Tenets

Sessions & Guiding Principles (Tenets)

The killer feature: define guiding principles once, and they'reautomatically injected into every prompt.

# Create a working session tenets session create payment-feature # Add guiding principles (tenets) — these auto-inject into all prompts tenets tenet add "Always validate user inputs before database operations" --priority critical tenets tenet add "Use Decimal for monetary calculations, never float" --priority high tenets tenet add "Log all payment state transitions" --priority medium # Pin critical files (guaranteed inclusion in context) tenets session pin-file payment-feature src/core/payment.py # Instill tenets to the session tenets instill --session payment-feature # Now every distill automatically includes your tenets + pinned files tenets distill "add refund flow" --session payment-feature # Output includes: relevant code + your 3 guiding principles

Why this matters:In long AI conversations, context drifts. The AI forgets your coding standards. Tenets solve this by re-injecting your rules every time.

# Visualize architecture tenets viz deps --output architecture.svg # Dependency graph tenets viz deps --format html -o deps.html # Interactive HTML # Track development patterns tenets chronicle --since "last week" # Git activity tenets momentum --team # Sprint velocity # Analyze codebase tenets examine . --complexity --threshold 10 # Find complex code

ranking: algorithm: balanced # fast | balanced | thorough threshold: 0.1 use_git: true # Use git signals for relevance context: max_tokens: 100000 output: format: markdown copy_on_distill: true # Auto-copy to clipboard ignore: - vendor/ - '.generated.'

tenets employs a multi-layered approach optimized specifically for code understanding (but its core functionality could be applied to any field of document matching). It tokenizescamelCaseandsnake_caseidentifiers intelligently. Test files are excluded by default unless specifically mentioned in some way. Language-specific AST parsing for15+ languagesis included.

Semantic understand can be had with ML features:pip install tenets[ml]. Enable with--ml --rerankerflags or setuse_ml: trueanduse_reranker: truein config.

Inthoroughmode, sentence-transformer embeddings are enabled, andunderstandthatauthenticate()andlogin()are conceptually related for example, and thatpaymenteven has some crossover in relevancy (since these are typically associated together).

Optional cross-encoder neural re-rankingin this mode jointly evaluates query-document pairs with self-attention for superior accuracy.

A cross-encoder, for example, will correctly rank"DEPRECATED: We no longer implement oauth2"lower thanimplement_authorization_flow()for query"implement oauth2", understanding the negative context despite keyword matches.

Since cross-encoders process document-query pairs together (O(n²) complexity), they're much slower than bi-encoders and only used for re-ranking top K results.

- Full Documentation- Complete guide and API reference
- CLI Reference- All commands and options
- Configuration Guide- Detailed configuration options
- Architecture Overview- How tenets works internally

# Markdown (default, optimized for AI) tenets distill "implement OAuth2" --format markdown # Interactive HTML with search, charts, copy buttons tenets distill "review API" --format html -o report.html # JSON for programmatic use tenets distill "analyze" --format json | jq '.files[0]' # XML optimized for Claude tenets distill "debug issue" --format xml

from tenets import Tenets # Initialize tenets = Tenets() # Basic usage result = tenets.distill("implement user authentication") print(f"Generated {result.token_count} tokens") # Rank files without content from tenets.core.ranking import RelevanceRanker ranker = RelevanceRanker(algorithm="balanced") ranked_files = ranker.rank(files, prompt_context, threshold=0.1) for file in ranked_files[:10]: print(f"{file.path}: {file.relevance_score:.3f}")

Specialized analyzers for Python, JavaScript/TypeScript, Go, Java, C/C++, Ruby, PHP, Rust, and more. Configuration and documentation files are analyzed with smart heuristics for YAML, TOML, JSON, Markdown, etc.

Documentation·MCP Guide·Privacy·Terms

An open-source MCP server that integrates with Google's Gemini AI. Requires a Google Gemini API key.