observe
Store observation with auto-summarization, importance scoring, entity extraction, topic detection
recall
Retrieve verbatim content by filter (importance, type, flag, time)
search
Hybrid search (BM25 + vector + optional LLM judge)
ask
Natural language Q&A over the full memory store
timeline
Reverse-chronological observations with importance badges and flags
stats
Token economics for current session (raw vs. compressed)
save_knowledge
Save a knowledge entry with contradiction detection + temporal validity windows
search_knowledge
Search (superseded entries filtered by default)
promote_knowledge
Promote to global cross-project store
global_search
Search across all projects simultaneously
resolve_contradiction
Resolve knowledge conflicts (supersede / merge / keep / archive)
merge_suggestions
View cross-project duplicate suggestions
graph_query
Traverse entity relationships
add_relationship
Link entities with typed relationships
graph_neighbors
Find connected entities (configurable depth)
temporal_query
Query what was true at a specific point in time
time_travel
Compare project state at two arbitrary timestamps
explain_decision
Walk evidence chain backward to reconstruct why a decision was made
predict_loss
Identify observations at risk of compression/deletion
generate_story
Generate PR description, standup update, ADR, or onboarding guide
entity_detect
Detect entities in arbitrary text
find_tunnels
Find cross-project topic connections
wake_up
Token-budgeted context primer for session start
restore_session
Restore session from checkpoint
handoff_session
Cross-session continuity package
agent_register
Register an agent with role and capabilities
agent_status
Check all active agents and their claimed resources
claim_files
Claim files to prevent parallel-agent conflicts
agent_broadcast
Broadcast a finding to all agents in the project
configure
Update runtime configuration
budget_status
Token budget management
budget_configure
Token budget management
summarize
Summarize content without storing (one-shot)
execute
Run code (JS, TS, Python, Shell, Ruby, Go, Rust, PHP, Perl, R, Elixir)
index_content
Index with code-aware chunking
search_content
Search indexed chunks
list_people
Browse entities and topics
list_topics
Browse entities and topics
import_conversations
Import conversation history
browse
Retrieve observations by person, entity, or topic
diagnostics
Error log, pipeline stats, storage health