprocess, pickle, child_process, MessageDigest, BinaryFormatter)
- Include disclaimers about evolving security landscape
- Add CVE mapping models (CVEMapping, RiskCorrelation, ComplianceMapping)
- Update database schema with new tables and indexes
- Add request/response types for new MCP tools
- Maintain LLM plug-and-play design with context-window efficiency

This expands security pattern coverage to include framework and library-specific
vulnerabilities while maintaining TinyBrain's core principles of speed and efficiency.
@rainmana
Add MIT License
21952bd
Initial plan
1d51fe6
Copilot AI and others added 2 commits October 8, 2025 19:46
@rainmana
Add core documentation pages and API reference
5a7ad2e 
Co-authored-by: rainmana <66031080+rainmana@users.noreply.github.com>
@rainmana
Add workflow and dataset documentation
baa4fdd 
Co-authored-by: rainmana <66031080+rainmana@users.noreply.github.com>
@rainmana
Add remaining documentation pages (advanced features, integrations, c…
dd9df1c 
…ontributing, roadmap, FAQ)

Co-authored-by: rainmana <66031080+rainmana@users.noreply.github.com>
Copilot AI changed the title [WIP] Add GitHub Pages documentation for TinyBrain Add GitHub Pages documentation (docs site) Oct 8, 2025
Copilot AI requested a review from rainmana October 8, 2025 20:00
@rainmana rainmana closed this Oct 24, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@rainmana rainmana Awaiting requested review from rainmana

Assignees

@rainmana rainmana

Copilot code review Copilot

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@rainmana