OSINT OpenEnv Space

A containerized OpenEnv-compatible benchmark for synthetic OSINT reasoning over profiles, forum threads, posts, aliases, organizations, locations, and event links.

The Space boots with the fixed-level benchmark so visitors get a stable environment snapshot instead of a different graph every restart.

Open Dashboard Environment JSON

Included Snapshot

Tasks
30
Provider
mock
Score
0.603
Success
1.000

Action Space

  • CALL_TOOL: query platform views or semantic memory.
  • ADD_EDGE: add a hypothesized relation to the working graph.
  • ANSWER: submit the final node id answer.

Difficulty Mix

  • easy: 10
  • hard: 10
  • medium: 10

Task Families

  • easy_trace
  • hard_trace
  • medium_trace