Openexp
未认领Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land (deal closed, sprint shipped). Hooks + MCP server for Claude Code, Qdrant + FastEmbed local-first.
ai-agentsclaudeclaude-codeepisodic-memoryllm-toolsmcpmemoryqdranttrajectorydecision-extraction
工具（17 个）
actual_signal
yes
add_memory
Store a memory. Supports clientid for entity tagging
applied_action
yes
case_id
yes
cited_step
yes
days_to_resolve
yes
expected_signal
yes
expected_window_days
yes
log_outcome
Resolve a prediction with the observed signal — interpretation-free record.
log_prediction
Log a pack-grounded prediction. Required when an installed experience pack cites a specific relativeday as the basis for an action recommendation.
memory_stats
Collection stats: point counts by source/type, session count
notes
optional
pack_author
yes
pack_id
yes
prediction_id
yes
prevented_action
optional
search_memory
Hybrid search: semantic similarity + BM25 + recency