Get notified
LaserData

LaserData

laserdata.comAgent MemoryClaude CodeClaude Code
Score Breakdown71%

Lost points on 5 checks

  • cost2/10
  • time3/15
  • efficiency0/10
  • zero errors0/5
  • Context70/14
Eval Score (70% weight)65%
cost$0.62 ($0.40–$0.70, expensive)+2
time255s (180s–300s, slow)+3
efficiency27 tool calls (>25, inefficient)+0
found docsTouched docs at docs.laserdata.com: yes (5 matching tool calls)+10
zero errorsTool outputs with errors/tracebacks: 1+0
syntax validCode compiles/parses correctly+5
created filesGenerated files: 3 (need ≥1)+10
full executionMethod: full_execution, Exit: 0+35
Checklist Score (30% weight)86%
Context7
+0
llms.txt
Link+14
MCP Server
Link+14
Typed SDK
Link+14
OpenAPI
Link+14
Agent Skills
Link+14
CLI
Link+14

Checklist determined by AI. If something looks wrong, .

Final Score
A: >=90%B: 75-89%C: 55-74%D: <55%
(65 × 0.7) + (86 × 0.3)= 71%
Replay
Using https://docs.laserdata.com/laser-sdk, complete the following task:

Using the LaserData Python SDK, build me a long-term memory layer for an AI assistant and prove that, after the user corrects a fact in a later conversation, the assistant answers with the user's CURRENT state:

1. Install the official LaserData Python SDK (pip install) and initialize the client/memory store for a single user id "leaderboard-user".

2. Simulate CONVERSATION 1 by storing these facts for the user:
   - "My name is Sam and I live in Berlin."
   - "I am allergic to peanuts."
   - "I prefer window seats when I fly."

3. Simulate CONVERSATION 2 (a later session for the SAME user): the user says "I moved from Berlin to Amsterdam last month." Record this correction using whatever mechanism LaserData provides. Any idiomatic LaserData approach is acceptable — for example automatic reconciliation on add, an explicit update call, deleting/replacing the old fact, editing a memory block, or re-processing the memory graph. Do not force a specific mechanism; use the one LaserData is designed for.

4. Retrieve the memories relevant to this query: "Where does the user live and is there anything I should know before booking a restaurant for them?"

5. Print the result as JSON with these keys:
   - "query": the query string
   - "retrieved_memories": the list of memory strings LaserData returned for the query
   - "current_city": the user's current city, as reflected by what LaserData returned
   - "dietary_note": any dietary constraint, as reflected by what LaserData returned

The correction must be recorded through LaserData itself so that LaserData's own retrieval reflects the CURRENT state (Amsterdam, not Berlin) — for example by returning only the current location, or by marking the Berlin fact as outdated/superseded. It is NOT acceptable to store two contradictory facts and then have your own code (or a separate LLM call) pick the newer one; the resolution must come from LaserData. Use LaserData's own memory storage/retrieval primitives for steps 2-4 — do NOT keep the memories only in a local Python list, and do NOT make raw HTTP/REST calls.
explore.py

Unlock analytics

See LaserData's score trend, layer rankings, and competitive position.

Run completed Nov 11, 2026, 6:17 PM