| search_conversations | Full-text search across all conversation messages.
Args:
term: Search term (keyword). If empty with role="user", finds recent user questions.
limit: Max results (default 15)
role: Filter by role — "user" for your words, "assistant" for AI responses.
With role="user" and empty term, returns recent questions asked.
|
| get_conversation | Get the full content of a specific conversation by ID.
Use search_conversations() first to find conversation IDs.
|
| conversations_by_date | Get conversations from a specific date (YYYY-MM-DD format). |
| semantic_search | Search conversations using semantic similarity (vector embeddings).
Finds messages that are conceptually similar to your query,
even if they don't contain the exact words. More powerful than keyword search for finding related ideas. |
| search_summaries | Search conversation summaries with hybrid vector + keyword search.
Args:
query: Search query
extract: What to extract from results:
- "summary" (default): Full summary with metadata
- "questions": Open questions from matching conversations
- "decisions": Decisions made in matching conversations
- "quotes": Quotable phrases from matching conversations
limit: Max results (default 10)
domain: Filter by domain (e.g. "ai-dev", "business-strategy")
importance: Filter by importance ("breakthrough", "significant", "routine")
thinking_stage: Filter by stage ("exploring", "crystallizing", "refining", "executing")
source: Filter by source ("claude-code", "chatgpt", etc.)
mode: Search mode — "hybrid" (default), "vector", "fts"
|
| unified_search | Search across ALL sources: conversations, GitHub, markdown.
Returns integrated timeline of thinking on a topic.
|
| search_docs | Search markdown corpus and IP documents with various filters.
Args:
query: Search query (keyword for markdown, semantic for IP docs)
filter: What to search/filter:
- None (default): Keyword search on markdown corpus
- "ip": Vector search on curated IP documents
- "breakthrough": Documents with BREAKTHROUGH energy
- "deep": High depth-score documents
- "project": Documents for a specific project
- "todos": Documents with open TODOs
project: Project name (used with filter="project" or filter="todos")
limit: Max results (default 15)
min_depth: Minimum depth score (used with filter="deep", default 70)
|
| what_do_i_think | Synthesize what you think about a topic, or find similar past situations.
Args:
topic: The topic or situation to analyze
mode: Analysis mode:
- "synthesize" (default): Full synthesis with decisions, open questions, quotes
- "precedent": Find similar past situations with context and decisions made
|
| alignment_check | Check if a decision aligns with your principles.
Searches principles file and semantic history for guidance. |
| thinking_trajectory | Track the evolution of thinking about a topic over time.
Args:
topic: The concept/term to track
view: What to show:
- "full" (default): Complete trajectory with genesis, temporal pattern, semantic matches, thinking stages
- "velocity": How often the concept appears over time with trend analysis
- "first": When the concept first appeared — the genesis moment
|
| what_was_i_thinking | Time-travel snapshot: What was on your mind during a specific month?
Format: YYYY-MM (e.g., '2024-08')
|
| brain_stats | Brain overview, domain distribution, and thinking pulse.
Args:
view: What to display:
- "overview" (default): Stats across all data sources
- "domains": Domain breakdown with counts, %, breakthroughs, top concepts
- "pulse": Domain × thinking_stage matrix — what's crystallizing vs exploring
- "conversations": Detailed conversation stats
- "embeddings": Embedding coverage stats
- "github": Repository and commit stats
- "markdown": Document corpus stats
|
| unfinished_threads | Find conversations worth revisiting: exploring/crystallizing stage with open questions.
|
| tunnel_state | Reconstruct cognitive save-state for a domain — where you left off.
Returns: thinking stage, open questions, decisions, concepts, emotional tone.
The 'load game' button for your mind.
|
| dormant_contexts | Find abandoned tunnels — domains with open questions you haven't resolved.
The 'what have I forgotten?' alarm. |
| context_recovery | Full 'waking up' brief for re-entering a domain.
Returns recent summaries + accumulated state — everything needed to resume work.
The prosthetic's core value: making re-entry cheap.
|
| tunnel_history | Meta-view of your engagement with a domain over time.
Shows total conversations, thinking stage distribution, importance peaks,
and cognitive patterns. |
| switching_cost | Estimate cognitive cost of switching between domains.
Factors: open questions left behind, shared concepts (overlap discount).
Returns 0-1 score where lower = cheaper switch.
|
| cognitive_patterns | Analyze cognitive patterns and problem-solving approaches.
Answers: 'When do I think best?' with data.
|
| open_threads | Global inventory of ALL open questions across ALL domains.
The 'unfinished business' dashboard. |
| trust_dashboard | System-wide stats proving the prosthetic works.
Shows everything that's preserved: conversations, domains, questions, decisions.
The 'everything is okay' view.
|
| github_search | Search GitHub repos, commits, and cross-reference with conversations.
Args:
query: Search query (used for code semantic search or as conversation_id for validate mode)
project: Project/repo name (used for timeline and conversations modes)
mode: Search mode:
- "timeline" (default): Project creation date, commits, activity windows
- "conversations": Find conversations mentioning a project
- "code": Semantic search across commits AND conversations
- "validate": Check conversation date validity via GitHub evidence.
Pass conversation_id as query.
limit: Max results (default 10)
|
| query_analytics | Query analytics across timeline, tool stacks, problem resolution,
spend, and conversation summary.
Args:
view: What to analyze:
- "timeline" (default): What happened on a specific date
- "stacks": Technology stack patterns over time
- "problems": Debugging and problem resolution patterns
- "spend": Cost breakdown by source/time
- "summary": Comprehensive conversation analysis summary
date: Date in YYYY-MM-DD format (used with view="timeline")
month: YYYY-MM filter (used with stacks, problems, spend views)
source: Source filter for spend (e.g., "openrouter", "claude_code")
limit: Max results (default 15)
|
| list_principles | List your configured principles.
Principles are loaded from the YAML/JSON file specified in config.toml. |
| get_principle | Get detailed info about a specific principle. |
